tags, highlighting the changes. Begin with a concise introduction, then proceed with the sections as outlined above.\n",
" Your work will be evaluated for comprehensive and detailed updates to the persona.\n",
+ " \"\"\"\n",
" unwrap: true\n",
"\n",
- "# Create a new persona document\n",
+ "# Step 8: Create a new persona document\n",
"- tool: create_user_doc\n",
" arguments:\n",
- " user_id: outputs[3]['user']['id']\n",
+ " user_id: $ steps[3].output.user['id']\n",
" data:\n",
- " title: \"'User Persona'\"\n",
- " content: _\n",
+ " title: User Persona\n",
+ " content: $ _\n",
"\n",
- "# Update the about section of the user with the new persona\n",
+ "# Step 9: Update the about section of the user with the new persona\n",
"- tool: update_user\n",
" arguments:\n",
- " user_id: outputs[3]['user']['id']\n",
- " name: outputs[3]['user']['name']\n",
- " about: outputs[7]\n",
+ " user_id: $ steps[3].output.user['id']\n",
+ " name: $ steps[3].output.user['name']\n",
+ " about: $ steps[7]\n",
"''')\n",
"\n",
"# creating the task object\n",
@@ -1280,8 +1429,26 @@
" task_id=TASK_UUID_3,\n",
" agent_id=AGENT_UUID,\n",
" **task_def_3,\n",
- ")\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Creating an Execution\n",
+ "\n",
+ "An execution is a single run of a task. It is a way to run a task with a specific set of inputs.\n",
"\n",
+ "To learn more about executions, please refer to the `Executions` section in [Julep Concepts](https://docs.julep.ai/docs/concepts/execution)."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
"execution_3 = client.executions.create(\n",
" task_id=TASK_UUID_3,\n",
" input={\n",
@@ -1291,6 +1458,22 @@
")"
]
},
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Checking execution details and output\n",
+ "\n",
+ "There are multiple ways to get the execution details and the output:\n",
+ "\n",
+ "1. **Get Execution Details**: This method retrieves the details of the execution, including the output of the last transition that took place.\n",
+ "\n",
+ "2. **List Transitions**: This method lists all the task steps that have been executed up to this point in time, so the output of a successful execution will be the output of the last transition (first in the transition list as it is in reverse chronological order), which should have a type of `finish`.\n",
+ "\n",
+ "\n",
+ "Note: You need to wait for a few seconds for the execution to complete before you can get the final output, so feel free to run the following cells multiple times until you get the final output.\n"
+ ]
+ },
{
"cell_type": "code",
"execution_count": 21,
@@ -1516,7 +1699,7 @@
"persona_doc = client.users.docs.list(user_id=USER_ID).items[0]\n",
"\n",
"print(\"User docs: \")\n",
- "print(persona_doc.content[0])\n"
+ "print(persona_doc.content[0])"
]
}
],
diff --git a/cookbooks/10-crawling-and-rag.ipynb b/cookbooks/10-crawling-and-rag.ipynb
deleted file mode 100644
index ceddc5f41..000000000
--- a/cookbooks/10-crawling-and-rag.ipynb
+++ /dev/null
@@ -1,1864 +0,0 @@
-{
- "cells": [
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "\n",
- "
![\"julep\"](\"https://socialify.git.ci/julep-ai/julep/image?description=1&descriptionEditable=Rapidly%20build%20AI%20workflows%20and%20agents&font=Source%20Code%20Pro&logo=https%3A%2F%2Fraw.githubusercontent.com%2Fjulep-ai%2Fjulep%2Fdev%2F.github%2Fjulep-logo.svg&owner=1&forks=1&pattern=Solid&stargazers=1&theme=Auto\")
\n",
- "
\n",
- "
\n",
- " Explore Docs (wip)\n",
- " ·\n",
- " Discord\n",
- " ·\n",
- " 𝕏\n",
- " ·\n",
- " LinkedIn\n",
- "
\n",
- "\n",
- "\n",
- " ![\"NPM](\"https://img.shields.io/npm/v/%40julep%2Fsdk?style=social&logo=npm&link=https%3A%2F%2Fwww.npmjs.com%2Fpackage%2F%40julep%2Fsdk\")
\n",
- " \n",
- " ![\"PyPI](\"https://img.shields.io/pypi/v/julep?style=social&logo=python&label=PyPI&link=https%3A%2F%2Fpypi.org%2Fproject%2Fjulep\")
\n",
- " \n",
- " ![\"Docker](\"https://img.shields.io/docker/v/julepai/agents-api?sort=semver&style=social&logo=docker&link=https%3A%2F%2Fhub.docker.com%2Fu%2Fjulepai\")
\n",
- " \n",
- " ![\"GitHub](\"https://img.shields.io/github/license/julep-ai/julep\")
\n",
- "
\n",
- "\n",
- "## Task Definition: Crawling and RAG\n",
- "\n",
- "### Overview\n",
- "\n",
- "This task implements an automated system to index and process certain website. The system crawls a website, extracts relevant information, and creates a searchable knowledge base that can be queried programmatically.\n",
- "\n",
- "### Task Tools:\n",
- "\n",
- "- **spider_crawler**: Web crawler component for systematically traversing the website\n",
- "- **create_agent_doc**: Document processor for converting web content into indexed, searchable documents\n",
- "\n",
- "### Task Input:\n",
- "\n",
- "Required parameter:\n",
- "- **url**: Entry point URL for the crawler (e.g., \"https://julep.ai/\")\n",
- "\n",
- "### Task Output:\n",
- "\n",
- "- Indexed knowledge base containing processed website\n",
- "- Query interface for programmatic access to the crawled information\n"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Implementation\n",
- "\n",
- "To recreate the notebook and see the code implementation for this task, you can access the Google Colab notebook using the link below:\n",
- "\n",
- "\n",
- " ![\"Open](\"https://colab.research.google.com/assets/colab-badge.svg\")
\n",
- "\n",
- "\n",
- "### Additional Information\n",
- "\n",
- "For more details about the task or if you have any questions, please don't hesitate to contact the author:\n",
- "\n",
- "**Author:** Julep AI \n",
- "**Contact:** [hey@julep.ai](mailto:hey@julep.ai) or Discord"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "Installing the Julep Client"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# Install the Julep SDK\n",
- "!pip install --upgrade julep --quiet"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "#### NOTE:\n",
- "\n",
- "- UUIDs are generated for both the agent and task to uniquely identify them within the system.\n",
- "- Once created, these UUIDs should remain unchanged for simplicity.\n",
- "- Altering a UUID will result in the system treating it as a new agent or task.\n",
- "- If a UUID is changed, the original agent or task will continue to exist in the system alongside the new one."
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 1,
- "metadata": {},
- "outputs": [],
- "source": [
- "# Global UUID is generated for agent and task\n",
- "from dotenv import load_dotenv\n",
- "from julep import Client\n",
- "import os\n",
- "\n",
- "load_dotenv(override=True)\n",
- "\n",
- "# Set your API keys\n",
- "JULEP_API_KEY = os.getenv(\"JULEP_API_KEY\")\n",
- "\n",
- "# Create a Julep client\n",
- "client = Client(api_key=JULEP_API_KEY, environment=\"production\")"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Creating an \"agent\"\n",
- "\n",
- "Agent is the object to which LLM settings, like model, temperature along with tools are scoped to.\n",
- "\n",
- "To learn more about the agent, please refer to the [documentation](https://github.com/julep-ai/julep/blob/dev/docs/julep-concepts.md#agent)."
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 2,
- "metadata": {},
- "outputs": [],
- "source": [
- "# Create agent\n",
- "agent = client.agents.create(\n",
- " name=\"Website Crawler\",\n",
- " about=\"An AI assistant that can crawl any website and create a knowledge base.\",\n",
- " model=\"gpt-4o\",\n",
- ")"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 3,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Number of documents in the agent's document store: 0\n"
- ]
- }
- ],
- "source": [
- "num_docs = len(client.agents.docs.list(agent_id=agent.id, limit=100).items)\n",
- "print(f\"Number of documents in the agent's document store: {num_docs}\")"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Defining a Task\n",
- "\n",
- "Tasks in Julep are Github-Actions-style workflows that define long-running, multi-step actions.\n",
- "\n",
- "You can use them to conduct complex actions by defining them step-by-step.\n",
- "\n",
- "To learn more about tasks, please refer to the `Tasks` section in [Julep Concepts](https://github.com/julep-ai/julep/blob/dev/docs/julep-concepts.md#tasks)."
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 4,
- "metadata": {},
- "outputs": [],
- "source": [
- "import yaml\n",
- "\n",
- "task_def = yaml.safe_load(f\"\"\"\n",
- "name: Crawl a website and create a agent document\n",
- "\n",
- "# Define the tools that the agent will use in this workflow\n",
- "tools:\n",
- "- name: spider_crawler\n",
- " type: integration\n",
- " integration:\n",
- " provider: spider\n",
- " method: crawl\n",
- " setup:\n",
- " spider_api_key: \"{os.getenv('SPIDER_API_KEY')}\"\n",
- "\n",
- "- name : create_agent_doc\n",
- " description: Create an agent doc\n",
- " type: system\n",
- " system:\n",
- " resource: agent\n",
- " subresource: doc\n",
- " operation: create\n",
- "\n",
- "index_page:\n",
- "\n",
- "- evaluate:\n",
- " documents: _['content']\n",
- "\n",
- "- over: \"[(_0.content, chunk) for chunk in _['documents']]\"\n",
- " parallelism: 3\n",
- " map:\n",
- " prompt: \n",
- " - role: user\n",
- " content: >-\n",
- " \n",
- " {{{{_[0]}}}}\n",
- " \n",
- "\n",
- " Here is the chunk we want to situate within the whole document\n",
- " \n",
- " {{{{_[1]}}}}\n",
- " \n",
- "\n",
- " Please give a short succinct context to situate this chunk within the overall document for the purposes of improving search retrieval of the chunk. \n",
- " Answer only with the succinct context and nothing else. \n",
- " \n",
- " unwrap: true\n",
- " settings:\n",
- " max_tokens: 16000\n",
- "\n",
- "- evaluate:\n",
- " final_chunks: |\n",
- " [\n",
- " NEWLINE.join([chunk, succint]) for chunk, succint in zip(_1.documents, _)\n",
- " ]\n",
- "\n",
- "# Create a new document and add it to the agent docs store\n",
- "- over: _['final_chunks']\n",
- " parallelism: 3\n",
- " map:\n",
- " tool: create_agent_doc\n",
- " arguments:\n",
- " agent_id: \"'{agent.id}'\"\n",
- " data:\n",
- " metadata:\n",
- " source: \"'spider_crawler'\"\n",
- "\n",
- " title: \"'Website Document'\"\n",
- " content: _\n",
- "\n",
- "# Define the steps of the workflow\n",
- "main:\n",
- "\n",
- "# Define a tool call step that calls the spider_crawler tool with the url input\n",
- "- tool: spider_crawler\n",
- " arguments:\n",
- " url: \"_['url']\" # You can also use 'inputs[0]['url']'\n",
- " params:\n",
- " request: \"'smart_mode'\"\n",
- " limit: _['pages_limit'] # <--- This is the number of pages to crawl (taken from the input of the task)\n",
- " return_format: \"'markdown'\"\n",
- " proxy_enabled: \"True\"\n",
- " filter_output_images: \"True\" # <--- This is to execlude images from the output\n",
- " filter_output_svg: \"True\" # <--- This is to execlude svg from the output\n",
- " # filter_output_main_only: \"True\"\n",
- " readability: \"True\" # <--- This is to make the output more readable\n",
- " sitemap: \"True\" # <--- This is to crawl the sitemap\n",
- " chunking_alg: # <--- Using spider's bysentence algorithm to chunk the output\n",
- " type: \"'bysentence'\"\n",
- " value: \"15\" # <--- This is the number of sentences per chunk\n",
- "\n",
- "# Evaluate step to document chunks\n",
- "- foreach:\n",
- " in: _['result']\n",
- " do:\n",
- " workflow: index_page\n",
- " arguments:\n",
- " content: _.content\n",
- "\"\"\")\n"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "Notes:\n",
- "- The reason for using the quadruple curly braces `{{{{}}}}` for the jinja template is to avoid conflicts with the curly braces when using the `f` formatted strings in python. [More information here](https://stackoverflow.com/questions/64493332/jinja-templating-in-airflow-along-with-formatted-text)\n",
- "- The `unwrap: True` in the prompt step is used to unwrap the output of the prompt step (to unwrap the `choices[0].message.content` from the output of the model).\n"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Creating a task"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 5,
- "metadata": {},
- "outputs": [],
- "source": [
- "# Create the task\n",
- "task = client.tasks.create(\n",
- " agent_id=agent.id,\n",
- " **task_def\n",
- ")"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Creating an Execution (Starting from the Homepage)\n",
- "\n",
- "An execution is a single run of a task. It is a way to run a task with a specific set of inputs."
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 10,
- "metadata": {},
- "outputs": [],
- "source": [
- "execution = client.executions.create(\n",
- " task_id=task.id,\n",
- " input={\n",
- " \"url\": \"https://julep.ai/\",\n",
- " \"pages_limit\": 5,\n",
- " }\n",
- ")"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Checking execution details and output\n",
- "\n",
- "There are multiple ways to get the execution details and the output:\n",
- "\n",
- "1. **Get Execution Details**: This method retrieves the details of the execution, including the output of the last transition that took place.\n",
- "\n",
- "2. **List Transitions**: This method lists all the task steps that have been executed up to this point in time, so the output of a successful execution will be the output of the last transition (first in the transition list as it is in reverse chronological order), which should have a type of `finish`.\n",
- "\n",
- "\n",
- "Note: You need to wait for a few seconds for the execution to complete before you can get the final output, so feel free to run the following cells multiple times until you get the final output.\n"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 12,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Execution status: succeeded\n"
- ]
- }
- ],
- "source": [
- "status = client.executions.get(execution_id=execution.id).status\n",
- "\n",
- "print(\"Execution status: \", status)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 13,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Index: 0 Type: init\n",
- "output: {\n",
- " \"url\": \"https://julep.ai/\",\n",
- " \"pages_limit\": 5\n",
- "}\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 1 Type: step\n",
- "output: {\n",
- " \"result\": [\n",
- " {\n",
- " \"url\": \"https://julep.ai/\",\n",
- " \"costs\": {\n",
- " \"ai_cost\": 0,\n",
- " \"file_cost\": 0.0004,\n",
- " \"total_cost\": 0.0006,\n",
- " \"compute_cost\": 0.0001,\n",
- " \"transform_cost\": 0.0001,\n",
- " \"bytes_transferred_cost\": 0\n",
- " },\n",
- " \"error\": null,\n",
- " \"status\": 200,\n",
- " \"content\": [\n",
- " \"[\\n](./)\\n[\\nDocs\\n](https://docs.julep.ai/)\\n[\\nGithub\\n](https://github.com/julep-ai/julep)\\n[\\nDashboard\\n](https://dashboard.julep.ai/agents/)\\nExamples\\n[\\nDiscord\\n](https://discord.gg/2EUJzJU2Yt)\\n[\\nBook demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nContact Us\\n](./contact)\\n[\\n](./)\\n[\\n](./)\\nAnnouncing our Education+NGO program Eligible organizations get unlimited free credits Please apply[here](https://forms.gle/CCP6sDYeUfAXdUoi7) [](https://www.producthunt.com/posts/julep-ai)\\nOpen Source\\n[\\nGithub\\n\\u26054.4K\\n](https://github.com/julep-ai/julep)\\n# Buildscalable\\nAIworkflows\\ninminutes\\nAPI to build multi-step agent workflows\\n[\\nDeploy your first agent\\n](https://dashboard-dev.julep.ai/)\\n[\\nDeploy your first agent\\n](https://dashboard-dev.julep.ai/)\\n[\\nGet a demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nGet a demo\\n](< https://calendly.com/ishita-julep>)\\nCUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place CUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place CUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place ## Connect with any AI model,\\nAPI or data source\\nSeamlessly integrate with your existing stack and favorite AI models LLM Platforms\\nLanguages\\nIntegrations\\n* * * * * * Any REST API\\n## Real people, Real results\\n* Julep to me sits in the intersection of what Zapier did for simplifying workflows, and what Vercel did for simplifying shipping The new possibilities are endless I am excited abut what all can be done with this tech at ES Suryansh Tibarewal\\nCEO, EssentiallySports\\n* For Vidyo, we shipped 6 months worth of product development in 6 hours GAME CHANGER!\",\n",
- " \"Vedant Maheshwari\\nCEO, Vidyo.ai\\n* We tried building our ai stack where we needed simple automated computer use we spent months trying to get it right, but our development time got cut to a couple weeks because most of the infra orchestration was handled by julep all that we had to do was refine our prompts\\nMadhavan\\nCEO, Reclaim Protocol\\n* \\\"Same experience as reviewing designs on Figma with my designer Sat with my developer once, and we kept brainstorming, testing, prototyping and shipping at once I got control back in my hands as a non-developer.\\\"\\nAkshay Pruthi\\nCEO, Calm Sleep\\n* Working with Julep accelerated Ukumi, by enabling us to focus on our core strengths and letting Julep navigate the complex web of calls to ai models we could do more with less Sachin Gaur\\nCofounder, Ukumi AI\\n### Build with Julep\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\nDeploy\\nExecute production-grade workflows with one command\\nagent = julep.agents.create(\\nname=\\\"Spiderman\\\",\\nabout=\\\"AI that can crawl the web and extract data\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\ndefault\\\\_settings={\\n\\\"temperature\\\":0.75,\\n\\\"max\\\\_tokens\\\":10000,\\n\\\"top\\\\_p\\\":1.0,\\n}\\n)\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\njulep.agents.tools.create(\\nagent\\\\_id=agent.id,\\nname=\\\"my\\\\_weather\\\\_tool\\\",\\nintegration={\\n\\\"provider\\\":\\\"weather\\\",\\n\\\"setup\\\": {\\n\\\"openweathermap\\\\_api\\\\_key\\\":\\\"OPENWEATHERMAP\\\\_API\\\\_KEY\\\"\\n}\\n}\\n)\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\niimportyaml\\ntask =julep.task.create(\\\"\\\"\\\"\\nname: Weather Reporting Task\\nmain:\\n- tool: spider\\\\_crawler\\narguments:\\nurl: \\\\_.url\\n- prompt: |\\nHere\\u2019s a crawl of {{inputs[0].url}}:\\n{{\\\\_.documents}}\\nCreate a short summary (\\\\~100 words) of the website \\\"\\\"\\\")- city\\nDeploy\\nExecute production-grade workflows with one command\\nexecution = julep.executions.create(\\ntask\\\\_id=task.id,\\ninput={\\n\\\"url\\\": \\\"https://spider.cloud\\\"\\n}\\n)\\nagent = julep.agents.create(\\nname=\\\"Cristopher\\\",\\nabout=\\\"An agent specialized in weather reporting\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\n)\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\nDeploy\\nExecute production-grade workflows with one command\\nagent = julep.agents.create(\\nname=\\\"Spiderman\\\",\\nabout=\\\"AI that can crawl the web and extract data\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\ndefault\\\\_settings={\\n\\\"temperature\\\":0.75,\\n\\\"max\\\\_tokens\\\":10000,\\n\\\"top\\\\_p\\\":1.0,\\n}\\n)\\n## Build AI pipelines\\nin minutes Scale to millions Rapid Prototyping\\n\\\"From idea to demo in minutes\\\" using built-in RAG and state management\\nProduction Ready\\n\\\"Go live instantly with managed infrastructure\\\" and features such as long-running tasks, automatic retries and error handling\\nModular Design\\n\\\"Build features like Lego blocks\\\" by connecting to any external API, switch between LLMs and add custom tools\\nInfinite Scale\\nHandle millions of concurrent users with automatic scaling and load balancing\\nFuture Proof\\n\\\"Add new AI models anytime\\\" \\\"Integrate with any new tool or API\\\"\\nComplete Control\\n\\\"Full visibility into AI operations\\\" \\\"Manage costs and performance easily\\\"\\n## Questions Answers What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks\",\n",
- " \"It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching\",\n",
- " \"-Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing -Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching -Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing -Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement\",\n",
- " \"How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching -Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing.-Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks\",\n",
- " \"How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks ### Build faster using Julep API\\n### Deploy multi-step workflows easily with\\n### built-in tools and\\n### state management that is\\n### production ready from day one Keep me informed\\n### Build faster using Julep API\\n### Deploy multi-step workflows easily with built-in tools and State management that is production ready from day one Keep me informed\\nKeep me informed\\nKeep me informed\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\"\n",
- " ]\n",
- " },\n",
- " {\n",
- " \"url\": \"https://julep.ai/about\",\n",
- " \"costs\": {\n",
- " \"ai_cost\": 0,\n",
- " \"file_cost\": 0.0001,\n",
- " \"total_cost\": 0.0003,\n",
- " \"compute_cost\": 0.0001,\n",
- " \"transform_cost\": 0.0001,\n",
- " \"bytes_transferred_cost\": 0\n",
- " },\n",
- " \"error\": null,\n",
- " \"status\": 200,\n",
- " \"content\": [\n",
- " \"[\\n](./)\\n[\\nDocs\\n](https://docs.julep.ai/)\\n[\\nGithub\\n](https://github.com/julep-ai/julep)\\n[\\nDashboard\\n](https://dashboard.julep.ai/agents/)\\nExamples\\n[\\nDiscord\\n](https://discord.gg/2EUJzJU2Yt)\\n[\\nBook demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nContact Us\\n](./contact)\\n[\\n](./)\\n[\\n](./)\\n# MakingAIDevelopment\\nWhatItShouldBe\\nTwo years ago, we started Julep with a simple belief: making intelligence more human shouldn't mean making engineering less rigorous While the world rushed to stack prompts and call it engineering, we chose to build something foundational We created the 8-Factor Agent methodology not because it was easy, but because AI development deserves real tools, real engineering, and real infrastructure We're engineers who believe the future of software will be built on AI - not as a collection of clever hacks, but as properly engineered systems with clear interfaces, predictable behavior, and production-grade reliability Julep isn't another abstraction layer or prompt management tool It's a complete rethinking of how AI applications should be built, tested, and scaled Our task language isn't another abstraction layer; it's a new way to think about AI workflows Our infrastructure isn't just about scaling; it's about bringing reliability and rigor to a field that sorely needs it Because taking the hard path to simple AI development isn't just our approach - it's our conviction that this is how it should be done We're building the foundation for AI's future, not chasing its hype * * * Dev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\"\n",
- " ]\n",
- " },\n",
- " {\n",
- " \"url\": \"https://julep.ai/contact\",\n",
- " \"costs\": {\n",
- " \"ai_cost\": 0,\n",
- " \"file_cost\": 0.0002,\n",
- " \"total_cost\": 0.0004,\n",
- " \"compute_cost\": 0.0001,\n",
- " \"transform_cost\": 0.0001,\n",
- " \"bytes_transferred_cost\": 0\n",
- " },\n",
- " \"error\": null,\n",
- " \"status\": 200,\n",
- " \"content\": [\n",
- " \"[\\n](./)\\n[\\nDocs\\n](https://docs.julep.ai/)\\n[\\nGithub\\n](https://github.com/julep-ai/julep)\\n[\\nDashboard\\n](https://dashboard.julep.ai/agents/)\\nExamples\\n[\\nDiscord\\n](https://discord.gg/2EUJzJU2Yt)\\n[\\nBook demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nContact Us\\n](./contact)\\n[\\n](./)\\n[\\n](./)\\n## How can we help you today We\\u2019re here to help Reach out to learn more about Synth Assistant or start your AI journey today\\nDev Support\\nhey@julep.ai\\nDev Support\\nhey@julep.ai\\nDev Support\\nhey@julep.ai\\nBook a demo\\nBook\\nBook a demo\\nBook\\nBook a demo\\nBook\\nJoin Our Community\\nDiscord\\nJoin Our Community\\nDiscord\\nJoin Our Community\\nDiscord\\nor\\nName\\nEmail\\nEmail\\nSubmit\\nSubmit\\nSubmit\\n### Build faster using Julep API\\n### Deploy multi-step workflows easily with\\n### built-in tools and\\n### State management that is\\n### production ready from day one Keep me informed\\n### Build faster using Julep API\\n### Deploy multi-step workflows easily with built-in tools and State management that is production ready from day one Keep me informed\\nKeep me informed\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\"\n",
- " ]\n",
- " }\n",
- " ]\n",
- "}\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 2 Type: init_branch\n",
- "output: {\n",
- " \"url\": \"https://julep.ai/\",\n",
- " \"costs\": {\n",
- " \"ai_cost\": 0,\n",
- " \"file_cost\": 0.0004,\n",
- " \"total_cost\": 0.0006,\n",
- " \"compute_cost\": 0.0001,\n",
- " \"transform_cost\": 0.0001,\n",
- " \"bytes_transferred_cost\": 0\n",
- " },\n",
- " \"error\": null,\n",
- " \"status\": 200,\n",
- " \"content\": [\n",
- " \"[\\n](./)\\n[\\nDocs\\n](https://docs.julep.ai/)\\n[\\nGithub\\n](https://github.com/julep-ai/julep)\\n[\\nDashboard\\n](https://dashboard.julep.ai/agents/)\\nExamples\\n[\\nDiscord\\n](https://discord.gg/2EUJzJU2Yt)\\n[\\nBook demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nContact Us\\n](./contact)\\n[\\n](./)\\n[\\n](./)\\nAnnouncing our Education+NGO program Eligible organizations get unlimited free credits Please apply[here](https://forms.gle/CCP6sDYeUfAXdUoi7) [](https://www.producthunt.com/posts/julep-ai)\\nOpen Source\\n[\\nGithub\\n\\u26054.4K\\n](https://github.com/julep-ai/julep)\\n# Buildscalable\\nAIworkflows\\ninminutes\\nAPI to build multi-step agent workflows\\n[\\nDeploy your first agent\\n](https://dashboard-dev.julep.ai/)\\n[\\nDeploy your first agent\\n](https://dashboard-dev.julep.ai/)\\n[\\nGet a demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nGet a demo\\n](< https://calendly.com/ishita-julep>)\\nCUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place CUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place CUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place ## Connect with any AI model,\\nAPI or data source\\nSeamlessly integrate with your existing stack and favorite AI models LLM Platforms\\nLanguages\\nIntegrations\\n* * * * * * Any REST API\\n## Real people, Real results\\n* Julep to me sits in the intersection of what Zapier did for simplifying workflows, and what Vercel did for simplifying shipping The new possibilities are endless I am excited abut what all can be done with this tech at ES Suryansh Tibarewal\\nCEO, EssentiallySports\\n* For Vidyo, we shipped 6 months worth of product development in 6 hours GAME CHANGER!\",\n",
- " \"Vedant Maheshwari\\nCEO, Vidyo.ai\\n* We tried building our ai stack where we needed simple automated computer use we spent months trying to get it right, but our development time got cut to a couple weeks because most of the infra orchestration was handled by julep all that we had to do was refine our prompts\\nMadhavan\\nCEO, Reclaim Protocol\\n* \\\"Same experience as reviewing designs on Figma with my designer Sat with my developer once, and we kept brainstorming, testing, prototyping and shipping at once I got control back in my hands as a non-developer.\\\"\\nAkshay Pruthi\\nCEO, Calm Sleep\\n* Working with Julep accelerated Ukumi, by enabling us to focus on our core strengths and letting Julep navigate the complex web of calls to ai models we could do more with less Sachin Gaur\\nCofounder, Ukumi AI\\n### Build with Julep\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\nDeploy\\nExecute production-grade workflows with one command\\nagent = julep.agents.create(\\nname=\\\"Spiderman\\\",\\nabout=\\\"AI that can crawl the web and extract data\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\ndefault\\\\_settings={\\n\\\"temperature\\\":0.75,\\n\\\"max\\\\_tokens\\\":10000,\\n\\\"top\\\\_p\\\":1.0,\\n}\\n)\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\njulep.agents.tools.create(\\nagent\\\\_id=agent.id,\\nname=\\\"my\\\\_weather\\\\_tool\\\",\\nintegration={\\n\\\"provider\\\":\\\"weather\\\",\\n\\\"setup\\\": {\\n\\\"openweathermap\\\\_api\\\\_key\\\":\\\"OPENWEATHERMAP\\\\_API\\\\_KEY\\\"\\n}\\n}\\n)\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\niimportyaml\\ntask =julep.task.create(\\\"\\\"\\\"\\nname: Weather Reporting Task\\nmain:\\n- tool: spider\\\\_crawler\\narguments:\\nurl: \\\\_.url\\n- prompt: |\\nHere\\u2019s a crawl of {{inputs[0].url}}:\\n{{\\\\_.documents}}\\nCreate a short summary (\\\\~100 words) of the website \\\"\\\"\\\")- city\\nDeploy\\nExecute production-grade workflows with one command\\nexecution = julep.executions.create(\\ntask\\\\_id=task.id,\\ninput={\\n\\\"url\\\": \\\"https://spider.cloud\\\"\\n}\\n)\\nagent = julep.agents.create(\\nname=\\\"Cristopher\\\",\\nabout=\\\"An agent specialized in weather reporting\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\n)\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\nDeploy\\nExecute production-grade workflows with one command\\nagent = julep.agents.create(\\nname=\\\"Spiderman\\\",\\nabout=\\\"AI that can crawl the web and extract data\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\ndefault\\\\_settings={\\n\\\"temperature\\\":0.75,\\n\\\"max\\\\_tokens\\\":10000,\\n\\\"top\\\\_p\\\":1.0,\\n}\\n)\\n## Build AI pipelines\\nin minutes Scale to millions Rapid Prototyping\\n\\\"From idea to demo in minutes\\\" using built-in RAG and state management\\nProduction Ready\\n\\\"Go live instantly with managed infrastructure\\\" and features such as long-running tasks, automatic retries and error handling\\nModular Design\\n\\\"Build features like Lego blocks\\\" by connecting to any external API, switch between LLMs and add custom tools\\nInfinite Scale\\nHandle millions of concurrent users with automatic scaling and load balancing\\nFuture Proof\\n\\\"Add new AI models anytime\\\" \\\"Integrate with any new tool or API\\\"\\nComplete Control\\n\\\"Full visibility into AI operations\\\" \\\"Manage costs and performance easily\\\"\\n## Questions Answers What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks\",\n",
- " \"It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching\",\n",
- " \"-Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing -Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching -Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing -Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement\",\n",
- " \"How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching -Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing.-Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks\",\n",
- " \"How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks ### Build faster using Julep API\\n### Deploy multi-step workflows easily with\\n### built-in tools and\\n### state management that is\\n### production ready from day one Keep me informed\\n### Build faster using Julep API\\n### Deploy multi-step workflows easily with built-in tools and State management that is production ready from day one Keep me informed\\nKeep me informed\\nKeep me informed\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\"\n",
- " ]\n",
- "}\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 3 Type: step\n",
- "output: {\n",
- " \"content\": [\n",
- " \"[\\n](./)\\n[\\nDocs\\n](https://docs.julep.ai/)\\n[\\nGithub\\n](https://github.com/julep-ai/julep)\\n[\\nDashboard\\n](https://dashboard.julep.ai/agents/)\\nExamples\\n[\\nDiscord\\n](https://discord.gg/2EUJzJU2Yt)\\n[\\nBook demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nContact Us\\n](./contact)\\n[\\n](./)\\n[\\n](./)\\nAnnouncing our Education+NGO program Eligible organizations get unlimited free credits Please apply[here](https://forms.gle/CCP6sDYeUfAXdUoi7) [](https://www.producthunt.com/posts/julep-ai)\\nOpen Source\\n[\\nGithub\\n\\u26054.4K\\n](https://github.com/julep-ai/julep)\\n# Buildscalable\\nAIworkflows\\ninminutes\\nAPI to build multi-step agent workflows\\n[\\nDeploy your first agent\\n](https://dashboard-dev.julep.ai/)\\n[\\nDeploy your first agent\\n](https://dashboard-dev.julep.ai/)\\n[\\nGet a demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nGet a demo\\n](< https://calendly.com/ishita-julep>)\\nCUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place CUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place CUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place ## Connect with any AI model,\\nAPI or data source\\nSeamlessly integrate with your existing stack and favorite AI models LLM Platforms\\nLanguages\\nIntegrations\\n* * * * * * Any REST API\\n## Real people, Real results\\n* Julep to me sits in the intersection of what Zapier did for simplifying workflows, and what Vercel did for simplifying shipping The new possibilities are endless I am excited abut what all can be done with this tech at ES Suryansh Tibarewal\\nCEO, EssentiallySports\\n* For Vidyo, we shipped 6 months worth of product development in 6 hours GAME CHANGER!\",\n",
- " \"Vedant Maheshwari\\nCEO, Vidyo.ai\\n* We tried building our ai stack where we needed simple automated computer use we spent months trying to get it right, but our development time got cut to a couple weeks because most of the infra orchestration was handled by julep all that we had to do was refine our prompts\\nMadhavan\\nCEO, Reclaim Protocol\\n* \\\"Same experience as reviewing designs on Figma with my designer Sat with my developer once, and we kept brainstorming, testing, prototyping and shipping at once I got control back in my hands as a non-developer.\\\"\\nAkshay Pruthi\\nCEO, Calm Sleep\\n* Working with Julep accelerated Ukumi, by enabling us to focus on our core strengths and letting Julep navigate the complex web of calls to ai models we could do more with less Sachin Gaur\\nCofounder, Ukumi AI\\n### Build with Julep\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\nDeploy\\nExecute production-grade workflows with one command\\nagent = julep.agents.create(\\nname=\\\"Spiderman\\\",\\nabout=\\\"AI that can crawl the web and extract data\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\ndefault\\\\_settings={\\n\\\"temperature\\\":0.75,\\n\\\"max\\\\_tokens\\\":10000,\\n\\\"top\\\\_p\\\":1.0,\\n}\\n)\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\njulep.agents.tools.create(\\nagent\\\\_id=agent.id,\\nname=\\\"my\\\\_weather\\\\_tool\\\",\\nintegration={\\n\\\"provider\\\":\\\"weather\\\",\\n\\\"setup\\\": {\\n\\\"openweathermap\\\\_api\\\\_key\\\":\\\"OPENWEATHERMAP\\\\_API\\\\_KEY\\\"\\n}\\n}\\n)\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\niimportyaml\\ntask =julep.task.create(\\\"\\\"\\\"\\nname: Weather Reporting Task\\nmain:\\n- tool: spider\\\\_crawler\\narguments:\\nurl: \\\\_.url\\n- prompt: |\\nHere\\u2019s a crawl of {{inputs[0].url}}:\\n{{\\\\_.documents}}\\nCreate a short summary (\\\\~100 words) of the website \\\"\\\"\\\")- city\\nDeploy\\nExecute production-grade workflows with one command\\nexecution = julep.executions.create(\\ntask\\\\_id=task.id,\\ninput={\\n\\\"url\\\": \\\"https://spider.cloud\\\"\\n}\\n)\\nagent = julep.agents.create(\\nname=\\\"Cristopher\\\",\\nabout=\\\"An agent specialized in weather reporting\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\n)\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\nDeploy\\nExecute production-grade workflows with one command\\nagent = julep.agents.create(\\nname=\\\"Spiderman\\\",\\nabout=\\\"AI that can crawl the web and extract data\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\ndefault\\\\_settings={\\n\\\"temperature\\\":0.75,\\n\\\"max\\\\_tokens\\\":10000,\\n\\\"top\\\\_p\\\":1.0,\\n}\\n)\\n## Build AI pipelines\\nin minutes Scale to millions Rapid Prototyping\\n\\\"From idea to demo in minutes\\\" using built-in RAG and state management\\nProduction Ready\\n\\\"Go live instantly with managed infrastructure\\\" and features such as long-running tasks, automatic retries and error handling\\nModular Design\\n\\\"Build features like Lego blocks\\\" by connecting to any external API, switch between LLMs and add custom tools\\nInfinite Scale\\nHandle millions of concurrent users with automatic scaling and load balancing\\nFuture Proof\\n\\\"Add new AI models anytime\\\" \\\"Integrate with any new tool or API\\\"\\nComplete Control\\n\\\"Full visibility into AI operations\\\" \\\"Manage costs and performance easily\\\"\\n## Questions Answers What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks\",\n",
- " \"It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching\",\n",
- " \"-Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing -Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching -Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing -Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement\",\n",
- " \"How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching -Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing.-Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks\",\n",
- " \"How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks ### Build faster using Julep API\\n### Deploy multi-step workflows easily with\\n### built-in tools and\\n### state management that is\\n### production ready from day one Keep me informed\\n### Build faster using Julep API\\n### Deploy multi-step workflows easily with built-in tools and State management that is production ready from day one Keep me informed\\nKeep me informed\\nKeep me informed\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\"\n",
- " ]\n",
- "}\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 4 Type: init_branch\n",
- "output: {\n",
- " \"content\": [\n",
- " \"[\\n](./)\\n[\\nDocs\\n](https://docs.julep.ai/)\\n[\\nGithub\\n](https://github.com/julep-ai/julep)\\n[\\nDashboard\\n](https://dashboard.julep.ai/agents/)\\nExamples\\n[\\nDiscord\\n](https://discord.gg/2EUJzJU2Yt)\\n[\\nBook demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nContact Us\\n](./contact)\\n[\\n](./)\\n[\\n](./)\\nAnnouncing our Education+NGO program Eligible organizations get unlimited free credits Please apply[here](https://forms.gle/CCP6sDYeUfAXdUoi7) [](https://www.producthunt.com/posts/julep-ai)\\nOpen Source\\n[\\nGithub\\n\\u26054.4K\\n](https://github.com/julep-ai/julep)\\n# Buildscalable\\nAIworkflows\\ninminutes\\nAPI to build multi-step agent workflows\\n[\\nDeploy your first agent\\n](https://dashboard-dev.julep.ai/)\\n[\\nDeploy your first agent\\n](https://dashboard-dev.julep.ai/)\\n[\\nGet a demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nGet a demo\\n](< https://calendly.com/ishita-julep>)\\nCUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place CUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place CUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place ## Connect with any AI model,\\nAPI or data source\\nSeamlessly integrate with your existing stack and favorite AI models LLM Platforms\\nLanguages\\nIntegrations\\n* * * * * * Any REST API\\n## Real people, Real results\\n* Julep to me sits in the intersection of what Zapier did for simplifying workflows, and what Vercel did for simplifying shipping The new possibilities are endless I am excited abut what all can be done with this tech at ES Suryansh Tibarewal\\nCEO, EssentiallySports\\n* For Vidyo, we shipped 6 months worth of product development in 6 hours GAME CHANGER!\",\n",
- " \"Vedant Maheshwari\\nCEO, Vidyo.ai\\n* We tried building our ai stack where we needed simple automated computer use we spent months trying to get it right, but our development time got cut to a couple weeks because most of the infra orchestration was handled by julep all that we had to do was refine our prompts\\nMadhavan\\nCEO, Reclaim Protocol\\n* \\\"Same experience as reviewing designs on Figma with my designer Sat with my developer once, and we kept brainstorming, testing, prototyping and shipping at once I got control back in my hands as a non-developer.\\\"\\nAkshay Pruthi\\nCEO, Calm Sleep\\n* Working with Julep accelerated Ukumi, by enabling us to focus on our core strengths and letting Julep navigate the complex web of calls to ai models we could do more with less Sachin Gaur\\nCofounder, Ukumi AI\\n### Build with Julep\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\nDeploy\\nExecute production-grade workflows with one command\\nagent = julep.agents.create(\\nname=\\\"Spiderman\\\",\\nabout=\\\"AI that can crawl the web and extract data\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\ndefault\\\\_settings={\\n\\\"temperature\\\":0.75,\\n\\\"max\\\\_tokens\\\":10000,\\n\\\"top\\\\_p\\\":1.0,\\n}\\n)\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\njulep.agents.tools.create(\\nagent\\\\_id=agent.id,\\nname=\\\"my\\\\_weather\\\\_tool\\\",\\nintegration={\\n\\\"provider\\\":\\\"weather\\\",\\n\\\"setup\\\": {\\n\\\"openweathermap\\\\_api\\\\_key\\\":\\\"OPENWEATHERMAP\\\\_API\\\\_KEY\\\"\\n}\\n}\\n)\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\niimportyaml\\ntask =julep.task.create(\\\"\\\"\\\"\\nname: Weather Reporting Task\\nmain:\\n- tool: spider\\\\_crawler\\narguments:\\nurl: \\\\_.url\\n- prompt: |\\nHere\\u2019s a crawl of {{inputs[0].url}}:\\n{{\\\\_.documents}}\\nCreate a short summary (\\\\~100 words) of the website \\\"\\\"\\\")- city\\nDeploy\\nExecute production-grade workflows with one command\\nexecution = julep.executions.create(\\ntask\\\\_id=task.id,\\ninput={\\n\\\"url\\\": \\\"https://spider.cloud\\\"\\n}\\n)\\nagent = julep.agents.create(\\nname=\\\"Cristopher\\\",\\nabout=\\\"An agent specialized in weather reporting\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\n)\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\nDeploy\\nExecute production-grade workflows with one command\\nagent = julep.agents.create(\\nname=\\\"Spiderman\\\",\\nabout=\\\"AI that can crawl the web and extract data\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\ndefault\\\\_settings={\\n\\\"temperature\\\":0.75,\\n\\\"max\\\\_tokens\\\":10000,\\n\\\"top\\\\_p\\\":1.0,\\n}\\n)\\n## Build AI pipelines\\nin minutes Scale to millions Rapid Prototyping\\n\\\"From idea to demo in minutes\\\" using built-in RAG and state management\\nProduction Ready\\n\\\"Go live instantly with managed infrastructure\\\" and features such as long-running tasks, automatic retries and error handling\\nModular Design\\n\\\"Build features like Lego blocks\\\" by connecting to any external API, switch between LLMs and add custom tools\\nInfinite Scale\\nHandle millions of concurrent users with automatic scaling and load balancing\\nFuture Proof\\n\\\"Add new AI models anytime\\\" \\\"Integrate with any new tool or API\\\"\\nComplete Control\\n\\\"Full visibility into AI operations\\\" \\\"Manage costs and performance easily\\\"\\n## Questions Answers What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks\",\n",
- " \"It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching\",\n",
- " \"-Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing -Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching -Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing -Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement\",\n",
- " \"How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching -Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing.-Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks\",\n",
- " \"How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks ### Build faster using Julep API\\n### Deploy multi-step workflows easily with\\n### built-in tools and\\n### state management that is\\n### production ready from day one Keep me informed\\n### Build faster using Julep API\\n### Deploy multi-step workflows easily with built-in tools and State management that is production ready from day one Keep me informed\\nKeep me informed\\nKeep me informed\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\"\n",
- " ]\n",
- "}\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 5 Type: step\n",
- "output: {\n",
- " \"documents\": [\n",
- " \"[\\n](./)\\n[\\nDocs\\n](https://docs.julep.ai/)\\n[\\nGithub\\n](https://github.com/julep-ai/julep)\\n[\\nDashboard\\n](https://dashboard.julep.ai/agents/)\\nExamples\\n[\\nDiscord\\n](https://discord.gg/2EUJzJU2Yt)\\n[\\nBook demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nContact Us\\n](./contact)\\n[\\n](./)\\n[\\n](./)\\nAnnouncing our Education+NGO program Eligible organizations get unlimited free credits Please apply[here](https://forms.gle/CCP6sDYeUfAXdUoi7) [](https://www.producthunt.com/posts/julep-ai)\\nOpen Source\\n[\\nGithub\\n\\u26054.4K\\n](https://github.com/julep-ai/julep)\\n# Buildscalable\\nAIworkflows\\ninminutes\\nAPI to build multi-step agent workflows\\n[\\nDeploy your first agent\\n](https://dashboard-dev.julep.ai/)\\n[\\nDeploy your first agent\\n](https://dashboard-dev.julep.ai/)\\n[\\nGet a demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nGet a demo\\n](< https://calendly.com/ishita-julep>)\\nCUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place CUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place CUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place ## Connect with any AI model,\\nAPI or data source\\nSeamlessly integrate with your existing stack and favorite AI models LLM Platforms\\nLanguages\\nIntegrations\\n* * * * * * Any REST API\\n## Real people, Real results\\n* Julep to me sits in the intersection of what Zapier did for simplifying workflows, and what Vercel did for simplifying shipping The new possibilities are endless I am excited abut what all can be done with this tech at ES Suryansh Tibarewal\\nCEO, EssentiallySports\\n* For Vidyo, we shipped 6 months worth of product development in 6 hours GAME CHANGER!\",\n",
- " \"Vedant Maheshwari\\nCEO, Vidyo.ai\\n* We tried building our ai stack where we needed simple automated computer use we spent months trying to get it right, but our development time got cut to a couple weeks because most of the infra orchestration was handled by julep all that we had to do was refine our prompts\\nMadhavan\\nCEO, Reclaim Protocol\\n* \\\"Same experience as reviewing designs on Figma with my designer Sat with my developer once, and we kept brainstorming, testing, prototyping and shipping at once I got control back in my hands as a non-developer.\\\"\\nAkshay Pruthi\\nCEO, Calm Sleep\\n* Working with Julep accelerated Ukumi, by enabling us to focus on our core strengths and letting Julep navigate the complex web of calls to ai models we could do more with less Sachin Gaur\\nCofounder, Ukumi AI\\n### Build with Julep\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\nDeploy\\nExecute production-grade workflows with one command\\nagent = julep.agents.create(\\nname=\\\"Spiderman\\\",\\nabout=\\\"AI that can crawl the web and extract data\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\ndefault\\\\_settings={\\n\\\"temperature\\\":0.75,\\n\\\"max\\\\_tokens\\\":10000,\\n\\\"top\\\\_p\\\":1.0,\\n}\\n)\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\njulep.agents.tools.create(\\nagent\\\\_id=agent.id,\\nname=\\\"my\\\\_weather\\\\_tool\\\",\\nintegration={\\n\\\"provider\\\":\\\"weather\\\",\\n\\\"setup\\\": {\\n\\\"openweathermap\\\\_api\\\\_key\\\":\\\"OPENWEATHERMAP\\\\_API\\\\_KEY\\\"\\n}\\n}\\n)\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\niimportyaml\\ntask =julep.task.create(\\\"\\\"\\\"\\nname: Weather Reporting Task\\nmain:\\n- tool: spider\\\\_crawler\\narguments:\\nurl: \\\\_.url\\n- prompt: |\\nHere\\u2019s a crawl of {{inputs[0].url}}:\\n{{\\\\_.documents}}\\nCreate a short summary (\\\\~100 words) of the website \\\"\\\"\\\")- city\\nDeploy\\nExecute production-grade workflows with one command\\nexecution = julep.executions.create(\\ntask\\\\_id=task.id,\\ninput={\\n\\\"url\\\": \\\"https://spider.cloud\\\"\\n}\\n)\\nagent = julep.agents.create(\\nname=\\\"Cristopher\\\",\\nabout=\\\"An agent specialized in weather reporting\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\n)\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\nDeploy\\nExecute production-grade workflows with one command\\nagent = julep.agents.create(\\nname=\\\"Spiderman\\\",\\nabout=\\\"AI that can crawl the web and extract data\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\ndefault\\\\_settings={\\n\\\"temperature\\\":0.75,\\n\\\"max\\\\_tokens\\\":10000,\\n\\\"top\\\\_p\\\":1.0,\\n}\\n)\\n## Build AI pipelines\\nin minutes Scale to millions Rapid Prototyping\\n\\\"From idea to demo in minutes\\\" using built-in RAG and state management\\nProduction Ready\\n\\\"Go live instantly with managed infrastructure\\\" and features such as long-running tasks, automatic retries and error handling\\nModular Design\\n\\\"Build features like Lego blocks\\\" by connecting to any external API, switch between LLMs and add custom tools\\nInfinite Scale\\nHandle millions of concurrent users with automatic scaling and load balancing\\nFuture Proof\\n\\\"Add new AI models anytime\\\" \\\"Integrate with any new tool or API\\\"\\nComplete Control\\n\\\"Full visibility into AI operations\\\" \\\"Manage costs and performance easily\\\"\\n## Questions Answers What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks\",\n",
- " \"It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching\",\n",
- " \"-Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing -Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching -Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing -Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement\",\n",
- " \"How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching -Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing.-Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks\",\n",
- " \"How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks ### Build faster using Julep API\\n### Deploy multi-step workflows easily with\\n### built-in tools and\\n### state management that is\\n### production ready from day one Keep me informed\\n### Build faster using Julep API\\n### Deploy multi-step workflows easily with built-in tools and State management that is production ready from day one Keep me informed\\nKeep me informed\\nKeep me informed\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\"\n",
- " ]\n",
- "}\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 6 Type: init_branch\n",
- "output: [\n",
- " [\n",
- " \"[\\n](./)\\n[\\nDocs\\n](https://docs.julep.ai/)\\n[\\nGithub\\n](https://github.com/julep-ai/julep)\\n[\\nDashboard\\n](https://dashboard.julep.ai/agents/)\\nExamples\\n[\\nDiscord\\n](https://discord.gg/2EUJzJU2Yt)\\n[\\nBook demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nContact Us\\n](./contact)\\n[\\n](./)\\n[\\n](./)\\nAnnouncing our Education+NGO program Eligible organizations get unlimited free credits Please apply[here](https://forms.gle/CCP6sDYeUfAXdUoi7) [](https://www.producthunt.com/posts/julep-ai)\\nOpen Source\\n[\\nGithub\\n\\u26054.4K\\n](https://github.com/julep-ai/julep)\\n# Buildscalable\\nAIworkflows\\ninminutes\\nAPI to build multi-step agent workflows\\n[\\nDeploy your first agent\\n](https://dashboard-dev.julep.ai/)\\n[\\nDeploy your first agent\\n](https://dashboard-dev.julep.ai/)\\n[\\nGet a demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nGet a demo\\n](< https://calendly.com/ishita-julep>)\\nCUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place CUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place CUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place ## Connect with any AI model,\\nAPI or data source\\nSeamlessly integrate with your existing stack and favorite AI models LLM Platforms\\nLanguages\\nIntegrations\\n* * * * * * Any REST API\\n## Real people, Real results\\n* Julep to me sits in the intersection of what Zapier did for simplifying workflows, and what Vercel did for simplifying shipping The new possibilities are endless I am excited abut what all can be done with this tech at ES Suryansh Tibarewal\\nCEO, EssentiallySports\\n* For Vidyo, we shipped 6 months worth of product development in 6 hours GAME CHANGER!\",\n",
- " \"Vedant Maheshwari\\nCEO, Vidyo.ai\\n* We tried building our ai stack where we needed simple automated computer use we spent months trying to get it right, but our development time got cut to a couple weeks because most of the infra orchestration was handled by julep all that we had to do was refine our prompts\\nMadhavan\\nCEO, Reclaim Protocol\\n* \\\"Same experience as reviewing designs on Figma with my designer Sat with my developer once, and we kept brainstorming, testing, prototyping and shipping at once I got control back in my hands as a non-developer.\\\"\\nAkshay Pruthi\\nCEO, Calm Sleep\\n* Working with Julep accelerated Ukumi, by enabling us to focus on our core strengths and letting Julep navigate the complex web of calls to ai models we could do more with less Sachin Gaur\\nCofounder, Ukumi AI\\n### Build with Julep\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\nDeploy\\nExecute production-grade workflows with one command\\nagent = julep.agents.create(\\nname=\\\"Spiderman\\\",\\nabout=\\\"AI that can crawl the web and extract data\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\ndefault\\\\_settings={\\n\\\"temperature\\\":0.75,\\n\\\"max\\\\_tokens\\\":10000,\\n\\\"top\\\\_p\\\":1.0,\\n}\\n)\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\njulep.agents.tools.create(\\nagent\\\\_id=agent.id,\\nname=\\\"my\\\\_weather\\\\_tool\\\",\\nintegration={\\n\\\"provider\\\":\\\"weather\\\",\\n\\\"setup\\\": {\\n\\\"openweathermap\\\\_api\\\\_key\\\":\\\"OPENWEATHERMAP\\\\_API\\\\_KEY\\\"\\n}\\n}\\n)\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\niimportyaml\\ntask =julep.task.create(\\\"\\\"\\\"\\nname: Weather Reporting Task\\nmain:\\n- tool: spider\\\\_crawler\\narguments:\\nurl: \\\\_.url\\n- prompt: |\\nHere\\u2019s a crawl of {{inputs[0].url}}:\\n{{\\\\_.documents}}\\nCreate a short summary (\\\\~100 words) of the website \\\"\\\"\\\")- city\\nDeploy\\nExecute production-grade workflows with one command\\nexecution = julep.executions.create(\\ntask\\\\_id=task.id,\\ninput={\\n\\\"url\\\": \\\"https://spider.cloud\\\"\\n}\\n)\\nagent = julep.agents.create(\\nname=\\\"Cristopher\\\",\\nabout=\\\"An agent specialized in weather reporting\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\n)\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\nDeploy\\nExecute production-grade workflows with one command\\nagent = julep.agents.create(\\nname=\\\"Spiderman\\\",\\nabout=\\\"AI that can crawl the web and extract data\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\ndefault\\\\_settings={\\n\\\"temperature\\\":0.75,\\n\\\"max\\\\_tokens\\\":10000,\\n\\\"top\\\\_p\\\":1.0,\\n}\\n)\\n## Build AI pipelines\\nin minutes Scale to millions Rapid Prototyping\\n\\\"From idea to demo in minutes\\\" using built-in RAG and state management\\nProduction Ready\\n\\\"Go live instantly with managed infrastructure\\\" and features such as long-running tasks, automatic retries and error handling\\nModular Design\\n\\\"Build features like Lego blocks\\\" by connecting to any external API, switch between LLMs and add custom tools\\nInfinite Scale\\nHandle millions of concurrent users with automatic scaling and load balancing\\nFuture Proof\\n\\\"Add new AI models anytime\\\" \\\"Integrate with any new tool or API\\\"\\nComplete Control\\n\\\"Full visibility into AI operations\\\" \\\"Manage costs and performance easily\\\"\\n## Questions Answers What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks\",\n",
- " \"It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching\",\n",
- " \"-Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing -Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching -Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing -Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement\",\n",
- " \"How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching -Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing.-Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks\",\n",
- " \"How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks ### Build faster using Julep API\\n### Deploy multi-step workflows easily with\\n### built-in tools and\\n### state management that is\\n### production ready from day one Keep me informed\\n### Build faster using Julep API\\n### Deploy multi-step workflows easily with built-in tools and State management that is production ready from day one Keep me informed\\nKeep me informed\\nKeep me informed\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\"\n",
- " ],\n",
- " \"It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching\"\n",
- "]\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 7 Type: init_branch\n",
- "output: [\n",
- " [\n",
- " \"[\\n](./)\\n[\\nDocs\\n](https://docs.julep.ai/)\\n[\\nGithub\\n](https://github.com/julep-ai/julep)\\n[\\nDashboard\\n](https://dashboard.julep.ai/agents/)\\nExamples\\n[\\nDiscord\\n](https://discord.gg/2EUJzJU2Yt)\\n[\\nBook demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nContact Us\\n](./contact)\\n[\\n](./)\\n[\\n](./)\\nAnnouncing our Education+NGO program Eligible organizations get unlimited free credits Please apply[here](https://forms.gle/CCP6sDYeUfAXdUoi7) [](https://www.producthunt.com/posts/julep-ai)\\nOpen Source\\n[\\nGithub\\n\\u26054.4K\\n](https://github.com/julep-ai/julep)\\n# Buildscalable\\nAIworkflows\\ninminutes\\nAPI to build multi-step agent workflows\\n[\\nDeploy your first agent\\n](https://dashboard-dev.julep.ai/)\\n[\\nDeploy your first agent\\n](https://dashboard-dev.julep.ai/)\\n[\\nGet a demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nGet a demo\\n](< https://calendly.com/ishita-julep>)\\nCUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place CUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place CUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place ## Connect with any AI model,\\nAPI or data source\\nSeamlessly integrate with your existing stack and favorite AI models LLM Platforms\\nLanguages\\nIntegrations\\n* * * * * * Any REST API\\n## Real people, Real results\\n* Julep to me sits in the intersection of what Zapier did for simplifying workflows, and what Vercel did for simplifying shipping The new possibilities are endless I am excited abut what all can be done with this tech at ES Suryansh Tibarewal\\nCEO, EssentiallySports\\n* For Vidyo, we shipped 6 months worth of product development in 6 hours GAME CHANGER!\",\n",
- " \"Vedant Maheshwari\\nCEO, Vidyo.ai\\n* We tried building our ai stack where we needed simple automated computer use we spent months trying to get it right, but our development time got cut to a couple weeks because most of the infra orchestration was handled by julep all that we had to do was refine our prompts\\nMadhavan\\nCEO, Reclaim Protocol\\n* \\\"Same experience as reviewing designs on Figma with my designer Sat with my developer once, and we kept brainstorming, testing, prototyping and shipping at once I got control back in my hands as a non-developer.\\\"\\nAkshay Pruthi\\nCEO, Calm Sleep\\n* Working with Julep accelerated Ukumi, by enabling us to focus on our core strengths and letting Julep navigate the complex web of calls to ai models we could do more with less Sachin Gaur\\nCofounder, Ukumi AI\\n### Build with Julep\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\nDeploy\\nExecute production-grade workflows with one command\\nagent = julep.agents.create(\\nname=\\\"Spiderman\\\",\\nabout=\\\"AI that can crawl the web and extract data\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\ndefault\\\\_settings={\\n\\\"temperature\\\":0.75,\\n\\\"max\\\\_tokens\\\":10000,\\n\\\"top\\\\_p\\\":1.0,\\n}\\n)\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\njulep.agents.tools.create(\\nagent\\\\_id=agent.id,\\nname=\\\"my\\\\_weather\\\\_tool\\\",\\nintegration={\\n\\\"provider\\\":\\\"weather\\\",\\n\\\"setup\\\": {\\n\\\"openweathermap\\\\_api\\\\_key\\\":\\\"OPENWEATHERMAP\\\\_API\\\\_KEY\\\"\\n}\\n}\\n)\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\niimportyaml\\ntask =julep.task.create(\\\"\\\"\\\"\\nname: Weather Reporting Task\\nmain:\\n- tool: spider\\\\_crawler\\narguments:\\nurl: \\\\_.url\\n- prompt: |\\nHere\\u2019s a crawl of {{inputs[0].url}}:\\n{{\\\\_.documents}}\\nCreate a short summary (\\\\~100 words) of the website \\\"\\\"\\\")- city\\nDeploy\\nExecute production-grade workflows with one command\\nexecution = julep.executions.create(\\ntask\\\\_id=task.id,\\ninput={\\n\\\"url\\\": \\\"https://spider.cloud\\\"\\n}\\n)\\nagent = julep.agents.create(\\nname=\\\"Cristopher\\\",\\nabout=\\\"An agent specialized in weather reporting\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\n)\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\nDeploy\\nExecute production-grade workflows with one command\\nagent = julep.agents.create(\\nname=\\\"Spiderman\\\",\\nabout=\\\"AI that can crawl the web and extract data\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\ndefault\\\\_settings={\\n\\\"temperature\\\":0.75,\\n\\\"max\\\\_tokens\\\":10000,\\n\\\"top\\\\_p\\\":1.0,\\n}\\n)\\n## Build AI pipelines\\nin minutes Scale to millions Rapid Prototyping\\n\\\"From idea to demo in minutes\\\" using built-in RAG and state management\\nProduction Ready\\n\\\"Go live instantly with managed infrastructure\\\" and features such as long-running tasks, automatic retries and error handling\\nModular Design\\n\\\"Build features like Lego blocks\\\" by connecting to any external API, switch between LLMs and add custom tools\\nInfinite Scale\\nHandle millions of concurrent users with automatic scaling and load balancing\\nFuture Proof\\n\\\"Add new AI models anytime\\\" \\\"Integrate with any new tool or API\\\"\\nComplete Control\\n\\\"Full visibility into AI operations\\\" \\\"Manage costs and performance easily\\\"\\n## Questions Answers What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks\",\n",
- " \"It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching\",\n",
- " \"-Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing -Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching -Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing -Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement\",\n",
- " \"How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching -Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing.-Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks\",\n",
- " \"How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks ### Build faster using Julep API\\n### Deploy multi-step workflows easily with\\n### built-in tools and\\n### state management that is\\n### production ready from day one Keep me informed\\n### Build faster using Julep API\\n### Deploy multi-step workflows easily with built-in tools and State management that is production ready from day one Keep me informed\\nKeep me informed\\nKeep me informed\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\"\n",
- " ],\n",
- " \"[\\n](./)\\n[\\nDocs\\n](https://docs.julep.ai/)\\n[\\nGithub\\n](https://github.com/julep-ai/julep)\\n[\\nDashboard\\n](https://dashboard.julep.ai/agents/)\\nExamples\\n[\\nDiscord\\n](https://discord.gg/2EUJzJU2Yt)\\n[\\nBook demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nContact Us\\n](./contact)\\n[\\n](./)\\n[\\n](./)\\nAnnouncing our Education+NGO program Eligible organizations get unlimited free credits Please apply[here](https://forms.gle/CCP6sDYeUfAXdUoi7) [](https://www.producthunt.com/posts/julep-ai)\\nOpen Source\\n[\\nGithub\\n\\u26054.4K\\n](https://github.com/julep-ai/julep)\\n# Buildscalable\\nAIworkflows\\ninminutes\\nAPI to build multi-step agent workflows\\n[\\nDeploy your first agent\\n](https://dashboard-dev.julep.ai/)\\n[\\nDeploy your first agent\\n](https://dashboard-dev.julep.ai/)\\n[\\nGet a demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nGet a demo\\n](< https://calendly.com/ishita-julep>)\\nCUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place CUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place CUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place ## Connect with any AI model,\\nAPI or data source\\nSeamlessly integrate with your existing stack and favorite AI models LLM Platforms\\nLanguages\\nIntegrations\\n* * * * * * Any REST API\\n## Real people, Real results\\n* Julep to me sits in the intersection of what Zapier did for simplifying workflows, and what Vercel did for simplifying shipping The new possibilities are endless I am excited abut what all can be done with this tech at ES Suryansh Tibarewal\\nCEO, EssentiallySports\\n* For Vidyo, we shipped 6 months worth of product development in 6 hours GAME CHANGER!\"\n",
- "]\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 8 Type: init_branch\n",
- "output: [\n",
- " [\n",
- " \"[\\n](./)\\n[\\nDocs\\n](https://docs.julep.ai/)\\n[\\nGithub\\n](https://github.com/julep-ai/julep)\\n[\\nDashboard\\n](https://dashboard.julep.ai/agents/)\\nExamples\\n[\\nDiscord\\n](https://discord.gg/2EUJzJU2Yt)\\n[\\nBook demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nContact Us\\n](./contact)\\n[\\n](./)\\n[\\n](./)\\nAnnouncing our Education+NGO program Eligible organizations get unlimited free credits Please apply[here](https://forms.gle/CCP6sDYeUfAXdUoi7) [](https://www.producthunt.com/posts/julep-ai)\\nOpen Source\\n[\\nGithub\\n\\u26054.4K\\n](https://github.com/julep-ai/julep)\\n# Buildscalable\\nAIworkflows\\ninminutes\\nAPI to build multi-step agent workflows\\n[\\nDeploy your first agent\\n](https://dashboard-dev.julep.ai/)\\n[\\nDeploy your first agent\\n](https://dashboard-dev.julep.ai/)\\n[\\nGet a demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nGet a demo\\n](< https://calendly.com/ishita-julep>)\\nCUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place CUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place CUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place ## Connect with any AI model,\\nAPI or data source\\nSeamlessly integrate with your existing stack and favorite AI models LLM Platforms\\nLanguages\\nIntegrations\\n* * * * * * Any REST API\\n## Real people, Real results\\n* Julep to me sits in the intersection of what Zapier did for simplifying workflows, and what Vercel did for simplifying shipping The new possibilities are endless I am excited abut what all can be done with this tech at ES Suryansh Tibarewal\\nCEO, EssentiallySports\\n* For Vidyo, we shipped 6 months worth of product development in 6 hours GAME CHANGER!\",\n",
- " \"Vedant Maheshwari\\nCEO, Vidyo.ai\\n* We tried building our ai stack where we needed simple automated computer use we spent months trying to get it right, but our development time got cut to a couple weeks because most of the infra orchestration was handled by julep all that we had to do was refine our prompts\\nMadhavan\\nCEO, Reclaim Protocol\\n* \\\"Same experience as reviewing designs on Figma with my designer Sat with my developer once, and we kept brainstorming, testing, prototyping and shipping at once I got control back in my hands as a non-developer.\\\"\\nAkshay Pruthi\\nCEO, Calm Sleep\\n* Working with Julep accelerated Ukumi, by enabling us to focus on our core strengths and letting Julep navigate the complex web of calls to ai models we could do more with less Sachin Gaur\\nCofounder, Ukumi AI\\n### Build with Julep\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\nDeploy\\nExecute production-grade workflows with one command\\nagent = julep.agents.create(\\nname=\\\"Spiderman\\\",\\nabout=\\\"AI that can crawl the web and extract data\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\ndefault\\\\_settings={\\n\\\"temperature\\\":0.75,\\n\\\"max\\\\_tokens\\\":10000,\\n\\\"top\\\\_p\\\":1.0,\\n}\\n)\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\njulep.agents.tools.create(\\nagent\\\\_id=agent.id,\\nname=\\\"my\\\\_weather\\\\_tool\\\",\\nintegration={\\n\\\"provider\\\":\\\"weather\\\",\\n\\\"setup\\\": {\\n\\\"openweathermap\\\\_api\\\\_key\\\":\\\"OPENWEATHERMAP\\\\_API\\\\_KEY\\\"\\n}\\n}\\n)\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\niimportyaml\\ntask =julep.task.create(\\\"\\\"\\\"\\nname: Weather Reporting Task\\nmain:\\n- tool: spider\\\\_crawler\\narguments:\\nurl: \\\\_.url\\n- prompt: |\\nHere\\u2019s a crawl of {{inputs[0].url}}:\\n{{\\\\_.documents}}\\nCreate a short summary (\\\\~100 words) of the website \\\"\\\"\\\")- city\\nDeploy\\nExecute production-grade workflows with one command\\nexecution = julep.executions.create(\\ntask\\\\_id=task.id,\\ninput={\\n\\\"url\\\": \\\"https://spider.cloud\\\"\\n}\\n)\\nagent = julep.agents.create(\\nname=\\\"Cristopher\\\",\\nabout=\\\"An agent specialized in weather reporting\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\n)\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\nDeploy\\nExecute production-grade workflows with one command\\nagent = julep.agents.create(\\nname=\\\"Spiderman\\\",\\nabout=\\\"AI that can crawl the web and extract data\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\ndefault\\\\_settings={\\n\\\"temperature\\\":0.75,\\n\\\"max\\\\_tokens\\\":10000,\\n\\\"top\\\\_p\\\":1.0,\\n}\\n)\\n## Build AI pipelines\\nin minutes Scale to millions Rapid Prototyping\\n\\\"From idea to demo in minutes\\\" using built-in RAG and state management\\nProduction Ready\\n\\\"Go live instantly with managed infrastructure\\\" and features such as long-running tasks, automatic retries and error handling\\nModular Design\\n\\\"Build features like Lego blocks\\\" by connecting to any external API, switch between LLMs and add custom tools\\nInfinite Scale\\nHandle millions of concurrent users with automatic scaling and load balancing\\nFuture Proof\\n\\\"Add new AI models anytime\\\" \\\"Integrate with any new tool or API\\\"\\nComplete Control\\n\\\"Full visibility into AI operations\\\" \\\"Manage costs and performance easily\\\"\\n## Questions Answers What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks\",\n",
- " \"It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching\",\n",
- " \"-Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing -Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching -Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing -Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement\",\n",
- " \"How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching -Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing.-Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks\",\n",
- " \"How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks ### Build faster using Julep API\\n### Deploy multi-step workflows easily with\\n### built-in tools and\\n### state management that is\\n### production ready from day one Keep me informed\\n### Build faster using Julep API\\n### Deploy multi-step workflows easily with built-in tools and State management that is production ready from day one Keep me informed\\nKeep me informed\\nKeep me informed\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\"\n",
- " ],\n",
- " \"Vedant Maheshwari\\nCEO, Vidyo.ai\\n* We tried building our ai stack where we needed simple automated computer use we spent months trying to get it right, but our development time got cut to a couple weeks because most of the infra orchestration was handled by julep all that we had to do was refine our prompts\\nMadhavan\\nCEO, Reclaim Protocol\\n* \\\"Same experience as reviewing designs on Figma with my designer Sat with my developer once, and we kept brainstorming, testing, prototyping and shipping at once I got control back in my hands as a non-developer.\\\"\\nAkshay Pruthi\\nCEO, Calm Sleep\\n* Working with Julep accelerated Ukumi, by enabling us to focus on our core strengths and letting Julep navigate the complex web of calls to ai models we could do more with less Sachin Gaur\\nCofounder, Ukumi AI\\n### Build with Julep\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\nDeploy\\nExecute production-grade workflows with one command\\nagent = julep.agents.create(\\nname=\\\"Spiderman\\\",\\nabout=\\\"AI that can crawl the web and extract data\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\ndefault\\\\_settings={\\n\\\"temperature\\\":0.75,\\n\\\"max\\\\_tokens\\\":10000,\\n\\\"top\\\\_p\\\":1.0,\\n}\\n)\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\njulep.agents.tools.create(\\nagent\\\\_id=agent.id,\\nname=\\\"my\\\\_weather\\\\_tool\\\",\\nintegration={\\n\\\"provider\\\":\\\"weather\\\",\\n\\\"setup\\\": {\\n\\\"openweathermap\\\\_api\\\\_key\\\":\\\"OPENWEATHERMAP\\\\_API\\\\_KEY\\\"\\n}\\n}\\n)\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\niimportyaml\\ntask =julep.task.create(\\\"\\\"\\\"\\nname: Weather Reporting Task\\nmain:\\n- tool: spider\\\\_crawler\\narguments:\\nurl: \\\\_.url\\n- prompt: |\\nHere\\u2019s a crawl of {{inputs[0].url}}:\\n{{\\\\_.documents}}\\nCreate a short summary (\\\\~100 words) of the website \\\"\\\"\\\")- city\\nDeploy\\nExecute production-grade workflows with one command\\nexecution = julep.executions.create(\\ntask\\\\_id=task.id,\\ninput={\\n\\\"url\\\": \\\"https://spider.cloud\\\"\\n}\\n)\\nagent = julep.agents.create(\\nname=\\\"Cristopher\\\",\\nabout=\\\"An agent specialized in weather reporting\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\n)\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\nDeploy\\nExecute production-grade workflows with one command\\nagent = julep.agents.create(\\nname=\\\"Spiderman\\\",\\nabout=\\\"AI that can crawl the web and extract data\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\ndefault\\\\_settings={\\n\\\"temperature\\\":0.75,\\n\\\"max\\\\_tokens\\\":10000,\\n\\\"top\\\\_p\\\":1.0,\\n}\\n)\\n## Build AI pipelines\\nin minutes Scale to millions Rapid Prototyping\\n\\\"From idea to demo in minutes\\\" using built-in RAG and state management\\nProduction Ready\\n\\\"Go live instantly with managed infrastructure\\\" and features such as long-running tasks, automatic retries and error handling\\nModular Design\\n\\\"Build features like Lego blocks\\\" by connecting to any external API, switch between LLMs and add custom tools\\nInfinite Scale\\nHandle millions of concurrent users with automatic scaling and load balancing\\nFuture Proof\\n\\\"Add new AI models anytime\\\" \\\"Integrate with any new tool or API\\\"\\nComplete Control\\n\\\"Full visibility into AI operations\\\" \\\"Manage costs and performance easily\\\"\\n## Questions Answers What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks\"\n",
- "]\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 9 Type: finish_branch\n",
- "output: \"This chunk is part of a detailed description of the features and advantages of Julep, a platform for creating AI agents. It emphasizes Julep's capabilities in process management and error handling, and contrasts its disciplined approach to AI development with typical practices.\"\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 10 Type: finish_branch\n",
- "output: \"This chunk focuses on testimonials from CEOs and co-founders about their experiences using Julep AI, highlighting its benefits in reducing development time, enhancing collaboration, and leveraging AI for streamlined operations. It also outlines the process of building AI agents with Julep, including creating agents, equipping them with tools, defining tasks, and deploying workflows. The section emphasizes Julep's capabilities in rapid prototyping, modular design, infinite scalability, and comprehensive AI management.\"\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 11 Type: finish_branch\n",
- "output: \"The document outlines features and capabilities of Julep, a platform for building AI workflows and agents. It showcases customer stories and testimonials highlighting the platform's efficiency and integration benefits with existing tech stacks, similar to how Zapier and Vercel simplify workflows and shipping, respectively. The document also promotes an Education+NGO program offering unlimited free credits to eligible organizations and provides various resources, including demos, integrations, and documentation, to support AI development.\"\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 12 Type: init_branch\n",
- "output: [\n",
- " [\n",
- " \"[\\n](./)\\n[\\nDocs\\n](https://docs.julep.ai/)\\n[\\nGithub\\n](https://github.com/julep-ai/julep)\\n[\\nDashboard\\n](https://dashboard.julep.ai/agents/)\\nExamples\\n[\\nDiscord\\n](https://discord.gg/2EUJzJU2Yt)\\n[\\nBook demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nContact Us\\n](./contact)\\n[\\n](./)\\n[\\n](./)\\nAnnouncing our Education+NGO program Eligible organizations get unlimited free credits Please apply[here](https://forms.gle/CCP6sDYeUfAXdUoi7) [](https://www.producthunt.com/posts/julep-ai)\\nOpen Source\\n[\\nGithub\\n\\u26054.4K\\n](https://github.com/julep-ai/julep)\\n# Buildscalable\\nAIworkflows\\ninminutes\\nAPI to build multi-step agent workflows\\n[\\nDeploy your first agent\\n](https://dashboard-dev.julep.ai/)\\n[\\nDeploy your first agent\\n](https://dashboard-dev.julep.ai/)\\n[\\nGet a demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nGet a demo\\n](< https://calendly.com/ishita-julep>)\\nCUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place CUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place CUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place ## Connect with any AI model,\\nAPI or data source\\nSeamlessly integrate with your existing stack and favorite AI models LLM Platforms\\nLanguages\\nIntegrations\\n* * * * * * Any REST API\\n## Real people, Real results\\n* Julep to me sits in the intersection of what Zapier did for simplifying workflows, and what Vercel did for simplifying shipping The new possibilities are endless I am excited abut what all can be done with this tech at ES Suryansh Tibarewal\\nCEO, EssentiallySports\\n* For Vidyo, we shipped 6 months worth of product development in 6 hours GAME CHANGER!\",\n",
- " \"Vedant Maheshwari\\nCEO, Vidyo.ai\\n* We tried building our ai stack where we needed simple automated computer use we spent months trying to get it right, but our development time got cut to a couple weeks because most of the infra orchestration was handled by julep all that we had to do was refine our prompts\\nMadhavan\\nCEO, Reclaim Protocol\\n* \\\"Same experience as reviewing designs on Figma with my designer Sat with my developer once, and we kept brainstorming, testing, prototyping and shipping at once I got control back in my hands as a non-developer.\\\"\\nAkshay Pruthi\\nCEO, Calm Sleep\\n* Working with Julep accelerated Ukumi, by enabling us to focus on our core strengths and letting Julep navigate the complex web of calls to ai models we could do more with less Sachin Gaur\\nCofounder, Ukumi AI\\n### Build with Julep\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\nDeploy\\nExecute production-grade workflows with one command\\nagent = julep.agents.create(\\nname=\\\"Spiderman\\\",\\nabout=\\\"AI that can crawl the web and extract data\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\ndefault\\\\_settings={\\n\\\"temperature\\\":0.75,\\n\\\"max\\\\_tokens\\\":10000,\\n\\\"top\\\\_p\\\":1.0,\\n}\\n)\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\njulep.agents.tools.create(\\nagent\\\\_id=agent.id,\\nname=\\\"my\\\\_weather\\\\_tool\\\",\\nintegration={\\n\\\"provider\\\":\\\"weather\\\",\\n\\\"setup\\\": {\\n\\\"openweathermap\\\\_api\\\\_key\\\":\\\"OPENWEATHERMAP\\\\_API\\\\_KEY\\\"\\n}\\n}\\n)\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\niimportyaml\\ntask =julep.task.create(\\\"\\\"\\\"\\nname: Weather Reporting Task\\nmain:\\n- tool: spider\\\\_crawler\\narguments:\\nurl: \\\\_.url\\n- prompt: |\\nHere\\u2019s a crawl of {{inputs[0].url}}:\\n{{\\\\_.documents}}\\nCreate a short summary (\\\\~100 words) of the website \\\"\\\"\\\")- city\\nDeploy\\nExecute production-grade workflows with one command\\nexecution = julep.executions.create(\\ntask\\\\_id=task.id,\\ninput={\\n\\\"url\\\": \\\"https://spider.cloud\\\"\\n}\\n)\\nagent = julep.agents.create(\\nname=\\\"Cristopher\\\",\\nabout=\\\"An agent specialized in weather reporting\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\n)\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\nDeploy\\nExecute production-grade workflows with one command\\nagent = julep.agents.create(\\nname=\\\"Spiderman\\\",\\nabout=\\\"AI that can crawl the web and extract data\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\ndefault\\\\_settings={\\n\\\"temperature\\\":0.75,\\n\\\"max\\\\_tokens\\\":10000,\\n\\\"top\\\\_p\\\":1.0,\\n}\\n)\\n## Build AI pipelines\\nin minutes Scale to millions Rapid Prototyping\\n\\\"From idea to demo in minutes\\\" using built-in RAG and state management\\nProduction Ready\\n\\\"Go live instantly with managed infrastructure\\\" and features such as long-running tasks, automatic retries and error handling\\nModular Design\\n\\\"Build features like Lego blocks\\\" by connecting to any external API, switch between LLMs and add custom tools\\nInfinite Scale\\nHandle millions of concurrent users with automatic scaling and load balancing\\nFuture Proof\\n\\\"Add new AI models anytime\\\" \\\"Integrate with any new tool or API\\\"\\nComplete Control\\n\\\"Full visibility into AI operations\\\" \\\"Manage costs and performance easily\\\"\\n## Questions Answers What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks\",\n",
- " \"It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching\",\n",
- " \"-Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing -Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching -Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing -Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement\",\n",
- " \"How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching -Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing.-Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks\",\n",
- " \"How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks ### Build faster using Julep API\\n### Deploy multi-step workflows easily with\\n### built-in tools and\\n### state management that is\\n### production ready from day one Keep me informed\\n### Build faster using Julep API\\n### Deploy multi-step workflows easily with built-in tools and State management that is production ready from day one Keep me informed\\nKeep me informed\\nKeep me informed\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\"\n",
- " ],\n",
- " \"How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching -Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing.-Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks\"\n",
- "]\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 13 Type: init_branch\n",
- "output: [\n",
- " [\n",
- " \"[\\n](./)\\n[\\nDocs\\n](https://docs.julep.ai/)\\n[\\nGithub\\n](https://github.com/julep-ai/julep)\\n[\\nDashboard\\n](https://dashboard.julep.ai/agents/)\\nExamples\\n[\\nDiscord\\n](https://discord.gg/2EUJzJU2Yt)\\n[\\nBook demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nContact Us\\n](./contact)\\n[\\n](./)\\n[\\n](./)\\nAnnouncing our Education+NGO program Eligible organizations get unlimited free credits Please apply[here](https://forms.gle/CCP6sDYeUfAXdUoi7) [](https://www.producthunt.com/posts/julep-ai)\\nOpen Source\\n[\\nGithub\\n\\u26054.4K\\n](https://github.com/julep-ai/julep)\\n# Buildscalable\\nAIworkflows\\ninminutes\\nAPI to build multi-step agent workflows\\n[\\nDeploy your first agent\\n](https://dashboard-dev.julep.ai/)\\n[\\nDeploy your first agent\\n](https://dashboard-dev.julep.ai/)\\n[\\nGet a demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nGet a demo\\n](< https://calendly.com/ishita-julep>)\\nCUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place CUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place CUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place ## Connect with any AI model,\\nAPI or data source\\nSeamlessly integrate with your existing stack and favorite AI models LLM Platforms\\nLanguages\\nIntegrations\\n* * * * * * Any REST API\\n## Real people, Real results\\n* Julep to me sits in the intersection of what Zapier did for simplifying workflows, and what Vercel did for simplifying shipping The new possibilities are endless I am excited abut what all can be done with this tech at ES Suryansh Tibarewal\\nCEO, EssentiallySports\\n* For Vidyo, we shipped 6 months worth of product development in 6 hours GAME CHANGER!\",\n",
- " \"Vedant Maheshwari\\nCEO, Vidyo.ai\\n* We tried building our ai stack where we needed simple automated computer use we spent months trying to get it right, but our development time got cut to a couple weeks because most of the infra orchestration was handled by julep all that we had to do was refine our prompts\\nMadhavan\\nCEO, Reclaim Protocol\\n* \\\"Same experience as reviewing designs on Figma with my designer Sat with my developer once, and we kept brainstorming, testing, prototyping and shipping at once I got control back in my hands as a non-developer.\\\"\\nAkshay Pruthi\\nCEO, Calm Sleep\\n* Working with Julep accelerated Ukumi, by enabling us to focus on our core strengths and letting Julep navigate the complex web of calls to ai models we could do more with less Sachin Gaur\\nCofounder, Ukumi AI\\n### Build with Julep\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\nDeploy\\nExecute production-grade workflows with one command\\nagent = julep.agents.create(\\nname=\\\"Spiderman\\\",\\nabout=\\\"AI that can crawl the web and extract data\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\ndefault\\\\_settings={\\n\\\"temperature\\\":0.75,\\n\\\"max\\\\_tokens\\\":10000,\\n\\\"top\\\\_p\\\":1.0,\\n}\\n)\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\njulep.agents.tools.create(\\nagent\\\\_id=agent.id,\\nname=\\\"my\\\\_weather\\\\_tool\\\",\\nintegration={\\n\\\"provider\\\":\\\"weather\\\",\\n\\\"setup\\\": {\\n\\\"openweathermap\\\\_api\\\\_key\\\":\\\"OPENWEATHERMAP\\\\_API\\\\_KEY\\\"\\n}\\n}\\n)\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\niimportyaml\\ntask =julep.task.create(\\\"\\\"\\\"\\nname: Weather Reporting Task\\nmain:\\n- tool: spider\\\\_crawler\\narguments:\\nurl: \\\\_.url\\n- prompt: |\\nHere\\u2019s a crawl of {{inputs[0].url}}:\\n{{\\\\_.documents}}\\nCreate a short summary (\\\\~100 words) of the website \\\"\\\"\\\")- city\\nDeploy\\nExecute production-grade workflows with one command\\nexecution = julep.executions.create(\\ntask\\\\_id=task.id,\\ninput={\\n\\\"url\\\": \\\"https://spider.cloud\\\"\\n}\\n)\\nagent = julep.agents.create(\\nname=\\\"Cristopher\\\",\\nabout=\\\"An agent specialized in weather reporting\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\n)\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\nDeploy\\nExecute production-grade workflows with one command\\nagent = julep.agents.create(\\nname=\\\"Spiderman\\\",\\nabout=\\\"AI that can crawl the web and extract data\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\ndefault\\\\_settings={\\n\\\"temperature\\\":0.75,\\n\\\"max\\\\_tokens\\\":10000,\\n\\\"top\\\\_p\\\":1.0,\\n}\\n)\\n## Build AI pipelines\\nin minutes Scale to millions Rapid Prototyping\\n\\\"From idea to demo in minutes\\\" using built-in RAG and state management\\nProduction Ready\\n\\\"Go live instantly with managed infrastructure\\\" and features such as long-running tasks, automatic retries and error handling\\nModular Design\\n\\\"Build features like Lego blocks\\\" by connecting to any external API, switch between LLMs and add custom tools\\nInfinite Scale\\nHandle millions of concurrent users with automatic scaling and load balancing\\nFuture Proof\\n\\\"Add new AI models anytime\\\" \\\"Integrate with any new tool or API\\\"\\nComplete Control\\n\\\"Full visibility into AI operations\\\" \\\"Manage costs and performance easily\\\"\\n## Questions Answers What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks\",\n",
- " \"It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching\",\n",
- " \"-Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing -Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching -Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing -Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement\",\n",
- " \"How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching -Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing.-Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks\",\n",
- " \"How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks ### Build faster using Julep API\\n### Deploy multi-step workflows easily with\\n### built-in tools and\\n### state management that is\\n### production ready from day one Keep me informed\\n### Build faster using Julep API\\n### Deploy multi-step workflows easily with built-in tools and State management that is production ready from day one Keep me informed\\nKeep me informed\\nKeep me informed\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\"\n",
- " ],\n",
- " \"-Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing -Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching -Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing -Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement\"\n",
- "]\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 14 Type: init_branch\n",
- "output: [\n",
- " [\n",
- " \"[\\n](./)\\n[\\nDocs\\n](https://docs.julep.ai/)\\n[\\nGithub\\n](https://github.com/julep-ai/julep)\\n[\\nDashboard\\n](https://dashboard.julep.ai/agents/)\\nExamples\\n[\\nDiscord\\n](https://discord.gg/2EUJzJU2Yt)\\n[\\nBook demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nContact Us\\n](./contact)\\n[\\n](./)\\n[\\n](./)\\nAnnouncing our Education+NGO program Eligible organizations get unlimited free credits Please apply[here](https://forms.gle/CCP6sDYeUfAXdUoi7) [](https://www.producthunt.com/posts/julep-ai)\\nOpen Source\\n[\\nGithub\\n\\u26054.4K\\n](https://github.com/julep-ai/julep)\\n# Buildscalable\\nAIworkflows\\ninminutes\\nAPI to build multi-step agent workflows\\n[\\nDeploy your first agent\\n](https://dashboard-dev.julep.ai/)\\n[\\nDeploy your first agent\\n](https://dashboard-dev.julep.ai/)\\n[\\nGet a demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nGet a demo\\n](< https://calendly.com/ishita-julep>)\\nCUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place CUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place CUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place ## Connect with any AI model,\\nAPI or data source\\nSeamlessly integrate with your existing stack and favorite AI models LLM Platforms\\nLanguages\\nIntegrations\\n* * * * * * Any REST API\\n## Real people, Real results\\n* Julep to me sits in the intersection of what Zapier did for simplifying workflows, and what Vercel did for simplifying shipping The new possibilities are endless I am excited abut what all can be done with this tech at ES Suryansh Tibarewal\\nCEO, EssentiallySports\\n* For Vidyo, we shipped 6 months worth of product development in 6 hours GAME CHANGER!\",\n",
- " \"Vedant Maheshwari\\nCEO, Vidyo.ai\\n* We tried building our ai stack where we needed simple automated computer use we spent months trying to get it right, but our development time got cut to a couple weeks because most of the infra orchestration was handled by julep all that we had to do was refine our prompts\\nMadhavan\\nCEO, Reclaim Protocol\\n* \\\"Same experience as reviewing designs on Figma with my designer Sat with my developer once, and we kept brainstorming, testing, prototyping and shipping at once I got control back in my hands as a non-developer.\\\"\\nAkshay Pruthi\\nCEO, Calm Sleep\\n* Working with Julep accelerated Ukumi, by enabling us to focus on our core strengths and letting Julep navigate the complex web of calls to ai models we could do more with less Sachin Gaur\\nCofounder, Ukumi AI\\n### Build with Julep\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\nDeploy\\nExecute production-grade workflows with one command\\nagent = julep.agents.create(\\nname=\\\"Spiderman\\\",\\nabout=\\\"AI that can crawl the web and extract data\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\ndefault\\\\_settings={\\n\\\"temperature\\\":0.75,\\n\\\"max\\\\_tokens\\\":10000,\\n\\\"top\\\\_p\\\":1.0,\\n}\\n)\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\njulep.agents.tools.create(\\nagent\\\\_id=agent.id,\\nname=\\\"my\\\\_weather\\\\_tool\\\",\\nintegration={\\n\\\"provider\\\":\\\"weather\\\",\\n\\\"setup\\\": {\\n\\\"openweathermap\\\\_api\\\\_key\\\":\\\"OPENWEATHERMAP\\\\_API\\\\_KEY\\\"\\n}\\n}\\n)\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\niimportyaml\\ntask =julep.task.create(\\\"\\\"\\\"\\nname: Weather Reporting Task\\nmain:\\n- tool: spider\\\\_crawler\\narguments:\\nurl: \\\\_.url\\n- prompt: |\\nHere\\u2019s a crawl of {{inputs[0].url}}:\\n{{\\\\_.documents}}\\nCreate a short summary (\\\\~100 words) of the website \\\"\\\"\\\")- city\\nDeploy\\nExecute production-grade workflows with one command\\nexecution = julep.executions.create(\\ntask\\\\_id=task.id,\\ninput={\\n\\\"url\\\": \\\"https://spider.cloud\\\"\\n}\\n)\\nagent = julep.agents.create(\\nname=\\\"Cristopher\\\",\\nabout=\\\"An agent specialized in weather reporting\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\n)\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\nDeploy\\nExecute production-grade workflows with one command\\nagent = julep.agents.create(\\nname=\\\"Spiderman\\\",\\nabout=\\\"AI that can crawl the web and extract data\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\ndefault\\\\_settings={\\n\\\"temperature\\\":0.75,\\n\\\"max\\\\_tokens\\\":10000,\\n\\\"top\\\\_p\\\":1.0,\\n}\\n)\\n## Build AI pipelines\\nin minutes Scale to millions Rapid Prototyping\\n\\\"From idea to demo in minutes\\\" using built-in RAG and state management\\nProduction Ready\\n\\\"Go live instantly with managed infrastructure\\\" and features such as long-running tasks, automatic retries and error handling\\nModular Design\\n\\\"Build features like Lego blocks\\\" by connecting to any external API, switch between LLMs and add custom tools\\nInfinite Scale\\nHandle millions of concurrent users with automatic scaling and load balancing\\nFuture Proof\\n\\\"Add new AI models anytime\\\" \\\"Integrate with any new tool or API\\\"\\nComplete Control\\n\\\"Full visibility into AI operations\\\" \\\"Manage costs and performance easily\\\"\\n## Questions Answers What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks\",\n",
- " \"It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching\",\n",
- " \"-Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing -Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching -Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing -Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement\",\n",
- " \"How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching -Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing.-Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks\",\n",
- " \"How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks ### Build faster using Julep API\\n### Deploy multi-step workflows easily with\\n### built-in tools and\\n### state management that is\\n### production ready from day one Keep me informed\\n### Build faster using Julep API\\n### Deploy multi-step workflows easily with built-in tools and State management that is production ready from day one Keep me informed\\nKeep me informed\\nKeep me informed\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\"\n",
- " ],\n",
- " \"How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks ### Build faster using Julep API\\n### Deploy multi-step workflows easily with\\n### built-in tools and\\n### state management that is\\n### production ready from day one Keep me informed\\n### Build faster using Julep API\\n### Deploy multi-step workflows easily with built-in tools and State management that is production ready from day one Keep me informed\\nKeep me informed\\nKeep me informed\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\"\n",
- "]\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 15 Type: finish_branch\n",
- "output: \"This chunk provides information about Julep's differences from other agent frameworks such as LangChain, highlighting its capabilities for creating persistent AI agents with complex workflows, state management, and production-ready features. It also mentions various developer resources and use cases available within the Julep platform.\"\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 16 Type: finish_branch\n",
- "output: \"The chunk describes Julep's unique approach to AI development, highlighting its 8-Factor Agent methodology that emphasizes software engineering principles, modular capabilities, model independence, context management, and full observability. It contrasts Julep with other platforms like LangChain, positioning Julep as a comprehensive platform for building robust, production-ready AI systems with persistent agents and complex workflows.\"\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 17 Type: finish_branch\n",
- "output: \"This chunk discusses Julep's unique approach to AI development using the 8-Factor Agent methodology, which emphasizes software engineering principles like context management, model independence, structured reasoning, and full observability to create robust, production-ready AI systems, differentiating it from typical AI development practices that focus primarily on prompt engineering.\"\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 18 Type: step\n",
- "output: [\n",
- " \"The document outlines features and capabilities of Julep, a platform for building AI workflows and agents. It showcases customer stories and testimonials highlighting the platform's efficiency and integration benefits with existing tech stacks, similar to how Zapier and Vercel simplify workflows and shipping, respectively. The document also promotes an Education+NGO program offering unlimited free credits to eligible organizations and provides various resources, including demos, integrations, and documentation, to support AI development.\",\n",
- " \"This chunk focuses on testimonials from CEOs and co-founders about their experiences using Julep AI, highlighting its benefits in reducing development time, enhancing collaboration, and leveraging AI for streamlined operations. It also outlines the process of building AI agents with Julep, including creating agents, equipping them with tools, defining tasks, and deploying workflows. The section emphasizes Julep's capabilities in rapid prototyping, modular design, infinite scalability, and comprehensive AI management.\",\n",
- " \"This chunk is part of a detailed description of the features and advantages of Julep, a platform for creating AI agents. It emphasizes Julep's capabilities in process management and error handling, and contrasts its disciplined approach to AI development with typical practices.\",\n",
- " \"This chunk discusses Julep's unique approach to AI development using the 8-Factor Agent methodology, which emphasizes software engineering principles like context management, model independence, structured reasoning, and full observability to create robust, production-ready AI systems, differentiating it from typical AI development practices that focus primarily on prompt engineering.\",\n",
- " \"The chunk describes Julep's unique approach to AI development, highlighting its 8-Factor Agent methodology that emphasizes software engineering principles, modular capabilities, model independence, context management, and full observability. It contrasts Julep with other platforms like LangChain, positioning Julep as a comprehensive platform for building robust, production-ready AI systems with persistent agents and complex workflows.\",\n",
- " \"This chunk provides information about Julep's differences from other agent frameworks such as LangChain, highlighting its capabilities for creating persistent AI agents with complex workflows, state management, and production-ready features. It also mentions various developer resources and use cases available within the Julep platform.\"\n",
- "]\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 19 Type: step\n",
- "output: {\n",
- " \"final_chunks\": [\n",
- " \"[\\n](./)\\n[\\nDocs\\n](https://docs.julep.ai/)\\n[\\nGithub\\n](https://github.com/julep-ai/julep)\\n[\\nDashboard\\n](https://dashboard.julep.ai/agents/)\\nExamples\\n[\\nDiscord\\n](https://discord.gg/2EUJzJU2Yt)\\n[\\nBook demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nContact Us\\n](./contact)\\n[\\n](./)\\n[\\n](./)\\nAnnouncing our Education+NGO program Eligible organizations get unlimited free credits Please apply[here](https://forms.gle/CCP6sDYeUfAXdUoi7) [](https://www.producthunt.com/posts/julep-ai)\\nOpen Source\\n[\\nGithub\\n\\u26054.4K\\n](https://github.com/julep-ai/julep)\\n# Buildscalable\\nAIworkflows\\ninminutes\\nAPI to build multi-step agent workflows\\n[\\nDeploy your first agent\\n](https://dashboard-dev.julep.ai/)\\n[\\nDeploy your first agent\\n](https://dashboard-dev.julep.ai/)\\n[\\nGet a demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nGet a demo\\n](< https://calendly.com/ishita-julep>)\\nCUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place CUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place CUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place ## Connect with any AI model,\\nAPI or data source\\nSeamlessly integrate with your existing stack and favorite AI models LLM Platforms\\nLanguages\\nIntegrations\\n* * * * * * Any REST API\\n## Real people, Real results\\n* Julep to me sits in the intersection of what Zapier did for simplifying workflows, and what Vercel did for simplifying shipping The new possibilities are endless I am excited abut what all can be done with this tech at ES Suryansh Tibarewal\\nCEO, EssentiallySports\\n* For Vidyo, we shipped 6 months worth of product development in 6 hours GAME CHANGER!\\nThe document outlines features and capabilities of Julep, a platform for building AI workflows and agents. It showcases customer stories and testimonials highlighting the platform's efficiency and integration benefits with existing tech stacks, similar to how Zapier and Vercel simplify workflows and shipping, respectively. The document also promotes an Education+NGO program offering unlimited free credits to eligible organizations and provides various resources, including demos, integrations, and documentation, to support AI development.\",\n",
- " \"Vedant Maheshwari\\nCEO, Vidyo.ai\\n* We tried building our ai stack where we needed simple automated computer use we spent months trying to get it right, but our development time got cut to a couple weeks because most of the infra orchestration was handled by julep all that we had to do was refine our prompts\\nMadhavan\\nCEO, Reclaim Protocol\\n* \\\"Same experience as reviewing designs on Figma with my designer Sat with my developer once, and we kept brainstorming, testing, prototyping and shipping at once I got control back in my hands as a non-developer.\\\"\\nAkshay Pruthi\\nCEO, Calm Sleep\\n* Working with Julep accelerated Ukumi, by enabling us to focus on our core strengths and letting Julep navigate the complex web of calls to ai models we could do more with less Sachin Gaur\\nCofounder, Ukumi AI\\n### Build with Julep\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\nDeploy\\nExecute production-grade workflows with one command\\nagent = julep.agents.create(\\nname=\\\"Spiderman\\\",\\nabout=\\\"AI that can crawl the web and extract data\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\ndefault\\\\_settings={\\n\\\"temperature\\\":0.75,\\n\\\"max\\\\_tokens\\\":10000,\\n\\\"top\\\\_p\\\":1.0,\\n}\\n)\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\njulep.agents.tools.create(\\nagent\\\\_id=agent.id,\\nname=\\\"my\\\\_weather\\\\_tool\\\",\\nintegration={\\n\\\"provider\\\":\\\"weather\\\",\\n\\\"setup\\\": {\\n\\\"openweathermap\\\\_api\\\\_key\\\":\\\"OPENWEATHERMAP\\\\_API\\\\_KEY\\\"\\n}\\n}\\n)\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\niimportyaml\\ntask =julep.task.create(\\\"\\\"\\\"\\nname: Weather Reporting Task\\nmain:\\n- tool: spider\\\\_crawler\\narguments:\\nurl: \\\\_.url\\n- prompt: |\\nHere\\u2019s a crawl of {{inputs[0].url}}:\\n{{\\\\_.documents}}\\nCreate a short summary (\\\\~100 words) of the website \\\"\\\"\\\")- city\\nDeploy\\nExecute production-grade workflows with one command\\nexecution = julep.executions.create(\\ntask\\\\_id=task.id,\\ninput={\\n\\\"url\\\": \\\"https://spider.cloud\\\"\\n}\\n)\\nagent = julep.agents.create(\\nname=\\\"Cristopher\\\",\\nabout=\\\"An agent specialized in weather reporting\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\n)\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\nDeploy\\nExecute production-grade workflows with one command\\nagent = julep.agents.create(\\nname=\\\"Spiderman\\\",\\nabout=\\\"AI that can crawl the web and extract data\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\ndefault\\\\_settings={\\n\\\"temperature\\\":0.75,\\n\\\"max\\\\_tokens\\\":10000,\\n\\\"top\\\\_p\\\":1.0,\\n}\\n)\\n## Build AI pipelines\\nin minutes Scale to millions Rapid Prototyping\\n\\\"From idea to demo in minutes\\\" using built-in RAG and state management\\nProduction Ready\\n\\\"Go live instantly with managed infrastructure\\\" and features such as long-running tasks, automatic retries and error handling\\nModular Design\\n\\\"Build features like Lego blocks\\\" by connecting to any external API, switch between LLMs and add custom tools\\nInfinite Scale\\nHandle millions of concurrent users with automatic scaling and load balancing\\nFuture Proof\\n\\\"Add new AI models anytime\\\" \\\"Integrate with any new tool or API\\\"\\nComplete Control\\n\\\"Full visibility into AI operations\\\" \\\"Manage costs and performance easily\\\"\\n## Questions Answers What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks\\nThis chunk focuses on testimonials from CEOs and co-founders about their experiences using Julep AI, highlighting its benefits in reducing development time, enhancing collaboration, and leveraging AI for streamlined operations. It also outlines the process of building AI agents with Julep, including creating agents, equipping them with tools, defining tasks, and deploying workflows. The section emphasizes Julep's capabilities in rapid prototyping, modular design, infinite scalability, and comprehensive AI management.\",\n",
- " \"It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching\\nThis chunk is part of a detailed description of the features and advantages of Julep, a platform for creating AI agents. It emphasizes Julep's capabilities in process management and error handling, and contrasts its disciplined approach to AI development with typical practices.\",\n",
- " \"-Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing -Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching -Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing -Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement\\nThis chunk discusses Julep's unique approach to AI development using the 8-Factor Agent methodology, which emphasizes software engineering principles like context management, model independence, structured reasoning, and full observability to create robust, production-ready AI systems, differentiating it from typical AI development practices that focus primarily on prompt engineering.\",\n",
- " \"How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching -Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing.-Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks\\nThe chunk describes Julep's unique approach to AI development, highlighting its 8-Factor Agent methodology that emphasizes software engineering principles, modular capabilities, model independence, context management, and full observability. It contrasts Julep with other platforms like LangChain, positioning Julep as a comprehensive platform for building robust, production-ready AI systems with persistent agents and complex workflows.\",\n",
- " \"How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks ### Build faster using Julep API\\n### Deploy multi-step workflows easily with\\n### built-in tools and\\n### state management that is\\n### production ready from day one Keep me informed\\n### Build faster using Julep API\\n### Deploy multi-step workflows easily with built-in tools and State management that is production ready from day one Keep me informed\\nKeep me informed\\nKeep me informed\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nThis chunk provides information about Julep's differences from other agent frameworks such as LangChain, highlighting its capabilities for creating persistent AI agents with complex workflows, state management, and production-ready features. It also mentions various developer resources and use cases available within the Julep platform.\"\n",
- " ]\n",
- "}\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 20 Type: init_branch\n",
- "output: \"[\\n](./)\\n[\\nDocs\\n](https://docs.julep.ai/)\\n[\\nGithub\\n](https://github.com/julep-ai/julep)\\n[\\nDashboard\\n](https://dashboard.julep.ai/agents/)\\nExamples\\n[\\nDiscord\\n](https://discord.gg/2EUJzJU2Yt)\\n[\\nBook demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nContact Us\\n](./contact)\\n[\\n](./)\\n[\\n](./)\\nAnnouncing our Education+NGO program Eligible organizations get unlimited free credits Please apply[here](https://forms.gle/CCP6sDYeUfAXdUoi7) [](https://www.producthunt.com/posts/julep-ai)\\nOpen Source\\n[\\nGithub\\n\\u26054.4K\\n](https://github.com/julep-ai/julep)\\n# Buildscalable\\nAIworkflows\\ninminutes\\nAPI to build multi-step agent workflows\\n[\\nDeploy your first agent\\n](https://dashboard-dev.julep.ai/)\\n[\\nDeploy your first agent\\n](https://dashboard-dev.julep.ai/)\\n[\\nGet a demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nGet a demo\\n](< https://calendly.com/ishita-julep>)\\nCUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place CUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place CUSTOMER STORIES\\nVidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place ## Connect with any AI model,\\nAPI or data source\\nSeamlessly integrate with your existing stack and favorite AI models LLM Platforms\\nLanguages\\nIntegrations\\n* * * * * * Any REST API\\n## Real people, Real results\\n* Julep to me sits in the intersection of what Zapier did for simplifying workflows, and what Vercel did for simplifying shipping The new possibilities are endless I am excited abut what all can be done with this tech at ES Suryansh Tibarewal\\nCEO, EssentiallySports\\n* For Vidyo, we shipped 6 months worth of product development in 6 hours GAME CHANGER!\\nThe document outlines features and capabilities of Julep, a platform for building AI workflows and agents. It showcases customer stories and testimonials highlighting the platform's efficiency and integration benefits with existing tech stacks, similar to how Zapier and Vercel simplify workflows and shipping, respectively. The document also promotes an Education+NGO program offering unlimited free credits to eligible organizations and provides various resources, including demos, integrations, and documentation, to support AI development.\"\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 21 Type: init_branch\n",
- "output: \"It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\\n- Automatic retries for failed steps\\n- Message resending\\n- Task recovery\\n- Error handling\\n- Real-time monitoring How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching\\nThis chunk is part of a detailed description of the features and advantages of Julep, a platform for creating AI agents. It emphasizes Julep's capabilities in process management and error handling, and contrasts its disciplined approach to AI development with typical practices.\"\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 22 Type: init_branch\n",
- "output: \"Vedant Maheshwari\\nCEO, Vidyo.ai\\n* We tried building our ai stack where we needed simple automated computer use we spent months trying to get it right, but our development time got cut to a couple weeks because most of the infra orchestration was handled by julep all that we had to do was refine our prompts\\nMadhavan\\nCEO, Reclaim Protocol\\n* \\\"Same experience as reviewing designs on Figma with my designer Sat with my developer once, and we kept brainstorming, testing, prototyping and shipping at once I got control back in my hands as a non-developer.\\\"\\nAkshay Pruthi\\nCEO, Calm Sleep\\n* Working with Julep accelerated Ukumi, by enabling us to focus on our core strengths and letting Julep navigate the complex web of calls to ai models we could do more with less Sachin Gaur\\nCofounder, Ukumi AI\\n### Build with Julep\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\nDeploy\\nExecute production-grade workflows with one command\\nagent = julep.agents.create(\\nname=\\\"Spiderman\\\",\\nabout=\\\"AI that can crawl the web and extract data\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\ndefault\\\\_settings={\\n\\\"temperature\\\":0.75,\\n\\\"max\\\\_tokens\\\":10000,\\n\\\"top\\\\_p\\\":1.0,\\n}\\n)\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\njulep.agents.tools.create(\\nagent\\\\_id=agent.id,\\nname=\\\"my\\\\_weather\\\\_tool\\\",\\nintegration={\\n\\\"provider\\\":\\\"weather\\\",\\n\\\"setup\\\": {\\n\\\"openweathermap\\\\_api\\\\_key\\\":\\\"OPENWEATHERMAP\\\\_API\\\\_KEY\\\"\\n}\\n}\\n)\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\niimportyaml\\ntask =julep.task.create(\\\"\\\"\\\"\\nname: Weather Reporting Task\\nmain:\\n- tool: spider\\\\_crawler\\narguments:\\nurl: \\\\_.url\\n- prompt: |\\nHere\\u2019s a crawl of {{inputs[0].url}}:\\n{{\\\\_.documents}}\\nCreate a short summary (\\\\~100 words) of the website \\\"\\\"\\\")- city\\nDeploy\\nExecute production-grade workflows with one command\\nexecution = julep.executions.create(\\ntask\\\\_id=task.id,\\ninput={\\n\\\"url\\\": \\\"https://spider.cloud\\\"\\n}\\n)\\nagent = julep.agents.create(\\nname=\\\"Cristopher\\\",\\nabout=\\\"An agent specialized in weather reporting\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\n)\\nCreate an agent\\nDefine agents that can talk to users inside of a session\\nAdd tools\\nEquip agents with tools - web search, API calls, or custom integrations\\nDefine your tasks\\nDefine multi-step processes in YAML with decision trees, loops, and parallel execution\\nDeploy\\nExecute production-grade workflows with one command\\nagent = julep.agents.create(\\nname=\\\"Spiderman\\\",\\nabout=\\\"AI that can crawl the web and extract data\\\",\\nmodel=\\\"gpt-4o-mini\\\",\\ndefault\\\\_settings={\\n\\\"temperature\\\":0.75,\\n\\\"max\\\\_tokens\\\":10000,\\n\\\"top\\\\_p\\\":1.0,\\n}\\n)\\n## Build AI pipelines\\nin minutes Scale to millions Rapid Prototyping\\n\\\"From idea to demo in minutes\\\" using built-in RAG and state management\\nProduction Ready\\n\\\"Go live instantly with managed infrastructure\\\" and features such as long-running tasks, automatic retries and error handling\\nModular Design\\n\\\"Build features like Lego blocks\\\" by connecting to any external API, switch between LLMs and add custom tools\\nInfinite Scale\\nHandle millions of concurrent users with automatic scaling and load balancing\\nFuture Proof\\n\\\"Add new AI models anytime\\\" \\\"Integrate with any new tool or API\\\"\\nComplete Control\\n\\\"Full visibility into AI operations\\\" \\\"Manage costs and performance easily\\\"\\n## Questions Answers What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks\\nThis chunk focuses on testimonials from CEOs and co-founders about their experiences using Julep AI, highlighting its benefits in reducing development time, enhancing collaboration, and leveraging AI for streamlined operations. It also outlines the process of building AI agents with Julep, including creating agents, equipping them with tools, defining tasks, and deploying workflows. The section emphasizes Julep's capabilities in rapid prototyping, modular design, infinite scalability, and comprehensive AI management.\"\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 23 Type: finish_branch\n",
- "output: {\n",
- " \"id\": \"0678f7c3-dfc5-76b4-8000-b8c198ba7995\",\n",
- " \"jobs\": [],\n",
- " \"created_at\": \"2025-01-21T10:51:42.035897Z\"\n",
- "}\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 24 Type: finish_branch\n",
- "output: {\n",
- " \"id\": \"0678f7c3-dfbd-767b-8000-3e938c8bd27f\",\n",
- " \"jobs\": [],\n",
- " \"created_at\": \"2025-01-21T10:51:42.035552Z\"\n",
- "}\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 25 Type: finish_branch\n",
- "output: {\n",
- " \"id\": \"0678f7c3-e081-7ab4-8000-ff2c32bcfec3\",\n",
- " \"jobs\": [],\n",
- " \"created_at\": \"2025-01-21T10:51:42.081588Z\"\n",
- "}\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 26 Type: init_branch\n",
- "output: \"How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks ### Build faster using Julep API\\n### Deploy multi-step workflows easily with\\n### built-in tools and\\n### state management that is\\n### production ready from day one Keep me informed\\n### Build faster using Julep API\\n### Deploy multi-step workflows easily with built-in tools and State management that is production ready from day one Keep me informed\\nKeep me informed\\nKeep me informed\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nThis chunk provides information about Julep's differences from other agent frameworks such as LangChain, highlighting its capabilities for creating persistent AI agents with complex workflows, state management, and production-ready features. It also mentions various developer resources and use cases available within the Julep platform.\"\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 27 Type: init_branch\n",
- "output: \"-Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing -Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching -Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing -Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement\\nThis chunk discusses Julep's unique approach to AI development using the 8-Factor Agent methodology, which emphasizes software engineering principles like context management, model independence, structured reasoning, and full observability to create robust, production-ready AI systems, differentiating it from typical AI development practices that focus primarily on prompt engineering.\"\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 28 Type: init_branch\n",
- "output: \"How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\\n- Prompts as Code:\\nTrack prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\\nDefine explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\\nTreat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching -Context Management:\\nExplicitly define how application and user state is managed and reduced -Ground Truth Examples:\\nMaintain clear examples of expected prompt results for validation and testing.-Structured Reasoning:\\nSeparate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\\ncomplex processes as clear workflows rather than chains of prompts -Full Observability:\\nSave execution traces for debugging, monitoring, and continuous improvement How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks\\nThe chunk describes Julep's unique approach to AI development, highlighting its 8-Factor Agent methodology that emphasizes software engineering principles, modular capabilities, model independence, context management, and full observability. It contrasts Julep with other platforms like LangChain, positioning Julep as a comprehensive platform for building robust, production-ready AI systems with persistent agents and complex workflows.\"\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 29 Type: finish_branch\n",
- "output: {\n",
- " \"id\": \"0678f7c3-e8db-784d-8000-f45ae9b85623\",\n",
- " \"jobs\": [],\n",
- " \"created_at\": \"2025-01-21T10:51:42.590278Z\"\n",
- "}\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 30 Type: finish_branch\n",
- "output: {\n",
- " \"id\": \"0678f7c3-e981-7952-8000-3593fbc19d2a\",\n",
- " \"jobs\": [],\n",
- " \"created_at\": \"2025-01-21T10:51:42.630494Z\"\n",
- "}\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 31 Type: finish_branch\n",
- "output: {\n",
- " \"id\": \"0678f7c3-e945-70b6-8000-a1c494662a11\",\n",
- " \"jobs\": [],\n",
- " \"created_at\": \"2025-01-21T10:51:42.630639Z\"\n",
- "}\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 32 Type: finish_branch\n",
- "output: [\n",
- " {\n",
- " \"id\": \"0678f7c3-dfc5-76b4-8000-b8c198ba7995\",\n",
- " \"jobs\": [],\n",
- " \"created_at\": \"2025-01-21T10:51:42.035897Z\"\n",
- " },\n",
- " {\n",
- " \"id\": \"0678f7c3-e081-7ab4-8000-ff2c32bcfec3\",\n",
- " \"jobs\": [],\n",
- " \"created_at\": \"2025-01-21T10:51:42.081588Z\"\n",
- " },\n",
- " {\n",
- " \"id\": \"0678f7c3-dfbd-767b-8000-3e938c8bd27f\",\n",
- " \"jobs\": [],\n",
- " \"created_at\": \"2025-01-21T10:51:42.035552Z\"\n",
- " },\n",
- " {\n",
- " \"id\": \"0678f7c3-e945-70b6-8000-a1c494662a11\",\n",
- " \"jobs\": [],\n",
- " \"created_at\": \"2025-01-21T10:51:42.630639Z\"\n",
- " },\n",
- " {\n",
- " \"id\": \"0678f7c3-e981-7952-8000-3593fbc19d2a\",\n",
- " \"jobs\": [],\n",
- " \"created_at\": \"2025-01-21T10:51:42.630494Z\"\n",
- " },\n",
- " {\n",
- " \"id\": \"0678f7c3-e8db-784d-8000-f45ae9b85623\",\n",
- " \"jobs\": [],\n",
- " \"created_at\": \"2025-01-21T10:51:42.590278Z\"\n",
- " }\n",
- "]\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 33 Type: finish_branch\n",
- "output: [\n",
- " {\n",
- " \"id\": \"0678f7c3-dfc5-76b4-8000-b8c198ba7995\",\n",
- " \"jobs\": [],\n",
- " \"created_at\": \"2025-01-21T10:51:42.035897Z\"\n",
- " },\n",
- " {\n",
- " \"id\": \"0678f7c3-e081-7ab4-8000-ff2c32bcfec3\",\n",
- " \"jobs\": [],\n",
- " \"created_at\": \"2025-01-21T10:51:42.081588Z\"\n",
- " },\n",
- " {\n",
- " \"id\": \"0678f7c3-dfbd-767b-8000-3e938c8bd27f\",\n",
- " \"jobs\": [],\n",
- " \"created_at\": \"2025-01-21T10:51:42.035552Z\"\n",
- " },\n",
- " {\n",
- " \"id\": \"0678f7c3-e945-70b6-8000-a1c494662a11\",\n",
- " \"jobs\": [],\n",
- " \"created_at\": \"2025-01-21T10:51:42.630639Z\"\n",
- " },\n",
- " {\n",
- " \"id\": \"0678f7c3-e981-7952-8000-3593fbc19d2a\",\n",
- " \"jobs\": [],\n",
- " \"created_at\": \"2025-01-21T10:51:42.630494Z\"\n",
- " },\n",
- " {\n",
- " \"id\": \"0678f7c3-e8db-784d-8000-f45ae9b85623\",\n",
- " \"jobs\": [],\n",
- " \"created_at\": \"2025-01-21T10:51:42.590278Z\"\n",
- " }\n",
- "]\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 34 Type: init_branch\n",
- "output: {\n",
- " \"url\": \"https://julep.ai/about\",\n",
- " \"costs\": {\n",
- " \"ai_cost\": 0,\n",
- " \"file_cost\": 0.0001,\n",
- " \"total_cost\": 0.0003,\n",
- " \"compute_cost\": 0.0001,\n",
- " \"transform_cost\": 0.0001,\n",
- " \"bytes_transferred_cost\": 0\n",
- " },\n",
- " \"error\": null,\n",
- " \"status\": 200,\n",
- " \"content\": [\n",
- " \"[\\n](./)\\n[\\nDocs\\n](https://docs.julep.ai/)\\n[\\nGithub\\n](https://github.com/julep-ai/julep)\\n[\\nDashboard\\n](https://dashboard.julep.ai/agents/)\\nExamples\\n[\\nDiscord\\n](https://discord.gg/2EUJzJU2Yt)\\n[\\nBook demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nContact Us\\n](./contact)\\n[\\n](./)\\n[\\n](./)\\n# MakingAIDevelopment\\nWhatItShouldBe\\nTwo years ago, we started Julep with a simple belief: making intelligence more human shouldn't mean making engineering less rigorous While the world rushed to stack prompts and call it engineering, we chose to build something foundational We created the 8-Factor Agent methodology not because it was easy, but because AI development deserves real tools, real engineering, and real infrastructure We're engineers who believe the future of software will be built on AI - not as a collection of clever hacks, but as properly engineered systems with clear interfaces, predictable behavior, and production-grade reliability Julep isn't another abstraction layer or prompt management tool It's a complete rethinking of how AI applications should be built, tested, and scaled Our task language isn't another abstraction layer; it's a new way to think about AI workflows Our infrastructure isn't just about scaling; it's about bringing reliability and rigor to a field that sorely needs it Because taking the hard path to simple AI development isn't just our approach - it's our conviction that this is how it should be done We're building the foundation for AI's future, not chasing its hype * * * Dev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\"\n",
- " ]\n",
- "}\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 35 Type: step\n",
- "output: {\n",
- " \"content\": [\n",
- " \"[\\n](./)\\n[\\nDocs\\n](https://docs.julep.ai/)\\n[\\nGithub\\n](https://github.com/julep-ai/julep)\\n[\\nDashboard\\n](https://dashboard.julep.ai/agents/)\\nExamples\\n[\\nDiscord\\n](https://discord.gg/2EUJzJU2Yt)\\n[\\nBook demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nContact Us\\n](./contact)\\n[\\n](./)\\n[\\n](./)\\n# MakingAIDevelopment\\nWhatItShouldBe\\nTwo years ago, we started Julep with a simple belief: making intelligence more human shouldn't mean making engineering less rigorous While the world rushed to stack prompts and call it engineering, we chose to build something foundational We created the 8-Factor Agent methodology not because it was easy, but because AI development deserves real tools, real engineering, and real infrastructure We're engineers who believe the future of software will be built on AI - not as a collection of clever hacks, but as properly engineered systems with clear interfaces, predictable behavior, and production-grade reliability Julep isn't another abstraction layer or prompt management tool It's a complete rethinking of how AI applications should be built, tested, and scaled Our task language isn't another abstraction layer; it's a new way to think about AI workflows Our infrastructure isn't just about scaling; it's about bringing reliability and rigor to a field that sorely needs it Because taking the hard path to simple AI development isn't just our approach - it's our conviction that this is how it should be done We're building the foundation for AI's future, not chasing its hype * * * Dev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\"\n",
- " ]\n",
- "}\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 36 Type: init_branch\n",
- "output: {\n",
- " \"content\": [\n",
- " \"[\\n](./)\\n[\\nDocs\\n](https://docs.julep.ai/)\\n[\\nGithub\\n](https://github.com/julep-ai/julep)\\n[\\nDashboard\\n](https://dashboard.julep.ai/agents/)\\nExamples\\n[\\nDiscord\\n](https://discord.gg/2EUJzJU2Yt)\\n[\\nBook demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nContact Us\\n](./contact)\\n[\\n](./)\\n[\\n](./)\\n# MakingAIDevelopment\\nWhatItShouldBe\\nTwo years ago, we started Julep with a simple belief: making intelligence more human shouldn't mean making engineering less rigorous While the world rushed to stack prompts and call it engineering, we chose to build something foundational We created the 8-Factor Agent methodology not because it was easy, but because AI development deserves real tools, real engineering, and real infrastructure We're engineers who believe the future of software will be built on AI - not as a collection of clever hacks, but as properly engineered systems with clear interfaces, predictable behavior, and production-grade reliability Julep isn't another abstraction layer or prompt management tool It's a complete rethinking of how AI applications should be built, tested, and scaled Our task language isn't another abstraction layer; it's a new way to think about AI workflows Our infrastructure isn't just about scaling; it's about bringing reliability and rigor to a field that sorely needs it Because taking the hard path to simple AI development isn't just our approach - it's our conviction that this is how it should be done We're building the foundation for AI's future, not chasing its hype * * * Dev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\"\n",
- " ]\n",
- "}\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 37 Type: step\n",
- "output: {\n",
- " \"documents\": [\n",
- " \"[\\n](./)\\n[\\nDocs\\n](https://docs.julep.ai/)\\n[\\nGithub\\n](https://github.com/julep-ai/julep)\\n[\\nDashboard\\n](https://dashboard.julep.ai/agents/)\\nExamples\\n[\\nDiscord\\n](https://discord.gg/2EUJzJU2Yt)\\n[\\nBook demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nContact Us\\n](./contact)\\n[\\n](./)\\n[\\n](./)\\n# MakingAIDevelopment\\nWhatItShouldBe\\nTwo years ago, we started Julep with a simple belief: making intelligence more human shouldn't mean making engineering less rigorous While the world rushed to stack prompts and call it engineering, we chose to build something foundational We created the 8-Factor Agent methodology not because it was easy, but because AI development deserves real tools, real engineering, and real infrastructure We're engineers who believe the future of software will be built on AI - not as a collection of clever hacks, but as properly engineered systems with clear interfaces, predictable behavior, and production-grade reliability Julep isn't another abstraction layer or prompt management tool It's a complete rethinking of how AI applications should be built, tested, and scaled Our task language isn't another abstraction layer; it's a new way to think about AI workflows Our infrastructure isn't just about scaling; it's about bringing reliability and rigor to a field that sorely needs it Because taking the hard path to simple AI development isn't just our approach - it's our conviction that this is how it should be done We're building the foundation for AI's future, not chasing its hype * * * Dev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\"\n",
- " ]\n",
- "}\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 38 Type: init_branch\n",
- "output: [\n",
- " [\n",
- " \"[\\n](./)\\n[\\nDocs\\n](https://docs.julep.ai/)\\n[\\nGithub\\n](https://github.com/julep-ai/julep)\\n[\\nDashboard\\n](https://dashboard.julep.ai/agents/)\\nExamples\\n[\\nDiscord\\n](https://discord.gg/2EUJzJU2Yt)\\n[\\nBook demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nContact Us\\n](./contact)\\n[\\n](./)\\n[\\n](./)\\n# MakingAIDevelopment\\nWhatItShouldBe\\nTwo years ago, we started Julep with a simple belief: making intelligence more human shouldn't mean making engineering less rigorous While the world rushed to stack prompts and call it engineering, we chose to build something foundational We created the 8-Factor Agent methodology not because it was easy, but because AI development deserves real tools, real engineering, and real infrastructure We're engineers who believe the future of software will be built on AI - not as a collection of clever hacks, but as properly engineered systems with clear interfaces, predictable behavior, and production-grade reliability Julep isn't another abstraction layer or prompt management tool It's a complete rethinking of how AI applications should be built, tested, and scaled Our task language isn't another abstraction layer; it's a new way to think about AI workflows Our infrastructure isn't just about scaling; it's about bringing reliability and rigor to a field that sorely needs it Because taking the hard path to simple AI development isn't just our approach - it's our conviction that this is how it should be done We're building the foundation for AI's future, not chasing its hype * * * Dev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\"\n",
- " ],\n",
- " \"[\\n](./)\\n[\\nDocs\\n](https://docs.julep.ai/)\\n[\\nGithub\\n](https://github.com/julep-ai/julep)\\n[\\nDashboard\\n](https://dashboard.julep.ai/agents/)\\nExamples\\n[\\nDiscord\\n](https://discord.gg/2EUJzJU2Yt)\\n[\\nBook demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nContact Us\\n](./contact)\\n[\\n](./)\\n[\\n](./)\\n# MakingAIDevelopment\\nWhatItShouldBe\\nTwo years ago, we started Julep with a simple belief: making intelligence more human shouldn't mean making engineering less rigorous While the world rushed to stack prompts and call it engineering, we chose to build something foundational We created the 8-Factor Agent methodology not because it was easy, but because AI development deserves real tools, real engineering, and real infrastructure We're engineers who believe the future of software will be built on AI - not as a collection of clever hacks, but as properly engineered systems with clear interfaces, predictable behavior, and production-grade reliability Julep isn't another abstraction layer or prompt management tool It's a complete rethinking of how AI applications should be built, tested, and scaled Our task language isn't another abstraction layer; it's a new way to think about AI workflows Our infrastructure isn't just about scaling; it's about bringing reliability and rigor to a field that sorely needs it Because taking the hard path to simple AI development isn't just our approach - it's our conviction that this is how it should be done We're building the foundation for AI's future, not chasing its hype * * * Dev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\"\n",
- "]\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 39 Type: finish_branch\n",
- "output: \"The chunk is an introduction and overview of Julep's mission, philosophy, and resources focused on AI development. It highlights Julep's unique methodology for building AI applications with rigor and infrastructure and provides links to developer resources, use cases, company information, and social media.\"\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 40 Type: step\n",
- "output: [\n",
- " \"The chunk is an introduction and overview of Julep's mission, philosophy, and resources focused on AI development. It highlights Julep's unique methodology for building AI applications with rigor and infrastructure and provides links to developer resources, use cases, company information, and social media.\"\n",
- "]\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 41 Type: step\n",
- "output: {\n",
- " \"final_chunks\": [\n",
- " \"[\\n](./)\\n[\\nDocs\\n](https://docs.julep.ai/)\\n[\\nGithub\\n](https://github.com/julep-ai/julep)\\n[\\nDashboard\\n](https://dashboard.julep.ai/agents/)\\nExamples\\n[\\nDiscord\\n](https://discord.gg/2EUJzJU2Yt)\\n[\\nBook demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nContact Us\\n](./contact)\\n[\\n](./)\\n[\\n](./)\\n# MakingAIDevelopment\\nWhatItShouldBe\\nTwo years ago, we started Julep with a simple belief: making intelligence more human shouldn't mean making engineering less rigorous While the world rushed to stack prompts and call it engineering, we chose to build something foundational We created the 8-Factor Agent methodology not because it was easy, but because AI development deserves real tools, real engineering, and real infrastructure We're engineers who believe the future of software will be built on AI - not as a collection of clever hacks, but as properly engineered systems with clear interfaces, predictable behavior, and production-grade reliability Julep isn't another abstraction layer or prompt management tool It's a complete rethinking of how AI applications should be built, tested, and scaled Our task language isn't another abstraction layer; it's a new way to think about AI workflows Our infrastructure isn't just about scaling; it's about bringing reliability and rigor to a field that sorely needs it Because taking the hard path to simple AI development isn't just our approach - it's our conviction that this is how it should be done We're building the foundation for AI's future, not chasing its hype * * * Dev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nThe chunk is an introduction and overview of Julep's mission, philosophy, and resources focused on AI development. It highlights Julep's unique methodology for building AI applications with rigor and infrastructure and provides links to developer resources, use cases, company information, and social media.\"\n",
- " ]\n",
- "}\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 42 Type: init_branch\n",
- "output: \"[\\n](./)\\n[\\nDocs\\n](https://docs.julep.ai/)\\n[\\nGithub\\n](https://github.com/julep-ai/julep)\\n[\\nDashboard\\n](https://dashboard.julep.ai/agents/)\\nExamples\\n[\\nDiscord\\n](https://discord.gg/2EUJzJU2Yt)\\n[\\nBook demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nContact Us\\n](./contact)\\n[\\n](./)\\n[\\n](./)\\n# MakingAIDevelopment\\nWhatItShouldBe\\nTwo years ago, we started Julep with a simple belief: making intelligence more human shouldn't mean making engineering less rigorous While the world rushed to stack prompts and call it engineering, we chose to build something foundational We created the 8-Factor Agent methodology not because it was easy, but because AI development deserves real tools, real engineering, and real infrastructure We're engineers who believe the future of software will be built on AI - not as a collection of clever hacks, but as properly engineered systems with clear interfaces, predictable behavior, and production-grade reliability Julep isn't another abstraction layer or prompt management tool It's a complete rethinking of how AI applications should be built, tested, and scaled Our task language isn't another abstraction layer; it's a new way to think about AI workflows Our infrastructure isn't just about scaling; it's about bringing reliability and rigor to a field that sorely needs it Because taking the hard path to simple AI development isn't just our approach - it's our conviction that this is how it should be done We're building the foundation for AI's future, not chasing its hype * * * Dev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nThe chunk is an introduction and overview of Julep's mission, philosophy, and resources focused on AI development. It highlights Julep's unique methodology for building AI applications with rigor and infrastructure and provides links to developer resources, use cases, company information, and social media.\"\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 43 Type: finish_branch\n",
- "output: {\n",
- " \"id\": \"0678f7c4-33d5-731a-8000-7472c8f36677\",\n",
- " \"jobs\": [],\n",
- " \"created_at\": \"2025-01-21T10:51:47.277809Z\"\n",
- "}\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 44 Type: finish_branch\n",
- "output: [\n",
- " {\n",
- " \"id\": \"0678f7c4-33d5-731a-8000-7472c8f36677\",\n",
- " \"jobs\": [],\n",
- " \"created_at\": \"2025-01-21T10:51:47.277809Z\"\n",
- " }\n",
- "]\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 45 Type: finish_branch\n",
- "output: [\n",
- " {\n",
- " \"id\": \"0678f7c4-33d5-731a-8000-7472c8f36677\",\n",
- " \"jobs\": [],\n",
- " \"created_at\": \"2025-01-21T10:51:47.277809Z\"\n",
- " }\n",
- "]\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 46 Type: init_branch\n",
- "output: {\n",
- " \"url\": \"https://julep.ai/contact\",\n",
- " \"costs\": {\n",
- " \"ai_cost\": 0,\n",
- " \"file_cost\": 0.0002,\n",
- " \"total_cost\": 0.0004,\n",
- " \"compute_cost\": 0.0001,\n",
- " \"transform_cost\": 0.0001,\n",
- " \"bytes_transferred_cost\": 0\n",
- " },\n",
- " \"error\": null,\n",
- " \"status\": 200,\n",
- " \"content\": [\n",
- " \"[\\n](./)\\n[\\nDocs\\n](https://docs.julep.ai/)\\n[\\nGithub\\n](https://github.com/julep-ai/julep)\\n[\\nDashboard\\n](https://dashboard.julep.ai/agents/)\\nExamples\\n[\\nDiscord\\n](https://discord.gg/2EUJzJU2Yt)\\n[\\nBook demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nContact Us\\n](./contact)\\n[\\n](./)\\n[\\n](./)\\n## How can we help you today We\\u2019re here to help Reach out to learn more about Synth Assistant or start your AI journey today\\nDev Support\\nhey@julep.ai\\nDev Support\\nhey@julep.ai\\nDev Support\\nhey@julep.ai\\nBook a demo\\nBook\\nBook a demo\\nBook\\nBook a demo\\nBook\\nJoin Our Community\\nDiscord\\nJoin Our Community\\nDiscord\\nJoin Our Community\\nDiscord\\nor\\nName\\nEmail\\nEmail\\nSubmit\\nSubmit\\nSubmit\\n### Build faster using Julep API\\n### Deploy multi-step workflows easily with\\n### built-in tools and\\n### State management that is\\n### production ready from day one Keep me informed\\n### Build faster using Julep API\\n### Deploy multi-step workflows easily with built-in tools and State management that is production ready from day one Keep me informed\\nKeep me informed\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\"\n",
- " ]\n",
- "}\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 47 Type: step\n",
- "output: {\n",
- " \"content\": [\n",
- " \"[\\n](./)\\n[\\nDocs\\n](https://docs.julep.ai/)\\n[\\nGithub\\n](https://github.com/julep-ai/julep)\\n[\\nDashboard\\n](https://dashboard.julep.ai/agents/)\\nExamples\\n[\\nDiscord\\n](https://discord.gg/2EUJzJU2Yt)\\n[\\nBook demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nContact Us\\n](./contact)\\n[\\n](./)\\n[\\n](./)\\n## How can we help you today We\\u2019re here to help Reach out to learn more about Synth Assistant or start your AI journey today\\nDev Support\\nhey@julep.ai\\nDev Support\\nhey@julep.ai\\nDev Support\\nhey@julep.ai\\nBook a demo\\nBook\\nBook a demo\\nBook\\nBook a demo\\nBook\\nJoin Our Community\\nDiscord\\nJoin Our Community\\nDiscord\\nJoin Our Community\\nDiscord\\nor\\nName\\nEmail\\nEmail\\nSubmit\\nSubmit\\nSubmit\\n### Build faster using Julep API\\n### Deploy multi-step workflows easily with\\n### built-in tools and\\n### State management that is\\n### production ready from day one Keep me informed\\n### Build faster using Julep API\\n### Deploy multi-step workflows easily with built-in tools and State management that is production ready from day one Keep me informed\\nKeep me informed\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\"\n",
- " ]\n",
- "}\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 48 Type: init_branch\n",
- "output: {\n",
- " \"content\": [\n",
- " \"[\\n](./)\\n[\\nDocs\\n](https://docs.julep.ai/)\\n[\\nGithub\\n](https://github.com/julep-ai/julep)\\n[\\nDashboard\\n](https://dashboard.julep.ai/agents/)\\nExamples\\n[\\nDiscord\\n](https://discord.gg/2EUJzJU2Yt)\\n[\\nBook demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nContact Us\\n](./contact)\\n[\\n](./)\\n[\\n](./)\\n## How can we help you today We\\u2019re here to help Reach out to learn more about Synth Assistant or start your AI journey today\\nDev Support\\nhey@julep.ai\\nDev Support\\nhey@julep.ai\\nDev Support\\nhey@julep.ai\\nBook a demo\\nBook\\nBook a demo\\nBook\\nBook a demo\\nBook\\nJoin Our Community\\nDiscord\\nJoin Our Community\\nDiscord\\nJoin Our Community\\nDiscord\\nor\\nName\\nEmail\\nEmail\\nSubmit\\nSubmit\\nSubmit\\n### Build faster using Julep API\\n### Deploy multi-step workflows easily with\\n### built-in tools and\\n### State management that is\\n### production ready from day one Keep me informed\\n### Build faster using Julep API\\n### Deploy multi-step workflows easily with built-in tools and State management that is production ready from day one Keep me informed\\nKeep me informed\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\"\n",
- " ]\n",
- "}\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 49 Type: step\n",
- "output: {\n",
- " \"documents\": [\n",
- " \"[\\n](./)\\n[\\nDocs\\n](https://docs.julep.ai/)\\n[\\nGithub\\n](https://github.com/julep-ai/julep)\\n[\\nDashboard\\n](https://dashboard.julep.ai/agents/)\\nExamples\\n[\\nDiscord\\n](https://discord.gg/2EUJzJU2Yt)\\n[\\nBook demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nContact Us\\n](./contact)\\n[\\n](./)\\n[\\n](./)\\n## How can we help you today We\\u2019re here to help Reach out to learn more about Synth Assistant or start your AI journey today\\nDev Support\\nhey@julep.ai\\nDev Support\\nhey@julep.ai\\nDev Support\\nhey@julep.ai\\nBook a demo\\nBook\\nBook a demo\\nBook\\nBook a demo\\nBook\\nJoin Our Community\\nDiscord\\nJoin Our Community\\nDiscord\\nJoin Our Community\\nDiscord\\nor\\nName\\nEmail\\nEmail\\nSubmit\\nSubmit\\nSubmit\\n### Build faster using Julep API\\n### Deploy multi-step workflows easily with\\n### built-in tools and\\n### State management that is\\n### production ready from day one Keep me informed\\n### Build faster using Julep API\\n### Deploy multi-step workflows easily with built-in tools and State management that is production ready from day one Keep me informed\\nKeep me informed\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\"\n",
- " ]\n",
- "}\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 50 Type: init_branch\n",
- "output: [\n",
- " [\n",
- " \"[\\n](./)\\n[\\nDocs\\n](https://docs.julep.ai/)\\n[\\nGithub\\n](https://github.com/julep-ai/julep)\\n[\\nDashboard\\n](https://dashboard.julep.ai/agents/)\\nExamples\\n[\\nDiscord\\n](https://discord.gg/2EUJzJU2Yt)\\n[\\nBook demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nContact Us\\n](./contact)\\n[\\n](./)\\n[\\n](./)\\n## How can we help you today We\\u2019re here to help Reach out to learn more about Synth Assistant or start your AI journey today\\nDev Support\\nhey@julep.ai\\nDev Support\\nhey@julep.ai\\nDev Support\\nhey@julep.ai\\nBook a demo\\nBook\\nBook a demo\\nBook\\nBook a demo\\nBook\\nJoin Our Community\\nDiscord\\nJoin Our Community\\nDiscord\\nJoin Our Community\\nDiscord\\nor\\nName\\nEmail\\nEmail\\nSubmit\\nSubmit\\nSubmit\\n### Build faster using Julep API\\n### Deploy multi-step workflows easily with\\n### built-in tools and\\n### State management that is\\n### production ready from day one Keep me informed\\n### Build faster using Julep API\\n### Deploy multi-step workflows easily with built-in tools and State management that is production ready from day one Keep me informed\\nKeep me informed\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\"\n",
- " ],\n",
- " \"[\\n](./)\\n[\\nDocs\\n](https://docs.julep.ai/)\\n[\\nGithub\\n](https://github.com/julep-ai/julep)\\n[\\nDashboard\\n](https://dashboard.julep.ai/agents/)\\nExamples\\n[\\nDiscord\\n](https://discord.gg/2EUJzJU2Yt)\\n[\\nBook demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nContact Us\\n](./contact)\\n[\\n](./)\\n[\\n](./)\\n## How can we help you today We\\u2019re here to help Reach out to learn more about Synth Assistant or start your AI journey today\\nDev Support\\nhey@julep.ai\\nDev Support\\nhey@julep.ai\\nDev Support\\nhey@julep.ai\\nBook a demo\\nBook\\nBook a demo\\nBook\\nBook a demo\\nBook\\nJoin Our Community\\nDiscord\\nJoin Our Community\\nDiscord\\nJoin Our Community\\nDiscord\\nor\\nName\\nEmail\\nEmail\\nSubmit\\nSubmit\\nSubmit\\n### Build faster using Julep API\\n### Deploy multi-step workflows easily with\\n### built-in tools and\\n### State management that is\\n### production ready from day one Keep me informed\\n### Build faster using Julep API\\n### Deploy multi-step workflows easily with built-in tools and State management that is production ready from day one Keep me informed\\nKeep me informed\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\"\n",
- "]\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 51 Type: finish_branch\n",
- "output: \"The document provides comprehensive information about Julep AI, including resources for developers, use cases, and community engagement options. It offers links to documentation, API keys, SDKs, integration lists, and showcases various application use cases such as user profiling, email assistance, trip planning, document management, and more. The document also features company background, contact information, and social media links, emphasizing their support for engineers and developers.\"\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 52 Type: step\n",
- "output: [\n",
- " \"The document provides comprehensive information about Julep AI, including resources for developers, use cases, and community engagement options. It offers links to documentation, API keys, SDKs, integration lists, and showcases various application use cases such as user profiling, email assistance, trip planning, document management, and more. The document also features company background, contact information, and social media links, emphasizing their support for engineers and developers.\"\n",
- "]\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 53 Type: step\n",
- "output: {\n",
- " \"final_chunks\": [\n",
- " \"[\\n](./)\\n[\\nDocs\\n](https://docs.julep.ai/)\\n[\\nGithub\\n](https://github.com/julep-ai/julep)\\n[\\nDashboard\\n](https://dashboard.julep.ai/agents/)\\nExamples\\n[\\nDiscord\\n](https://discord.gg/2EUJzJU2Yt)\\n[\\nBook demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nContact Us\\n](./contact)\\n[\\n](./)\\n[\\n](./)\\n## How can we help you today We\\u2019re here to help Reach out to learn more about Synth Assistant or start your AI journey today\\nDev Support\\nhey@julep.ai\\nDev Support\\nhey@julep.ai\\nDev Support\\nhey@julep.ai\\nBook a demo\\nBook\\nBook a demo\\nBook\\nBook a demo\\nBook\\nJoin Our Community\\nDiscord\\nJoin Our Community\\nDiscord\\nJoin Our Community\\nDiscord\\nor\\nName\\nEmail\\nEmail\\nSubmit\\nSubmit\\nSubmit\\n### Build faster using Julep API\\n### Deploy multi-step workflows easily with\\n### built-in tools and\\n### State management that is\\n### production ready from day one Keep me informed\\n### Build faster using Julep API\\n### Deploy multi-step workflows easily with built-in tools and State management that is production ready from day one Keep me informed\\nKeep me informed\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nThe document provides comprehensive information about Julep AI, including resources for developers, use cases, and community engagement options. It offers links to documentation, API keys, SDKs, integration lists, and showcases various application use cases such as user profiling, email assistance, trip planning, document management, and more. The document also features company background, contact information, and social media links, emphasizing their support for engineers and developers.\"\n",
- " ]\n",
- "}\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 54 Type: init_branch\n",
- "output: \"[\\n](./)\\n[\\nDocs\\n](https://docs.julep.ai/)\\n[\\nGithub\\n](https://github.com/julep-ai/julep)\\n[\\nDashboard\\n](https://dashboard.julep.ai/agents/)\\nExamples\\n[\\nDiscord\\n](https://discord.gg/2EUJzJU2Yt)\\n[\\nBook demo\\n](< https://calendly.com/ishita-julep>)\\n[\\nContact Us\\n](./contact)\\n[\\n](./)\\n[\\n](./)\\n## How can we help you today We\\u2019re here to help Reach out to learn more about Synth Assistant or start your AI journey today\\nDev Support\\nhey@julep.ai\\nDev Support\\nhey@julep.ai\\nDev Support\\nhey@julep.ai\\nBook a demo\\nBook\\nBook a demo\\nBook\\nBook a demo\\nBook\\nJoin Our Community\\nDiscord\\nJoin Our Community\\nDiscord\\nJoin Our Community\\nDiscord\\nor\\nName\\nEmail\\nEmail\\nSubmit\\nSubmit\\nSubmit\\n### Build faster using Julep API\\n### Deploy multi-step workflows easily with\\n### built-in tools and\\n### State management that is\\n### production ready from day one Keep me informed\\n### Build faster using Julep API\\n### Deploy multi-step workflows easily with built-in tools and State management that is production ready from day one Keep me informed\\nKeep me informed\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nDev Resources\\n[Docs](https://docs.julep.ai/)\\n[Get API Key](https://dashboard-dev.julep.ai/)\\n[API Playground](https://dev.julep.ai/api/docs)\\n[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\\n[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\\n[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\\nUsecases\\n[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\\n[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\\n[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\\n[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\\n[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\\n[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\\n[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\\nCompany\\n[About](./about)\\n[Contact Us](./contact)\\n[Book Demo](https://calendly.com/ishita-julep)\\nSocials\\n[Github](https://github.com/julep-ai/julep)\\n[LinkedIn](https://www.linkedin.com/company/julep-ai)\\n[Twitter](https://x.com/julep_ai)\\n[Dev.to](https://dev.to/julep)\\n[Hugging Face](https://huggingface.co/julep-ai)\\n[Youtube](https://www.youtube.com/@julep_ai)\\nBuilt by Engineers, for Engineers\\n\\u00a9Julep AI Inc 2024\\nThe document provides comprehensive information about Julep AI, including resources for developers, use cases, and community engagement options. It offers links to documentation, API keys, SDKs, integration lists, and showcases various application use cases such as user profiling, email assistance, trip planning, document management, and more. The document also features company background, contact information, and social media links, emphasizing their support for engineers and developers.\"\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 55 Type: finish_branch\n",
- "output: {\n",
- " \"id\": \"0678f7c4-8748-7ce2-8000-97f8453d52da\",\n",
- " \"jobs\": [],\n",
- " \"created_at\": \"2025-01-21T10:51:52.513411Z\"\n",
- "}\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 56 Type: finish_branch\n",
- "output: [\n",
- " {\n",
- " \"id\": \"0678f7c4-8748-7ce2-8000-97f8453d52da\",\n",
- " \"jobs\": [],\n",
- " \"created_at\": \"2025-01-21T10:51:52.513411Z\"\n",
- " }\n",
- "]\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 57 Type: finish_branch\n",
- "output: [\n",
- " {\n",
- " \"id\": \"0678f7c4-8748-7ce2-8000-97f8453d52da\",\n",
- " \"jobs\": [],\n",
- " \"created_at\": \"2025-01-21T10:51:52.513411Z\"\n",
- " }\n",
- "]\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Index: 58 Type: finish\n",
- "output: [\n",
- " [\n",
- " {\n",
- " \"id\": \"0678f7c3-dfc5-76b4-8000-b8c198ba7995\",\n",
- " \"jobs\": [],\n",
- " \"created_at\": \"2025-01-21T10:51:42.035897Z\"\n",
- " },\n",
- " {\n",
- " \"id\": \"0678f7c3-e081-7ab4-8000-ff2c32bcfec3\",\n",
- " \"jobs\": [],\n",
- " \"created_at\": \"2025-01-21T10:51:42.081588Z\"\n",
- " },\n",
- " {\n",
- " \"id\": \"0678f7c3-dfbd-767b-8000-3e938c8bd27f\",\n",
- " \"jobs\": [],\n",
- " \"created_at\": \"2025-01-21T10:51:42.035552Z\"\n",
- " },\n",
- " {\n",
- " \"id\": \"0678f7c3-e945-70b6-8000-a1c494662a11\",\n",
- " \"jobs\": [],\n",
- " \"created_at\": \"2025-01-21T10:51:42.630639Z\"\n",
- " },\n",
- " {\n",
- " \"id\": \"0678f7c3-e981-7952-8000-3593fbc19d2a\",\n",
- " \"jobs\": [],\n",
- " \"created_at\": \"2025-01-21T10:51:42.630494Z\"\n",
- " },\n",
- " {\n",
- " \"id\": \"0678f7c3-e8db-784d-8000-f45ae9b85623\",\n",
- " \"jobs\": [],\n",
- " \"created_at\": \"2025-01-21T10:51:42.590278Z\"\n",
- " }\n",
- " ],\n",
- " [\n",
- " {\n",
- " \"id\": \"0678f7c4-33d5-731a-8000-7472c8f36677\",\n",
- " \"jobs\": [],\n",
- " \"created_at\": \"2025-01-21T10:51:47.277809Z\"\n",
- " }\n",
- " ],\n",
- " [\n",
- " {\n",
- " \"id\": \"0678f7c4-8748-7ce2-8000-97f8453d52da\",\n",
- " \"jobs\": [],\n",
- " \"created_at\": \"2025-01-21T10:51:52.513411Z\"\n",
- " }\n",
- " ]\n",
- "]\n",
- "----------------------------------------------------------------------------------------------------\n"
- ]
- }
- ],
- "source": [
- "import json\n",
- "execution_transitions = client.executions.transitions.list(\n",
- " execution_id=execution.id, limit=100).items\n",
- "\n",
- "for index, transition in enumerate(reversed(execution_transitions)):\n",
- " print(\"Index: \", index, \"Type: \", transition.type)\n",
- " print(\"output: \", json.dumps(transition.output, indent=2))\n",
- " print(\"-\" * 100)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 14,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Crawled pages: \n"
- ]
- },
- {
- "data": {
- "text/plain": [
- "['https://julep.ai/', 'https://julep.ai/about', 'https://julep.ai/contact']"
- ]
- },
- "execution_count": 14,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "crawled_pages = [r['url'] for r in execution_transitions[-2].output['result']]\n",
- "\n",
- "print(\"Crawled pages: \")\n",
- "crawled_pages"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Lisitng the Document Store for the Agent\n",
- "\n",
- "The document store is where the agent stores the documents it has created. Each document has a `title` , `content`, `id`, `metadata`, `created_at` and the `vector embedding` associated with it. This will be used for the retrieval of the documents when the agent is queried."
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 15,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Number of documents in the document store: 27\n"
- ]
- }
- ],
- "source": [
- "docs = client.agents.docs.list(agent_id=agent.id, limit=100).items\n",
- "num_docs = len(docs)\n",
- "print(\"Number of documents in the document store: \", num_docs)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 72,
- "metadata": {},
- "outputs": [],
- "source": [
- "# # # UNCOMMENT THIS TO DELETE ALL THE AGENT'S DOCUMENTS\n",
- "\n",
- "# for doc in client.agents.docs.list(agent_id=agent.id, limit=1000):\n",
- "# client.agents.docs.delete(agent_id=agent.id, doc_id=doc.id)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Creating a Session\n",
- "\n",
- "A session is used to interact with the agent. It is used to send messages to the agent and receive responses.\n",
- "Situation is the initial message that is sent to the agent to set the context for the conversation. Out here you can add more information about the agent and the task it is performing to help the agent answer better. Additionally, you can also define the `search_threshold` and `search_query_chars` which are used to control the retrieval of the documents from the document store which will be used for the retrieval of the documents when the agent is queried.\n",
- "More information about the session can be found [here](https://github.com/julep-ai/julep/blob/dev/docs/julep-concepts.md#session)."
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 19,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Agent created with ID: 0678f7b6-0865-7f65-8000-e64ed0ca4d19\n",
- "Session created with ID: 0678f7ce-79fc-7a37-8000-e72d0406c225\n"
- ]
- }
- ],
- "source": [
- "# Custom system template for this particular session to help the agent answer better\n",
- "system_template = \"\"\"\n",
- "You are an AI agent designed to assist users with their queries about a certain website.\n",
- "Your goal is to provide clear and detailed responses.\n",
- "\n",
- "**Guidelines**:\n",
- "1. Assume the user is unfamiliar with the company and products.\n",
- "2. Thoroughly read and comprehend the user's question.\n",
- "3. Use the provided context documents to find relevant information.\n",
- "4. Craft a detailed response based on the context and your understanding of the company and products.\n",
- "5. Include links to specific website pages for further information when applicable.\n",
- "\n",
- "**Response format**:\n",
- "- Use simple, clear language.\n",
- "- Include relevant website links.\n",
- "\n",
- "**Important**:\n",
- "- For questions related to the business, only use the information that are explicitly given in the documents above.\n",
- "- If the user asks about the business, and it's not given in the documents above, respond with an answer that states that you don't know.\n",
- "- Use the most recent and relevant data from context documents.\n",
- "- Be proactive in helping users find solutions.\n",
- "- Ask for clarification if the query is unclear.\n",
- "- Inform users if their query is unrelated to the given website.\n",
- "- Avoid using the following in your response: Based on the provided documents, based on the provided information, based on the documentation... etc.\n",
- "\n",
- "{%- if docs -%}\n",
- "**Relevant documents**:{{NEWLINE}}\n",
- " {%- for doc in docs -%}\n",
- " {{doc.title}}{{NEWLINE}}\n",
- " {%- if doc.content is string -%}\n",
- " {{doc.content}}{{NEWLINE}}\n",
- " {%- else -%}\n",
- " {%- for snippet in doc.content -%}\n",
- " {{snippet}}{{NEWLINE}}\n",
- " {%- endfor -%}\n",
- " {%- endif -%}\n",
- " {{\"---\"}}\n",
- " {%- endfor -%}\n",
- "\n",
- "{%- else -%}\n",
- "There are no documents available for this query.\n",
- "{%- endif -%}\n",
- "\n",
- "\"\"\"\n",
- "\n",
- "print(f\"Agent created with ID: {agent.id}\")\n",
- "\n",
- "# Create a session for interaction\n",
- "session = client.sessions.create(\n",
- " system_template=system_template,\n",
- " agent=agent.id,\n",
- " recall_options={\n",
- " \"mode\": \"hybrid\",\n",
- " \"num_search_messages\": 1,\n",
- " \"max_query_length\": 800,\n",
- " \"confidence\": -0.9,\n",
- " \"alpha\": 0.5,\n",
- " \"limit\": 10,\n",
- " \"mmr_strength\": 0.5,\n",
- " },\n",
- ")\n",
- "\n",
- "print(f\"Session created with ID: {session.id}\")"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## Chatting with the Agent\n",
- "\n",
- "The chat method is used to send messages to the agent and receive responses. The messages are sent as a list of dictionaries with the `role` and `content` keys."
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 20,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Julep is a comprehensive platform designed for creating AI agents that possess the ability to remember past interactions and execute complex tasks. It acts as the infrastructure between large language models (LLMs) and your software, providing support for long-term memory and multi-step process management.\n",
- "\n",
- "Key features of Julep include:\n",
- "\n",
- "1. **8-Factor Agent Methodology**: This approach incorporates software engineering principles into AI development. It includes managing prompts as code, ensuring model independence, structured reasoning, workflow-based models, and full observability for effective debugging and improvement.\n",
- "\n",
- "2. **Built-In Reliability**: Julep is equipped with self-healing capabilities such as automatic retries for failed steps, message resending, task recovery, error handling, and real-time monitoring to enhance reliability and manage errors efficiently.\n",
- "\n",
- "3. **Modular and Flexible Design**: By defining explicit interfaces for tool interactions, Julep ensures that capabilities are modular and maintainable. Additionally, it treats model providers as replaceable resources, allowing for flexibility and avoiding vendor lock-in.\n",
- "\n",
- "4. **Complex Workflow Management**: The platform allows users to define multi-step tasks in YAML, incorporate decision trees, loops, and execute tasks in parallel, which is particularly beneficial for sophisticated AI systems.\n",
- "\n",
- "5. **Rapid Prototyping and Scalability**: With features designed for rapid prototyping, Julep lets users go from idea to demo quickly while its infrastructure supports scalability to handle millions of concurrent users.\n",
- "\n",
- "6. **Ease of Use**: Development times can be significantly reduced as Julep handles much of the infrastructure orchestration, allowing developers to focus on refining prompts and core functionalities.\n",
- "\n",
- "Julep also offers numerous resources for developers including documentation, SDKs for Python and JavaScript, and integrations with various APIs. For further exploration and integration instructions, you can visit their [documentation page](https://docs.julep.ai/) or explore their [API Playground](https://dev.julep.ai/api/docs). If you're interested in a demonstration, you can [book a demo](https://calendly.com/ishita-julep) with their team.\n",
- "\n",
- "For those in education and NGOs, Julep offers a program with unlimited free credits. You can apply for this program [here](https://forms.gle/CCP6sDYeUfAXdUoi7).\n",
- "\n",
- "Feel free to check out their [GitHub repository](https://github.com/julep-ai/julep) to see more about their open-source initiatives.\n"
- ]
- }
- ],
- "source": [
- "user_question = \"Tell me about Julep\"\n",
- "\n",
- "response = client.sessions.chat(\n",
- " session_id=session.id,\n",
- " messages=[\n",
- " {\n",
- " \"role\": \"user\",\n",
- " \"content\": user_question,\n",
- " }\n",
- " ],\n",
- " recall=True,\n",
- ")\n",
- "\n",
- "print(response.choices[0].message.content)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### Check the matched documents"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 21,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Matched docs:\n",
- "\n",
- "\n",
- "Doc 1:\n",
- "Title: Website Document\n",
- "Snippet content:\n",
- "It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\n",
- "- Automatic retries for failed steps\n",
- "- Message resending\n",
- "- Task recovery\n",
- "- Error handling\n",
- "- Real-time monitoring How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\n",
- "- Automatic retries for failed steps\n",
- "- Message resending\n",
- "- Task recovery\n",
- "- Error handling\n",
- "- Real-time monitoring How does Julep handle errors and reliability Julep includes built-in self-healing capabilities:\n",
- "- Automatic retries for failed steps\n",
- "- Message resending\n",
- "- Task recovery\n",
- "- Error handling\n",
- "- Real-time monitoring How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\n",
- "- Prompts as Code:\n",
- "Track prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\n",
- "Define explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\n",
- "Treat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching\n",
- "This chunk is part of a detailed description of the features and advantages of Julep, a platform for creating AI agents. It emphasizes Julep's capabilities in process management and error handling, and contrasts its disciplined approach to AI development with typical practices.\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Doc 2:\n",
- "Title: Website Document\n",
- "Snippet content:\n",
- "How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\n",
- "- Prompts as Code:\n",
- "Track prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\n",
- "Define explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\n",
- "Treat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching -Context Management:\n",
- "Explicitly define how application and user state is managed and reduced -Ground Truth Examples:\n",
- "Maintain clear examples of expected prompt results for validation and testing.-Structured Reasoning:\n",
- "Separate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\n",
- "complex processes as clear workflows rather than chains of prompts -Full Observability:\n",
- "Save execution traces for debugging, monitoring, and continuous improvement How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks\n",
- "The chunk describes Julep's unique approach to AI development, highlighting its 8-Factor Agent methodology that emphasizes software engineering principles, modular capabilities, model independence, context management, and full observability. It contrasts Julep with other platforms like LangChain, positioning Julep as a comprehensive platform for building robust, production-ready AI systems with persistent agents and complex workflows.\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Doc 3:\n",
- "Title: Website Document\n",
- "Snippet content:\n",
- "Vedant Maheshwari\n",
- "CEO, Vidyo.ai\n",
- "* We tried building our ai stack where we needed simple automated computer use we spent months trying to get it right, but our development time got cut to a couple weeks because most of the infra orchestration was handled by julep all that we had to do was refine our prompts\n",
- "Madhavan\n",
- "CEO, Reclaim Protocol\n",
- "* \"Same experience as reviewing designs on Figma with my designer Sat with my developer once, and we kept brainstorming, testing, prototyping and shipping at once I got control back in my hands as a non-developer.\"\n",
- "Akshay Pruthi\n",
- "CEO, Calm Sleep\n",
- "* Working with Julep accelerated Ukumi, by enabling us to focus on our core strengths and letting Julep navigate the complex web of calls to ai models we could do more with less Sachin Gaur\n",
- "Cofounder, Ukumi AI\n",
- "### Build with Julep\n",
- "Create an agent\n",
- "Define agents that can talk to users inside of a session\n",
- "Add tools\n",
- "Equip agents with tools - web search, API calls, or custom integrations\n",
- "Define your tasks\n",
- "Define multi-step processes in YAML with decision trees, loops, and parallel execution\n",
- "Deploy\n",
- "Execute production-grade workflows with one command\n",
- "agent = julep.agents.create(\n",
- "name=\"Spiderman\",\n",
- "about=\"AI that can crawl the web and extract data\",\n",
- "model=\"gpt-4o-mini\",\n",
- "default\\_settings={\n",
- "\"temperature\":0.75,\n",
- "\"max\\_tokens\":10000,\n",
- "\"top\\_p\":1.0,\n",
- "}\n",
- ")\n",
- "Create an agent\n",
- "Define agents that can talk to users inside of a session\n",
- "Add tools\n",
- "Equip agents with tools - web search, API calls, or custom integrations\n",
- "julep.agents.tools.create(\n",
- "agent\\_id=agent.id,\n",
- "name=\"my\\_weather\\_tool\",\n",
- "integration={\n",
- "\"provider\":\"weather\",\n",
- "\"setup\": {\n",
- "\"openweathermap\\_api\\_key\":\"OPENWEATHERMAP\\_API\\_KEY\"\n",
- "}\n",
- "}\n",
- ")\n",
- "Define your tasks\n",
- "Define multi-step processes in YAML with decision trees, loops, and parallel execution\n",
- "iimportyaml\n",
- "task =julep.task.create(\"\"\"\n",
- "name: Weather Reporting Task\n",
- "main:\n",
- "- tool: spider\\_crawler\n",
- "arguments:\n",
- "url: \\_.url\n",
- "- prompt: |\n",
- "Here’s a crawl of {{inputs[0].url}}:\n",
- "{{\\_.documents}}\n",
- "Create a short summary (\\~100 words) of the website \"\"\")- city\n",
- "Deploy\n",
- "Execute production-grade workflows with one command\n",
- "execution = julep.executions.create(\n",
- "task\\_id=task.id,\n",
- "input={\n",
- "\"url\": \"https://spider.cloud\"\n",
- "}\n",
- ")\n",
- "agent = julep.agents.create(\n",
- "name=\"Cristopher\",\n",
- "about=\"An agent specialized in weather reporting\",\n",
- "model=\"gpt-4o-mini\",\n",
- ")\n",
- "Create an agent\n",
- "Define agents that can talk to users inside of a session\n",
- "Add tools\n",
- "Equip agents with tools - web search, API calls, or custom integrations\n",
- "Define your tasks\n",
- "Define multi-step processes in YAML with decision trees, loops, and parallel execution\n",
- "Deploy\n",
- "Execute production-grade workflows with one command\n",
- "agent = julep.agents.create(\n",
- "name=\"Spiderman\",\n",
- "about=\"AI that can crawl the web and extract data\",\n",
- "model=\"gpt-4o-mini\",\n",
- "default\\_settings={\n",
- "\"temperature\":0.75,\n",
- "\"max\\_tokens\":10000,\n",
- "\"top\\_p\":1.0,\n",
- "}\n",
- ")\n",
- "## Build AI pipelines\n",
- "in minutes Scale to millions Rapid Prototyping\n",
- "\"From idea to demo in minutes\" using built-in RAG and state management\n",
- "Production Ready\n",
- "\"Go live instantly with managed infrastructure\" and features such as long-running tasks, automatic retries and error handling\n",
- "Modular Design\n",
- "\"Build features like Lego blocks\" by connecting to any external API, switch between LLMs and add custom tools\n",
- "Infinite Scale\n",
- "Handle millions of concurrent users with automatic scaling and load balancing\n",
- "Future Proof\n",
- "\"Add new AI models anytime\" \"Integrate with any new tool or API\"\n",
- "Complete Control\n",
- "\"Full visibility into AI operations\" \"Manage costs and performance easily\"\n",
- "## Questions Answers What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks It provides the complete infrastructure layer between LLMs and your software, with built-in support for long-term memory and multi-step process management What is Julep Julep is a platform for creating AI agents that remember past interactions and can perform complex tasks\n",
- "This chunk focuses on testimonials from CEOs and co-founders about their experiences using Julep AI, highlighting its benefits in reducing development time, enhancing collaboration, and leveraging AI for streamlined operations. It also outlines the process of building AI agents with Julep, including creating agents, equipping them with tools, defining tasks, and deploying workflows. The section emphasizes Julep's capabilities in rapid prototyping, modular design, infinite scalability, and comprehensive AI management.\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Doc 4:\n",
- "Title: Website Document\n",
- "Snippet content:\n",
- "How is Julep different from agent frameworks While LangChain is great for creating sequences of prompts and managing model interactions, Julep is built for creating persistent AI agents with advanced task capabilities Think of LangChain as a tool for prompt chains, while Julep is a complete platform for building production-ready AI systems with complex workflows, state management, and long-running tasks ### Build faster using Julep API\n",
- "### Deploy multi-step workflows easily with\n",
- "### built-in tools and\n",
- "### state management that is\n",
- "### production ready from day one Keep me informed\n",
- "### Build faster using Julep API\n",
- "### Deploy multi-step workflows easily with built-in tools and State management that is production ready from day one Keep me informed\n",
- "Keep me informed\n",
- "Keep me informed\n",
- "Dev Resources\n",
- "[Docs](https://docs.julep.ai/)\n",
- "[Get API Key](https://dashboard-dev.julep.ai/)\n",
- "[API Playground](https://dev.julep.ai/api/docs)\n",
- "[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\n",
- "[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\n",
- "[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\n",
- "Usecases\n",
- "[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\n",
- "[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\n",
- "[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\n",
- "[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\n",
- "[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\n",
- "[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\n",
- "[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\n",
- "Company\n",
- "[About](./about)\n",
- "[Contact Us](./contact)\n",
- "[Book Demo](https://calendly.com/ishita-julep)\n",
- "Socials\n",
- "[Github](https://github.com/julep-ai/julep)\n",
- "[LinkedIn](https://www.linkedin.com/company/julep-ai)\n",
- "[Twitter](https://x.com/julep_ai)\n",
- "[Dev.to](https://dev.to/julep)\n",
- "[Hugging Face](https://huggingface.co/julep-ai)\n",
- "[Youtube](https://www.youtube.com/@julep_ai)\n",
- "Built by Engineers, for Engineers\n",
- "©Julep AI Inc 2024\n",
- "Dev Resources\n",
- "[Docs](https://docs.julep.ai/)\n",
- "[Get API Key](https://dashboard-dev.julep.ai/)\n",
- "[API Playground](https://dev.julep.ai/api/docs)\n",
- "[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\n",
- "[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\n",
- "[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\n",
- "Usecases\n",
- "[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\n",
- "[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\n",
- "[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\n",
- "[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\n",
- "[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\n",
- "[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\n",
- "[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\n",
- "Company\n",
- "[About](./about)\n",
- "[Contact Us](./contact)\n",
- "[Book Demo](https://calendly.com/ishita-julep)\n",
- "Socials\n",
- "[Github](https://github.com/julep-ai/julep)\n",
- "[LinkedIn](https://www.linkedin.com/company/julep-ai)\n",
- "[Twitter](https://x.com/julep_ai)\n",
- "[Dev.to](https://dev.to/julep)\n",
- "[Hugging Face](https://huggingface.co/julep-ai)\n",
- "[Youtube](https://www.youtube.com/@julep_ai)\n",
- "Built by Engineers, for Engineers\n",
- "©Julep AI Inc 2024\n",
- "Dev Resources\n",
- "[Docs](https://docs.julep.ai/)\n",
- "[Get API Key](https://dashboard-dev.julep.ai/)\n",
- "[API Playground](https://dev.julep.ai/api/docs)\n",
- "[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\n",
- "[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\n",
- "[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\n",
- "Usecases\n",
- "[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\n",
- "[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\n",
- "[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\n",
- "[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\n",
- "[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\n",
- "[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\n",
- "[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\n",
- "Company\n",
- "[About](./about)\n",
- "[Contact Us](./contact)\n",
- "[Book Demo](https://calendly.com/ishita-julep)\n",
- "Socials\n",
- "[Github](https://github.com/julep-ai/julep)\n",
- "[LinkedIn](https://www.linkedin.com/company/julep-ai)\n",
- "[Twitter](https://x.com/julep_ai)\n",
- "[Dev.to](https://dev.to/julep)\n",
- "[Hugging Face](https://huggingface.co/julep-ai)\n",
- "[Youtube](https://www.youtube.com/@julep_ai)\n",
- "Built by Engineers, for Engineers\n",
- "©Julep AI Inc 2024\n",
- "This chunk provides information about Julep's differences from other agent frameworks such as LangChain, highlighting its capabilities for creating persistent AI agents with complex workflows, state management, and production-ready features. It also mentions various developer resources and use cases available within the Julep platform.\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Doc 5:\n",
- "Title: Website Document\n",
- "Snippet content:\n",
- "[\n",
- "](./)\n",
- "[\n",
- "Docs\n",
- "](https://docs.julep.ai/)\n",
- "[\n",
- "Github\n",
- "](https://github.com/julep-ai/julep)\n",
- "[\n",
- "Dashboard\n",
- "](https://dashboard.julep.ai/agents/)\n",
- "Examples\n",
- "[\n",
- "Discord\n",
- "](https://discord.gg/2EUJzJU2Yt)\n",
- "[\n",
- "Book demo\n",
- "](< https://calendly.com/ishita-julep>)\n",
- "[\n",
- "Contact Us\n",
- "](./contact)\n",
- "[\n",
- "](./)\n",
- "[\n",
- "](./)\n",
- "# MakingAIDevelopment\n",
- "WhatItShouldBe\n",
- "Two years ago, we started Julep with a simple belief: making intelligence more human shouldn't mean making engineering less rigorous While the world rushed to stack prompts and call it engineering, we chose to build something foundational We created the 8-Factor Agent methodology not because it was easy, but because AI development deserves real tools, real engineering, and real infrastructure We're engineers who believe the future of software will be built on AI - not as a collection of clever hacks, but as properly engineered systems with clear interfaces, predictable behavior, and production-grade reliability Julep isn't another abstraction layer or prompt management tool It's a complete rethinking of how AI applications should be built, tested, and scaled Our task language isn't another abstraction layer; it's a new way to think about AI workflows Our infrastructure isn't just about scaling; it's about bringing reliability and rigor to a field that sorely needs it Because taking the hard path to simple AI development isn't just our approach - it's our conviction that this is how it should be done We're building the foundation for AI's future, not chasing its hype * * * Dev Resources\n",
- "[Docs](https://docs.julep.ai/)\n",
- "[Get API Key](https://dashboard-dev.julep.ai/)\n",
- "[API Playground](https://dev.julep.ai/api/docs)\n",
- "[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\n",
- "[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\n",
- "[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\n",
- "Usecases\n",
- "[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\n",
- "[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\n",
- "[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\n",
- "[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\n",
- "[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\n",
- "[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\n",
- "[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\n",
- "Company\n",
- "[About](./about)\n",
- "[Contact Us](./contact)\n",
- "[Book Demo](https://calendly.com/ishita-julep)\n",
- "Socials\n",
- "[Github](https://github.com/julep-ai/julep)\n",
- "[LinkedIn](https://www.linkedin.com/company/julep-ai)\n",
- "[Twitter](https://x.com/julep_ai)\n",
- "[Dev.to](https://dev.to/julep)\n",
- "[Hugging Face](https://huggingface.co/julep-ai)\n",
- "[Youtube](https://www.youtube.com/@julep_ai)\n",
- "Built by Engineers, for Engineers\n",
- "©Julep AI Inc 2024\n",
- "Dev Resources\n",
- "[Docs](https://docs.julep.ai/)\n",
- "[Get API Key](https://dashboard-dev.julep.ai/)\n",
- "[API Playground](https://dev.julep.ai/api/docs)\n",
- "[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\n",
- "[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\n",
- "[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\n",
- "Usecases\n",
- "[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\n",
- "[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\n",
- "[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\n",
- "[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\n",
- "[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\n",
- "[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\n",
- "[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\n",
- "Company\n",
- "[About](./about)\n",
- "[Contact Us](./contact)\n",
- "[Book Demo](https://calendly.com/ishita-julep)\n",
- "Socials\n",
- "[Github](https://github.com/julep-ai/julep)\n",
- "[LinkedIn](https://www.linkedin.com/company/julep-ai)\n",
- "[Twitter](https://x.com/julep_ai)\n",
- "[Dev.to](https://dev.to/julep)\n",
- "[Hugging Face](https://huggingface.co/julep-ai)\n",
- "[Youtube](https://www.youtube.com/@julep_ai)\n",
- "Built by Engineers, for Engineers\n",
- "©Julep AI Inc 2024\n",
- "Dev Resources\n",
- "[Docs](https://docs.julep.ai/)\n",
- "[Get API Key](https://dashboard-dev.julep.ai/)\n",
- "[API Playground](https://dev.julep.ai/api/docs)\n",
- "[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\n",
- "[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\n",
- "[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\n",
- "Usecases\n",
- "[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\n",
- "[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\n",
- "[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\n",
- "[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\n",
- "[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\n",
- "[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\n",
- "[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\n",
- "Company\n",
- "[About](./about)\n",
- "[Contact Us](./contact)\n",
- "[Book Demo](https://calendly.com/ishita-julep)\n",
- "Socials\n",
- "[Github](https://github.com/julep-ai/julep)\n",
- "[LinkedIn](https://www.linkedin.com/company/julep-ai)\n",
- "[Twitter](https://x.com/julep_ai)\n",
- "[Dev.to](https://dev.to/julep)\n",
- "[Hugging Face](https://huggingface.co/julep-ai)\n",
- "[Youtube](https://www.youtube.com/@julep_ai)\n",
- "Built by Engineers, for Engineers\n",
- "©Julep AI Inc 2024\n",
- "The chunk is an introduction and overview of Julep's mission, philosophy, and resources focused on AI development. It highlights Julep's unique methodology for building AI applications with rigor and infrastructure and provides links to developer resources, use cases, company information, and social media.\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Doc 6:\n",
- "Title: Website Document\n",
- "Snippet content:\n",
- "[\n",
- "](./)\n",
- "[\n",
- "Docs\n",
- "](https://docs.julep.ai/)\n",
- "[\n",
- "Github\n",
- "](https://github.com/julep-ai/julep)\n",
- "[\n",
- "Dashboard\n",
- "](https://dashboard.julep.ai/agents/)\n",
- "Examples\n",
- "[\n",
- "Discord\n",
- "](https://discord.gg/2EUJzJU2Yt)\n",
- "[\n",
- "Book demo\n",
- "](< https://calendly.com/ishita-julep>)\n",
- "[\n",
- "Contact Us\n",
- "](./contact)\n",
- "[\n",
- "](./)\n",
- "[\n",
- "](./)\n",
- "## How can we help you today We’re here to help Reach out to learn more about Synth Assistant or start your AI journey today\n",
- "Dev Support\n",
- "hey@julep.ai\n",
- "Dev Support\n",
- "hey@julep.ai\n",
- "Dev Support\n",
- "hey@julep.ai\n",
- "Book a demo\n",
- "Book\n",
- "Book a demo\n",
- "Book\n",
- "Book a demo\n",
- "Book\n",
- "Join Our Community\n",
- "Discord\n",
- "Join Our Community\n",
- "Discord\n",
- "Join Our Community\n",
- "Discord\n",
- "or\n",
- "Name\n",
- "Email\n",
- "Email\n",
- "Submit\n",
- "Submit\n",
- "Submit\n",
- "### Build faster using Julep API\n",
- "### Deploy multi-step workflows easily with\n",
- "### built-in tools and\n",
- "### State management that is\n",
- "### production ready from day one Keep me informed\n",
- "### Build faster using Julep API\n",
- "### Deploy multi-step workflows easily with built-in tools and State management that is production ready from day one Keep me informed\n",
- "Keep me informed\n",
- "Dev Resources\n",
- "[Docs](https://docs.julep.ai/)\n",
- "[Get API Key](https://dashboard-dev.julep.ai/)\n",
- "[API Playground](https://dev.julep.ai/api/docs)\n",
- "[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\n",
- "[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\n",
- "[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\n",
- "Usecases\n",
- "[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\n",
- "[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\n",
- "[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\n",
- "[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\n",
- "[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\n",
- "[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\n",
- "[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\n",
- "Company\n",
- "[About](./about)\n",
- "[Contact Us](./contact)\n",
- "[Book Demo](https://calendly.com/ishita-julep)\n",
- "Socials\n",
- "[Github](https://github.com/julep-ai/julep)\n",
- "[LinkedIn](https://www.linkedin.com/company/julep-ai)\n",
- "[Twitter](https://x.com/julep_ai)\n",
- "[Dev.to](https://dev.to/julep)\n",
- "[Hugging Face](https://huggingface.co/julep-ai)\n",
- "[Youtube](https://www.youtube.com/@julep_ai)\n",
- "Built by Engineers, for Engineers\n",
- "©Julep AI Inc 2024\n",
- "Dev Resources\n",
- "[Docs](https://docs.julep.ai/)\n",
- "[Get API Key](https://dashboard-dev.julep.ai/)\n",
- "[API Playground](https://dev.julep.ai/api/docs)\n",
- "[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\n",
- "[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\n",
- "[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\n",
- "Usecases\n",
- "[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\n",
- "[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\n",
- "[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\n",
- "[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\n",
- "[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\n",
- "[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\n",
- "[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\n",
- "Company\n",
- "[About](./about)\n",
- "[Contact Us](./contact)\n",
- "[Book Demo](https://calendly.com/ishita-julep)\n",
- "Socials\n",
- "[Github](https://github.com/julep-ai/julep)\n",
- "[LinkedIn](https://www.linkedin.com/company/julep-ai)\n",
- "[Twitter](https://x.com/julep_ai)\n",
- "[Dev.to](https://dev.to/julep)\n",
- "[Hugging Face](https://huggingface.co/julep-ai)\n",
- "[Youtube](https://www.youtube.com/@julep_ai)\n",
- "Built by Engineers, for Engineers\n",
- "©Julep AI Inc 2024\n",
- "Dev Resources\n",
- "[Docs](https://docs.julep.ai/)\n",
- "[Get API Key](https://dashboard-dev.julep.ai/)\n",
- "[API Playground](https://dev.julep.ai/api/docs)\n",
- "[Python SDK](https://github.com/julep-ai/python-sdk/blob/main/README.md)\n",
- "[Javascript SDK](https://github.com/julep-ai/node-sdk/blob/main/README.md)\n",
- "[Integration List](https://github.com/julep-ai/julep/tree/dev?tab=readme-ov-file#integrations)\n",
- "Usecases\n",
- "[User Profiling](https://github.com/julep-ai/julep/blob/dev/cookbooks/09-User_Management_and_Personalization.py)\n",
- "[Email Assistant (Mailgun)](https://github.com/julep-ai/julep/blob/dev/cookbooks/00-Devfest-Email-Assistant.ipynb)\n",
- "[Trip Planner (Weather + Wiki)](https://github.com/julep-ai/julep/blob/dev/cookbooks/04-TripPlanner_With_Weather_And_WikiInfo.ipynb)\n",
- "[Doc Management](https://github.com/julep-ai/julep/blob/dev/cookbooks/10-Document_Management_and_Search.py)\n",
- "[Website Crawler (Spider)](https://github.com/julep-ai/julep/blob/dev/cookbooks/01-Website_Crawler_using_Spider.ipynb)\n",
- "[Multi-step Tasks](https://github.com/julep-ai/julep/blob/dev/cookbooks/06-Designing_Multi-Step_Tasks.py)\n",
- "[Advanced Chat](https://github.com/julep-ai/julep/blob/dev/cookbooks/11-Advanced_Chat_Interactions.py)\n",
- "Company\n",
- "[About](./about)\n",
- "[Contact Us](./contact)\n",
- "[Book Demo](https://calendly.com/ishita-julep)\n",
- "Socials\n",
- "[Github](https://github.com/julep-ai/julep)\n",
- "[LinkedIn](https://www.linkedin.com/company/julep-ai)\n",
- "[Twitter](https://x.com/julep_ai)\n",
- "[Dev.to](https://dev.to/julep)\n",
- "[Hugging Face](https://huggingface.co/julep-ai)\n",
- "[Youtube](https://www.youtube.com/@julep_ai)\n",
- "Built by Engineers, for Engineers\n",
- "©Julep AI Inc 2024\n",
- "The document provides comprehensive information about Julep AI, including resources for developers, use cases, and community engagement options. It offers links to documentation, API keys, SDKs, integration lists, and showcases various application use cases such as user profiling, email assistance, trip planning, document management, and more. The document also features company background, contact information, and social media links, emphasizing their support for engineers and developers.\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Doc 7:\n",
- "Title: Website Document\n",
- "Snippet content:\n",
- "-Context Management:\n",
- "Explicitly define how application and user state is managed and reduced -Ground Truth Examples:\n",
- "Maintain clear examples of expected prompt results for validation and testing -Structured Reasoning:\n",
- "Separate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\n",
- "complex processes as clear workflows rather than chains of prompts -Full Observability:\n",
- "Save execution traces for debugging, monitoring, and continuous improvement How does Julep's approach differ from typical AI development While most platforms focus on prompt engineering and chaining LLM calls, Julep brings software engineering discipline to AI development Through our 8-Factor Agent methodology, we treat AI components as proper system elements:\n",
- "- Prompts as Code:\n",
- "Track prompts separately from application code, enabling systematic improvements and proper versioning - Clear Tool Interfaces:\n",
- "Define explicit interfaces for all tool interactions, making capabilities modular and maintainable -Model Independence:\n",
- "Treat model providers as external, replaceable resources to avoid vendor lock-in and enable easy switching -Context Management:\n",
- "Explicitly define how application and user state is managed and reduced -Ground Truth Examples:\n",
- "Maintain clear examples of expected prompt results for validation and testing -Structured Reasoning:\n",
- "Separate processes into deliberative (planned, multi-step) and impromptu (quick response) reasoning -Workflow-Based Model:\n",
- "complex processes as clear workflows rather than chains of prompts -Full Observability:\n",
- "Save execution traces for debugging, monitoring, and continuous improvement\n",
- "This chunk discusses Julep's unique approach to AI development using the 8-Factor Agent methodology, which emphasizes software engineering principles like context management, model independence, structured reasoning, and full observability to create robust, production-ready AI systems, differentiating it from typical AI development practices that focus primarily on prompt engineering.\n",
- "----------------------------------------------------------------------------------------------------\n",
- "Doc 8:\n",
- "Title: Website Document\n",
- "Snippet content:\n",
- "[\n",
- "](./)\n",
- "[\n",
- "Docs\n",
- "](https://docs.julep.ai/)\n",
- "[\n",
- "Github\n",
- "](https://github.com/julep-ai/julep)\n",
- "[\n",
- "Dashboard\n",
- "](https://dashboard.julep.ai/agents/)\n",
- "Examples\n",
- "[\n",
- "Discord\n",
- "](https://discord.gg/2EUJzJU2Yt)\n",
- "[\n",
- "Book demo\n",
- "](< https://calendly.com/ishita-julep>)\n",
- "[\n",
- "Contact Us\n",
- "](./contact)\n",
- "[\n",
- "](./)\n",
- "[\n",
- "](./)\n",
- "Announcing our Education+NGO program Eligible organizations get unlimited free credits Please apply[here](https://forms.gle/CCP6sDYeUfAXdUoi7) [](https://www.producthunt.com/posts/julep-ai)\n",
- "Open Source\n",
- "[\n",
- "Github\n",
- "★4.4K\n",
- "](https://github.com/julep-ai/julep)\n",
- "# Buildscalable\n",
- "AIworkflows\n",
- "inminutes\n",
- "API to build multi-step agent workflows\n",
- "[\n",
- "Deploy your first agent\n",
- "](https://dashboard-dev.julep.ai/)\n",
- "[\n",
- "Deploy your first agent\n",
- "](https://dashboard-dev.julep.ai/)\n",
- "[\n",
- "Get a demo\n",
- "](< https://calendly.com/ishita-julep>)\n",
- "[\n",
- "Get a demo\n",
- "](< https://calendly.com/ishita-julep>)\n",
- "CUSTOMER STORIES\n",
- "Vidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place CUSTOMER STORIES\n",
- "Vidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place CUSTOMER STORIES\n",
- "Vidyo built personalised marketing intelligence for thousands of users usingposting trendsandcurrent top trends Iterate and deploy AI features super fast by bringing data from different sources in one place ## Connect with any AI model,\n",
- "API or data source\n",
- "Seamlessly integrate with your existing stack and favorite AI models LLM Platforms\n",
- "Languages\n",
- "Integrations\n",
- "* * * * * * Any REST API\n",
- "## Real people, Real results\n",
- "* Julep to me sits in the intersection of what Zapier did for simplifying workflows, and what Vercel did for simplifying shipping The new possibilities are endless I am excited abut what all can be done with this tech at ES Suryansh Tibarewal\n",
- "CEO, EssentiallySports\n",
- "* For Vidyo, we shipped 6 months worth of product development in 6 hours GAME CHANGER!\n",
- "The document outlines features and capabilities of Julep, a platform for building AI workflows and agents. It showcases customer stories and testimonials highlighting the platform's efficiency and integration benefits with existing tech stacks, similar to how Zapier and Vercel simplify workflows and shipping, respectively. The document also promotes an Education+NGO program offering unlimited free credits to eligible organizations and provides various resources, including demos, integrations, and documentation, to support AI development.\n",
- "----------------------------------------------------------------------------------------------------\n"
- ]
- }
- ],
- "source": [
- "print(\"Matched docs:\\n\\n\")\n",
- "\n",
- "for index, doc in enumerate(response.docs):\n",
- " print(f\"Doc {index + 1}:\")\n",
- " print(f\"Title: {doc.title}\")\n",
- " print(f\"Snippet content:\\n{doc.snippet.content}\")\n",
- " print(\"-\" * 100)"
- ]
- }
- ],
- "metadata": {
- "kernelspec": {
- "display_name": "julep",
- "language": "python",
- "name": "python3"
- },
- "language_info": {
- "codemirror_mode": {
- "name": "ipython",
- "version": 3
- },
- "file_extension": ".py",
- "mimetype": "text/x-python",
- "name": "python",
- "nbconvert_exporter": "python",
- "pygments_lexer": "ipython3",
- "version": "3.12.3"
- }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}
diff --git a/cookbooks/README.md b/cookbooks/README.md
index ce6d04d70..223133ef3 100644
--- a/cookbooks/README.md
+++ b/cookbooks/README.md
@@ -18,9 +18,8 @@ Each notebook explores a unique use case, demonstrating different aspects of Jul
| `05-video-processing-with-natural-language.ipynb` | [Colab Link](https://colab.research.google.com/github/julep-ai/julep/blob/dev/cookbooks/05-video-processing-with-natural-language.ipynb) | Processes videos using natural language commands | Yes |
| `06-browser-use.ipynb` | [Colab Link](https://colab.research.google.com/github/julep-ai/julep/blob/dev/cookbooks/06-browser-use.ipynb) | Demonstrates browser automation capabilities | Yes |
| `07-personalized-research-assistant.ipynb` | [Colab Link](https://colab.research.google.com/github/julep-ai/julep/blob/dev/cookbooks/07-personalized-research-assistant.ipynb) | Demonstrates personalized research assistant capabilities | Yes |
-| `08_customer_support_chatbot.ipynb` | [Colab Link](https://colab.research.google.com/github/julep-ai/julep/blob/dev/cookbooks/08_customer_support_chatbot.ipynb) | Demonstrates customer support chatbot capabilities | Yes |
-| `09_companion_agent.ipynb` | [Colab Link](https://colab.research.google.com/github/julep-ai/julep/blob/dev/cookbooks/09_companion_agent.ipynb) | Demonstrates companion agent capabilities like story generation, user persona management, and more | Yes |
-| `10-crawling-and-rag.ipynb` | [Colab Link](https://colab.research.google.com/github/julep-ai/julep/blob/dev/cookbooks/10-crawling-and-rag.ipynb) | Demonstrates crawling and RAG capabilities | Yes |
+| `08-rag-customer-support-chatbot.ipynb` | [Colab Link](https://colab.research.google.com/github/julep-ai/julep/blob/dev/cookbooks/08-rag-customer-support-chatbot.ipynb) | Demonstrates customer support chatbot capabilities | Yes |
+| `09-companion-agent.ipynb` | [Colab Link](https://colab.research.google.com/github/julep-ai/julep/blob/dev/cookbooks/09-companion-agent.ipynb) | Demonstrates companion agent capabilities like story generation, user persona management, and more | Yes |
## Potential Cookbooks for Contributors
diff --git a/documentation/docs/advanced/agentic-patterns.mdx b/documentation/docs/advanced/agentic-patterns.mdx
index b35abb3d4..ceaa649cc 100644
--- a/documentation/docs/advanced/agentic-patterns.mdx
+++ b/documentation/docs/advanced/agentic-patterns.mdx
@@ -26,15 +26,15 @@ main:
- prompt:
role: system
content: >-
- Generate marketing copy for product X based on the following:
- target_audience: {{_.audience}}
- product_features: {{_.features}}
- keywords: {{_.seo_keywords}}
+ $ f'''Generate marketing copy for product X based on the following:
+ target_audience: {_.audience}
+ product_features: {_.features}
+ keywords: {_.seo_keywords}'''
unwrap: true
# Step 2: Quality check gate
- evaluate:
- quality_check: _.content
+ quality_check: $ _.content
# Step 3: Translation
- prompt:
@@ -66,17 +66,17 @@ main:
# Route based on classification
- switch:
- - case: _.classification == "technical_support"
+ - case: $ _.classification == "technical_support"
then:
- tool: handle_technical
arguments:
...
- - case: _.classification == "billing"
+ - case: $ _.classification == "billing"
then:
- tool: handle_billing
arguments:
...
- - case: _.classification == "general"
+ - case: $ _.classification == "general"
then:
- tool: handle_general
arguments:
@@ -111,18 +111,18 @@ main:
- prompt:
role: system
content: >
- Break this task into multiple subtasks.
- Here is the task: {{_.task}}
+ $ f'''Break this task into multiple subtasks.
+ Here is the task: {_.task}'''
unwrap: true
-- over: _.subtasks
+- over: $ _.subtasks
do:
- workflow: run_subtask
arguments:
...
- tool: aggregate_results
arguments:
- results: _
+ results: $ _
```
2. Voting:
@@ -138,17 +138,17 @@ run_subtask:
# Main workflow
main:
-- over: _.main_tasks
+- over: $ _.main_tasks
do:
- workflow: run_subtask # Run the same task multiple times (given that the `run_subtask` workflow is non-deterministic)
arguments:
...
- tool: perform_voting
arguments:
- results: _
+ results: $ _
- evaluate:
- final_result: _
+ final_result: $ _
```
### 4. Orchestrator-Workers Pattern
@@ -166,15 +166,15 @@ main:
# Orchestrator planning
- prompt:
role: system
- content: Break down the task into subtasks. Here is the task: {{_.task}}
+ content: $ f'''Break down the task into subtasks. Here is the task: {_.task}'''
unwrap: true
# Worker delegation
- foreach:
- in: _.subtasks
+ in: $ _.subtasks
do:
tool: assign_worker
arguments:
- task: _
+ task: $ _
```
### 5. Evaluator-Optimizer Pattern
@@ -210,38 +210,38 @@ tools:
evaluate_content:
- tool: score_content
arguments:
- content: _.content
-- if: _.score < 0.5 # If the content does not meet the criteria, improve it
+ content: $ _.content
+- if: $ _.score < 0.5 # If the content does not meet the criteria, improve it
then:
- workflow: improve_content
arguments:
- content: _0.content # _0 is the main input of this workflow
- feedback: _.feedback # _ is the output of the score_content tool call
+ content: $ steps[0].input.content # steps[0].input is the main input of this workflow
+ feedback: $ _.feedback # _ is the output of the score_content tool call
else:
evaluate:
- final_content: _0.content
+ final_content: $ steps[0].input.content
# Subworkflow to improve content
improve_content:
- prompt:
role: system
- content: Improve the content based on the feedback. Here is the feedback: {{_.feedback}}
+ content: $ f'''Improve the content based on the feedback. Here is the feedback: {_.feedback}'''
unwrap: true
- workflow: evaluate_content
arguments:
- content: _
+ content: $ _
main:
# Initial generation
- prompt:
role: system
- content: Generate initial content. Here is the task: {{_.task}}
+ content: $ f'''Generate initial content. Here is the task: {_.task}'''
unwrap: true
# Evaluation loop
- loop:
- while: "not _.meets_criteria"
+ while: $ not _.meets_criteria
do:
- tool: evaluate_content
- tool: improve_content
@@ -252,7 +252,7 @@ main:
1. The `evaluate_content` subworkflow:
- Takes content as input and scores it using a scoring tool
- If the score is below 0.5, it triggers the improvement workflow
- - Uses special variables (`_0` and `_`) to manage content and feedback between workflows
+ - Uses a special variable (`_`) to manage content and feedback between workflows
- Returns the final content once quality criteria are met
2. The `improve_content` subworkflow:
diff --git a/documentation/docs/advanced/lifecycle.mdx b/documentation/docs/advanced/lifecycle.mdx
index 7babe8eae..071a2ad1d 100644
--- a/documentation/docs/advanced/lifecycle.mdx
+++ b/documentation/docs/advanced/lifecycle.mdx
@@ -84,11 +84,11 @@ We're using two integrations:
#### Step 1: Fetch Weather Data
```yaml
-- over: inputs[0].locations
+- over: $ steps[0].input.locations
map:
tool: weather
arguments:
- location: _
+ location: $ _
```
This step:
@@ -99,11 +99,11 @@ This step:
#### Step 2: Search for Tourist Attractions
```yaml
-- over: inputs[0].locations
+- over: $ steps[0].input.locations
map:
tool: internet_search
arguments:
- query: "'tourist attractions in ' + _"
+ query: $ 'tourist attractions in ' + _
```
@@ -117,11 +117,11 @@ This step:
```yaml
- evaluate:
zipped: |-
- list(
+ $ list(
zip(
- inputs[0].locations,
- [output['result'] for output in outputs[0]],
- outputs[1]
+ steps[0].input.locations,
+ [output['result'] for output in steps[0].output],
+ steps[1].output
)
)
```
@@ -135,7 +135,7 @@ This step:
#### Step 4: Generate Itineraries
```yaml
-- over: _['zipped']
+- over: $ _['zipped']
parallelism: 3
# Inside the map step, each `_` represents the current element in the list
# which is a tuple of (location, weather, attractions)
@@ -143,18 +143,18 @@ This step:
prompt:
- role: system
content: >-
- You are {{{{agent.name}}}}. Your task is to create a detailed itinerary
+ $ f'''You are {agent.name}. Your task is to create a detailed itinerary
for visiting tourist attractions in some locations.
The user will give you the following information for each location:
- The location
- The current weather condition
- - The top tourist attractions
+ - The top tourist attractions'''
- role: user
content: >-
- Location: "{{{{_[0]}}}}"
- Weather: "{{{{_[1]}}}}"
- Attractions: "{{{{_[2]}}}}"
+ $ f'''Location: {_[0]}
+ Weather: {_[1]}
+ Attractions: {_[2]}'''
unwrap: true
```
@@ -171,7 +171,7 @@ This step:
```yaml
- evaluate:
final_plan: |-
- '\\n---------------\\n'.join(activity for activity in _)
+ $ '\\n---------------\\n'.join(activity for activity in _)
```
diff --git a/documentation/docs/advanced/new-syntax.mdx b/documentation/docs/advanced/new-syntax.mdx
new file mode 100644
index 000000000..44f389113
--- /dev/null
+++ b/documentation/docs/advanced/new-syntax.mdx
@@ -0,0 +1,115 @@
+---
+title: 'New Syntax (Important)'
+description: 'Learn about the new workflow syntax and how to migrate your existing workflows'
+icon: 'code'
+---
+
+## Overview
+We've updated our workflow syntax to make data flow more explicit and consistent. These changes improve readability and make workflows more maintainable. While this update requires modifications to existing workflows, it provides a more robust foundation for workflow development.
+
+## Major Changes
+
+### 1. Input/Output Data References
+
+The most significant change is how we reference input and output data between workflow steps. The new syntax makes the data flow more explicit by using the `steps` keyword.
+
+#### Old Syntax:
+- `inputs[x]` - Referenced input data from step x
+- `outputs[x]` - Referenced output data from step x
+- `_x` - Shorthand for input data from step x
+
+#### New Syntax:
+- `steps[x].input` - References input data from step x
+- `steps[x].output` - References output data from step x
+- `_x` - Has been removed
+
+### Example
+
+#### Old Syntax
+```yaml
+- evaluate:
+ input_data: inputs[0].a
+ output_data: outputs[0].b
+ shorthand: _0.c
+```
+
+#### New Syntax
+```yaml
+- evaluate:
+ input: $ steps[0].input.a
+ output: $ steps[0].output.b
+ shorthand: $ steps[0].input.c
+```
+
+
+Notice the addition of the `$` prefix in the new syntax. This indicates that the value should be treated as a Python expression. We'll cover this in detail in the next section.
+
+
+#### Key Changes:
+- `inputs[0]` becomes `steps[0].input`
+- `outputs[0]` becomes `steps[0].output`
+- `_0` becomes `steps[0].input`
+- Added `$` prefix to indicate Python expressions
+
+### 2. Template Syntax Changes Inside `prompt` Steps
+
+Another significant change is the removal of Jinja templates (`{{ }}`) in `log` steps and `prompt` steps. Instead, we now use Python f-strings with the `$` prefix for dynamic content.
+
+#### Old Syntax (Using Jinja):
+```yaml
+- prompt:
+ - role: user
+ content: Write me an article about the topic: {{inputs[0].topic}}
+```
+
+#### New Syntax (Using f-strings):
+```yaml
+- prompt:
+ - role: user
+ content: $ f"Write me an article about the topic: {steps[0].input.topic}"
+ - role: user
+ content: this is only text, no need for dollar sign prefix
+```
+
+For multiple lines, you can use a multiline f-string:
+
+```yaml
+- prompt:
+ - role: user
+ content: |-
+ $ f"""
+ Write me an article about the topic: {steps[0].input.topic}.
+ The article should be {steps[0].input.article_length} words long.
+ """
+```
+
+
+The `$` prefix is only needed when the value contains a Python expression or f-string. Plain text content doesn't require the prefix.
+
+
+### When to Use the $ Prefix
+
+The `$` prefix should be used in two scenarios:
+1. When referencing step data (inputs/outputs)
+2. When using Python expressions or f-strings
+
+#### Examples:
+
+```yaml
+steps:
+ - prompt:
+ # Needs $ because it uses an f-string
+ - role: user
+ content: $ f"The temperature is {steps[0].input.temp}°C"
+
+ # No $ needed - plain text
+ - role: user
+ content: Tell me about the weather
+
+ - evaluate:
+ # Needs $ because it references step data
+ input: $ steps[0].output
+
+ # Needs $ because it's a Python expression
+ condition: $ len(steps[0].input.text) > 100
+```
diff --git a/documentation/docs/advanced/python-expression.mdx b/documentation/docs/advanced/python-expression.mdx
index e427325e4..a22d1ecc9 100644
--- a/documentation/docs/advanced/python-expression.mdx
+++ b/documentation/docs/advanced/python-expression.mdx
@@ -16,29 +16,51 @@ The underscore `_` is a special variable that serves three different purposes de
```yaml
# If task is executed with input `{"topic": "AI"}`
- evaluate:
- topic: _.topic # Accesses the input "AI"
+ topic: $ _.topic # Accesses the input "AI"
```
2. **Previous Step Output**: In any subsequent step, `_` contains the output from the previous step:
```yaml
- evaluate:
- results: _.split('\n') # Splits previous step's output into lines
+ results: $ _.split('\n') # Splits previous step's output into lines
```
3. **Iterator Value**: In `foreach` and `map` steps, `_` represents the current item being iterated.
```yaml
# If the task is executed with input `{"questions": ["What is AI?", "What is Julep?"]}`
- foreach:
- in: _.questions
+ in: $ _.questions
do:
- wait_for_input:
info:
- "message": _ # _ is each question
+ "message": $ _ # _ is each question
```
+## The Special `$` Variable
+
+The `$` variable is used to differentiate between a Python expression and a string. When using the `$` variable, the expression is evaluated as a Python expression.
+
+```yaml
+- evaluate:
+ topic: $ _.topic # Accesses the input "AI"
+```
+
+```yaml
+- prompt:
+ - role: user
+ content: |-
+ f'''
+ Please answer the following question:
+ {_.question}
+ '''
+```
+
+To learn more about how to use the `$` variable, please refer to the [New Syntax](/docs/advanced/new-syntax) section.
+
+
## Where Python Expressions Are Used
-Python expressions can be used in various task steps. For a complete list of step types and their syntax, refer to the [Step Types table in the README](https://github.com/julep-ai/julep#types-of-workflow-steps).
+Python expressions can be used in various task steps. For a complete list of step types and their syntax, refer to the [Step Types table in the README](/docs/advanced/types-of-task-types).
Common places include:
- `evaluate` steps
@@ -99,13 +121,13 @@ Example using these functions in an evaluate step:
```yaml
- evaluate:
# Parse JSON string with size limit of 1MB
- data: json.loads(_.json_string)
+ data: $ json.loads(_.json_string)
# Parse YAML string with size limit of 1MB
- config: yaml.safe_load(_.yaml_string)
+ config: $ yaml.safe_load(_.yaml_string)
# Extract JSON from text that might contain markdown code blocks
- extracted_content: extract_json('Here is some JSON: ```json\n{"key": "value"}\n```')
+ extracted_content: $ extract_json('Here is some JSON: ```json\n{"key": "value"}\n```')
```
### CSV Functions
@@ -191,7 +213,7 @@ name: Data Processing Task
main:
# Using _ as input
- evaluate:
- csv_data: [row for row in csv.reader("a,b,c\n1,2,3")]
+ csv_data: $ [row for row in csv.reader("a,b,c\n1,2,3")]
```
### Standard Library Modules
@@ -220,19 +242,19 @@ name: Data Processing Task
main:
# Using _ as input
- evaluate:
- topics: _.topics # Access input topics
+ topics: $ _.topics # Access input topics
# Using _ as previous output
- evaluate:
- filtered_topics: [t for t in _.topics if len(t) > 3]
+ filtered_topics: $ [t for t in _.topics if len(t) > 3]
# Using _ in foreach
- foreach:
- in: _.filtered_topics
+ in: $ _.filtered_topics
do:
- tool: web_search
arguments:
- query: "'Latest news about ' + _" # _ is each topic
+ query: $ 'Latest news about ' + _ # _ is each topic
```
## Security
diff --git a/documentation/docs/advanced/types-of-task-steps.mdx b/documentation/docs/advanced/types-of-task-steps.mdx
index 756a17013..46a5ab8c3 100644
--- a/documentation/docs/advanced/types-of-task-steps.mdx
+++ b/documentation/docs/advanced/types-of-task-steps.mdx
@@ -42,19 +42,19 @@ Send messages to the AI model:
```yaml YAML
# Simple prompt
-- prompt: "What is your name?"
+- prompt: What is your name?
# Multi-message prompt
- prompt:
- role: system
- content: "You are a helpful assistant"
+ content: You are a helpful assistant
- role: user
content: "Hello!"
# Prompt with settings
- prompt:
- role: user
- content: "Generate a creative story"
+ content: Generate a creative story
settings:
model: "claude-3.5-sonnet"
temperature: 0.8
@@ -91,12 +91,12 @@ Execute tools defined in the task:
# Simple tool call
- tool: web_search
arguments:
- query: "Latest AI news"
+ query: Latest AI news
# Tool call with complex arguments
- tool: process_data
arguments:
- input_data: _.previous_result
+ input_data: $ _.previous_result
options:
format: "json"
validate: true
@@ -109,13 +109,13 @@ Perform calculations or data manipulation:
```yaml YAML
# Simple evaluation
- evaluate:
- count: "len(_.results)"
+ count: $ len(_.results)
# Multiple evaluations
- evaluate:
- total: "sum(_.numbers)"
- average: "_.total / len(_.numbers)"
- formatted: "f'Average: {_.average:.2f}'"
+ total: $ sum(_.numbers)
+ average: $ _.total / len(_.numbers)
+ formatted: $ f'Average: {_.average:.2f}'
```
@@ -166,14 +166,40 @@ Store values for later use:
```yaml YAML
# Set a single value
- set:
- user_name: "John"
+ user_name: John
# Set multiple values
- set:
- count: "len(_.results)"
- has_data: "_.count > 0"
+ count: $ len(_.results)
+ has_data: $ _.count > 0
```
+### Label Step
+
+Label a step to make it easier to identify and access those values later in any step:
+
+```yaml YAML
+# Step 0: Set a single value
+- set:
+ user_name: John
+ label: get_user_name
+
+# Step 1: Set multiple values
+- set:
+ count: $ len(_.results)
+ has_data: $ _.count > 0
+ label: get_count_and_has_data
+```
+
+In any steps following the label step, you can access the values set in the label step using the `$ steps['label_name'].input.attribute_name` or `$ steps['label_name'].output.attribute_name` syntax. For example:
+
+```yaml YAML
+- evaluate:
+ user_name: $ steps['get_user_name'].output.user_name
+- evaluate:
+ count: $ steps['get_count_and_has_data'].output.count
+ has_data: $ steps['get_count_and_has_data'].output.has_data
+```
## Iteration Steps
### Foreach Step
@@ -183,19 +209,19 @@ Iterate over a collection:
```yaml YAML
# Simple foreach
- foreach:
- in: _.items
+ in: $ _.items
do:
- - log: "Processing {{_}}"
+ - log: $ f'Processing {_}'
# Foreach with complex processing
- foreach:
- in: _.documents
+ in: $ _.documents
do:
- tool: analyze
arguments:
- text: _.content
+ text: $ _.content
- evaluate:
- results: "_ + [_.analysis]"
+ results: $ _ + [_.analysis]
```
### Map-Reduce Step
@@ -204,19 +230,19 @@ Process collections in parallel:
```yaml YAML
# Simple map-reduce
-- over: _.urls
+- over: $ _.urls
map:
tool: fetch_content
arguments:
- url: _
- reduce: results + [_]
+ url: $ _
+ reduce: $ results + [_]
# Map-reduce with parallelism
-- over: _.queries
+- over: $ _.queries
map:
tool: web_search
arguments:
- query: _
+ query: $ _
parallelism: 5 # Number of parallel steps to execute
```
@@ -234,7 +260,7 @@ Execute steps concurrently:
- parallel:
tool: task1
arguments:
- param: "value1"
+ param: value1
```
@@ -249,27 +275,27 @@ Conditional execution:
```yaml YAML
# Simple if
-- if: _.count > 0
+- if: $ _.count > 0
then:
- - log: "Found results"
+ - log: Found results
# If-else
-- if: _.score > 0.8
+- if: $ _.score > 0.8
then:
- - log: "High score"
+ - log: High score
else:
- - log: "Low score"
+ - log: Low score
# Nested conditions
-- if: _.type == "A"
+- if: $ _.type == "A"
then:
- - if: _.value > 10
+ - if: $ _.value > 10
then:
- - log: "High value A"
+ - log: High value A
else:
- - log: "Low value A"
+ - log: Low value A
else:
- - log: "Not type A"
+ - log: Not type A
```
### Switch Step
@@ -279,15 +305,15 @@ Multiple condition handling:
```yaml YAML
# Switch statement
- switch:
- - case: _.category == "A"
+ - case: $ _.category == "A"
then:
- - log: "Category A"
- - case: _.category == "B"
+ - log: Category A
+ - case: $ _.category == "B"
then:
- - log: "Category B"
- - case: _ # Default case
+ - log: Category B
+ - case: $ _ # Default case
then:
- - log: "Unknown category"
+ - log: Unknown category
```
## Other Control Flow
@@ -314,14 +340,14 @@ Return values from workflow:
```yaml YAML
# Simple return
-- return: _.result
+- return: $ _.result
# Structured return
- return:
- data: _.processed_data
+ data: $ _.processed_data
metadata:
- count: _.count
- timestamp: "datetime.now().isoformat()"
+ count: $ _.count
+ timestamp: $ datetime.now().isoformat()
```
### Yield Step
@@ -333,15 +359,15 @@ Execute subworkflows:
- yield:
workflow: process_data
arguments:
- input_data: _.raw_data
+ input_data: $ _.raw_data
# Yield with result handling
- yield:
workflow: analyze
arguments:
- text: _.content
+ text: $ _.content
- evaluate:
- analysis_result: _
+ analysis_result: $ _
```
### Log Step
@@ -349,7 +375,7 @@ Execute subworkflows:
Log messages or specific values:
```yaml YAML
-- log: "Processing completed for item {{item_id}}"
+- log: $ f'Processing completed for item {item_id}'
```
### Error Step
@@ -357,7 +383,7 @@ Log messages or specific values:
Handle errors by specifying an error message:
```yaml YAML
-- error: "Invalid input provided"
+- error: Invalid input provided
```
## Example: Complex Workflow
@@ -368,52 +394,52 @@ Here's an example combining various step types:
main:
# Initial setup
- evaluate:
- start_time: "datetime.now().isoformat()"
+ start_time: $ datetime.now().isoformat()
# Get user input
- wait_for_input:
info:
- message: "Enter search topics (comma-separated)"
+ message: Enter search topics (comma-separated)
# Process input
- evaluate:
- topics: "_.input.split(',')"
+ topics: $ _.input.split(',')
# Parallel search
- map_reduce:
- over: _.topics
+ over: $ _.topics
map:
- parallel:
- tool: web_search
arguments:
- query: _
+ query: $ _
- tool: arxiv_search
arguments:
- query: _
+ query: $ _
parallelism: 3
# Process results
- foreach:
- in: _
+ in: $ _
do:
- evaluate:
- web_results: _[0]
- academic_results: _[1]
- - if: "len(_.web_results) > 0 or len(_.academic_results) > 0"
+ web_results: $ _[0]
+ academic_results: $ _[1]
+ - if: $ len(_.web_results) > 0 or len(_.academic_results) > 0
then:
- tool: summarize
arguments:
- texts: _.web_results + _.academic_results
+ texts: $ _.web_results + _.academic_results
else:
- evaluate:
- summary: "'No results found'"
+ summary: No results found
# Return final results
- return:
- results: _
+ results: $ _
metadata:
- start_time: _.start_time
- end_time: "datetime.now().isoformat()"
+ start_time: $ _.start_time
+ end_time: $ datetime.now().isoformat()
```
## Best Practices
diff --git a/documentation/docs/concepts/docs.mdx b/documentation/docs/concepts/docs.mdx
index 08b10e863..9b40b300a 100644
--- a/documentation/docs/concepts/docs.mdx
+++ b/documentation/docs/concepts/docs.mdx
@@ -324,11 +324,11 @@ By leveraging [System Tools](/docs/concepts/tools#system-tools), Julep [Tasks](/
# Step that lists all documents for the current user
- tool: "list_user_docs"
arguments:
- user_id: "'USER_ID'"
+ user_id: USER_ID
# Step that evaluates the textual contents of all documents for the current user
- evaluate:
- all_user_docs_contents: [doc.content for doc in _.items]
+ all_user_docs_contents: $ [doc.content for doc in _.items]
```
diff --git a/documentation/docs/concepts/tasks.mdx b/documentation/docs/concepts/tasks.mdx
index 6772cc026..960271826 100644
--- a/documentation/docs/concepts/tasks.mdx
+++ b/documentation/docs/concepts/tasks.mdx
@@ -77,12 +77,12 @@ description: Create a concise summary of any document
sample_sub_workflow:
- prompt: |-
- Tell me a joke about {{inputs[0].topic}}:
+ $ f'Tell me a joke about {steps[0].input.topic}:'
main:
- workflow: sample_sub_workflow
arguments:
- topic: "'AI'"
+ topic: AI
```
### Steps
@@ -121,20 +121,41 @@ Tasks have access to three types of context:
#### Input Variables
Access input parameters:
```yaml YAML
-- prompt: "Hello {{inputs[0].user_name}}"
+- prompt: $ f'Hello {steps[0].input.user_name}'
```
#### Step Results
Use outputs from previous steps:
```yaml YAML
-- evaluate: len(_.search_results)
-- if: _.count > 0
+- evaluate: $ len(_.search_results)
+- if: $ _.count > 0
```
+
+
+In any step, you can access the input and output of a step using the `steps[index].output` or `steps[index].input` variable. For example:
+
+```yaml
+- evaluate:
+ topic: $ steps[0].input.topic
+```
+
+```yaml
+- evaluate:
+ topic: $ steps[0].output.topic
+```
+
+In Julep, the steps are indexed from 0. So the first step is `steps[0]` and the second step is `steps[1]` and so on.
+Furthermore the first step input is nothing but the task input and the last step output is nothing but the output of the task.
+
+
+
+To learn more about how to use the `$` variable and new syntax, please refer to the [New Syntax](/docs/advanced/new-syntax) section.
+
#### Environment Context
Access agent and session data:
```yaml YAML
-- prompt: "Agent {{agent.name}} is helping you"
+- prompt: $ f'Agent {agent.name} is helping you'
```
@@ -166,7 +187,7 @@ main:
- prompt: Analyze customer sentiment
- tool: categorize
arguments:
- text: inputs[0].feedback_text
+ text: $ steps[0].input.feedback_text
```
> Learn more about tools [here](/docs/concepts/tools).
@@ -195,19 +216,19 @@ input_schema:
main:
- prompt: |-
- Analyze the following text and create a summary:
- {{inputs[0].document_text}}
+ $ f'''Analyze the following text and create a summary:
+ {steps[0].input.document_text}'''
unwrap: true
- evaluate:
- too_long: len(_) > 500
- - if: _.too_long
+ too_long: $ len(_) > 500
+ - if: $ _.too_long
then:
prompt: |-
- Make the summary more concise:
- {{outputs[0]}}
+ $ f'''Make the summary more concise:
+ {steps[0].output}'''
else:
evaluate:
- content: outputs[0]
+ content: $ steps[0].output
```
```python Python
diff --git a/documentation/docs/concepts/tools.mdx b/documentation/docs/concepts/tools.mdx
index 05e879ab0..00b875784 100644
--- a/documentation/docs/concepts/tools.mdx
+++ b/documentation/docs/concepts/tools.mdx
@@ -45,7 +45,7 @@ tools:
main:
- tool: send_notification
arguments:
- content: '"hi"' # <-- python expression
+ content: "hi"
```
@@ -74,7 +74,7 @@ tools:
main:
- tool: list_agents
arguments:
- limit: 10 # <-- python expression
+ limit: $ 10
```
@@ -155,7 +155,7 @@ tools:
main:
- tool: wikipedia_search
arguments:
- query: "'Julep'"
+ query: "Julep"
```
@@ -179,7 +179,7 @@ main:
- tool: hello
arguments:
json:
- test: _.input # <-- python expression
+ test: $ _.input # <-- python expression
```
## How to Use Tools
@@ -247,7 +247,7 @@ tools:
main:
- tool: wikipedia_search
arguments:
- query: "'Julep'"
+ query: "Julep"
```
```python Python
diff --git a/documentation/docs/integrations/web_browser_automation/remote_browser.mdx b/documentation/docs/integrations/web_browser_automation/remote_browser.mdx
index 270b7e733..f1688454a 100644
--- a/documentation/docs/integrations/web_browser_automation/remote_browser.mdx
+++ b/documentation/docs/integrations/web_browser_automation/remote_browser.mdx
@@ -53,14 +53,14 @@ To get started with the Remote Browser integration, follow these steps to config
project_id: {browserbase_project_id}
- evaluate:
- browser_session_id: _.id
- connect_url: _.connect_url
+ browser_session_id: $ _.id
+ connect_url: $ _.connect_url
- tool: browser_tool
arguments:
- connect_url: _.connect_url
- action: "'navigate'"
- text: "'https://www.google.com'"
+ connect_url: $ _.connect_url
+ action: "navigate"
+ text: "https://www.google.com"
```
diff --git a/documentation/docs/introduction/quickstart.mdx b/documentation/docs/introduction/quickstart.mdx
index ead099bf0..19e20c6fe 100644
--- a/documentation/docs/introduction/quickstart.mdx
+++ b/documentation/docs/introduction/quickstart.mdx
@@ -26,7 +26,7 @@ main:
- role: system
content: You are a creative story writer.
- role: user
- content: Write a short story about {{inputs[0].topic}}
+ content: $ f'Write a short story about {steps[0].input.topic}'
```
@@ -107,7 +107,7 @@ Let's create a task that generates a short story based on a given topic:
- role: system
content: You are a creative story writer.
- role: user
- content: Write a short story about {{inputs.topic}}
+ content: $ f'Write a short story about {steps[0].input.topic}'
""")
task = client.tasks.create(
@@ -127,7 +127,7 @@ Let's create a task that generates a short story based on a given topic:
- role: system
content: You are a creative story writer.
- role: user
- content: Write a short story about {{inputs.topic}}
+ content: $ f'Write a short story about {steps[0].input.topic}'
`;
const task = await client.tasks.create(
diff --git a/documentation/docs/tutorials/browser-use.mdx b/documentation/docs/tutorials/browser-use.mdx
index 581fb85c7..4f8efefb0 100644
--- a/documentation/docs/tutorials/browser-use.mdx
+++ b/documentation/docs/tutorials/browser-use.mdx
@@ -87,8 +87,8 @@ tools:
```yaml
- tool: create_julep_session
arguments:
- agent: str(agent.id)
- situation: "'The environment is a browser'"
+ agent: $ str(agent.id)
+ situation: "The environment is a browser"
recall: 'False'
```
@@ -98,7 +98,7 @@ tools:
```yaml
- evaluate:
- julep_session_id: _.id
+ julep_session_id: $ _.id
```
After creating the session, we store its unique identifier for future reference.
@@ -115,8 +115,8 @@ tools:
```yaml
- evaluate:
- browser_session_id: _.id
- connect_url: _.connect_url
+ browser_session_id: $ _.id
+ connect_url: $ _.connect_url
```
We store both the browser session ID and connect URL in a single evaluation step.
@@ -125,7 +125,7 @@ tools:
```yaml
- tool: get_session_view_urls
arguments:
- id: _.browser_session_id
+ id: $ _.browser_session_id
```
This step retrieves various URLs associated with the browser session, including debugging interfaces and live view URLs.
@@ -133,7 +133,7 @@ tools:
```yaml
- evaluate:
- debugger_url: _.urls.debuggerUrl
+ debugger_url: $ _.urls.debuggerUrl
```
We specifically store the debugger URL, which provides access to Chrome DevTools Protocol debugging interface.
@@ -142,9 +142,9 @@ tools:
```yaml
- tool: perform_browser_action
arguments:
- connect_url: outputs[3].connect_url
- action: "'navigate'"
- text: "'https://www.google.com'"
+ connect_url: $ steps[3].output.connect_url
+ action: "navigate"
+ text: "https://www.google.com"
```
This step navigates to Google's homepage to avoid sending a blank screenshot when computer use starts.
@@ -153,12 +153,12 @@ tools:
```yaml
- workflow: run_browser
arguments:
- julep_session_id: outputs[1].julep_session_id
- cdp_url: outputs[3].connect_url
+ julep_session_id: $ steps[1].output.julep_session_id
+ cdp_url: $ steps[3].output.connect_url
messages:
- - role: "'user'"
+ - role: "user"
content: |-
- """
+ $ """
* You are utilising a headless chrome browser to interact with the internet.
* You can use the computer tool to interact with the browser.
@@ -170,7 +170,7 @@ tools:
* YOU CANNOT WRITE TO THE SEARCH BAR OF THE BROWSER.
- *""" + inputs[0].goal + NEWLINE + ""
+ *""" + steps[0].input.goal + NEWLINE + ""
```
Finally, we initiate the interactive browser workflow with system capabilities and user goal.
@@ -185,8 +185,8 @@ The `run_browser` subworkflow is a crucial component that handles the interactiv
```yaml
- tool: session_chat
arguments:
- session_id: _.julep_session_id
- messages: _.messages
+ session_id: $ _.julep_session_id
+ messages: $ _.messages
recall: 'False'
```
This step engages the AI agent in conversation, allowing it to:
@@ -199,14 +199,14 @@ The `run_browser` subworkflow is a crucial component that handles the interactiv
```yaml
- foreach:
- in: _.tool_calls
+ in: $ _.tool_calls
do:
tool: perform_browser_action
arguments:
- connect_url: inputs[0].cdp_url
- action: _.action
- text: _.get('text')
- coordinate: _.get('coordinate')
+ connect_url: $ steps[0].input.cdp_url
+ action: $ _.action
+ text: $ _.get('text')
+ coordinate: $ _.get('coordinate')
```
This component:
- Iterates through planned actions sequentially
@@ -219,9 +219,9 @@ The `run_browser` subworkflow is a crucial component that handles the interactiv
```yaml
- workflow: check_goal_status
arguments:
- messages: _.messages
- julep_session_id: _.julep_session_id
- cdp_url: _.cdp_url
+ messages: $ _.messages
+ julep_session_id: $ _.julep_session_id
+ cdp_url: $ _.cdp_url
```
This final part:
- Assesses progress toward the user's goal
@@ -239,14 +239,14 @@ The `check_goal_status` subworkflow is a recursive component that ensures contin
```yaml
check_goal_status:
- - if: len(_.messages) > 0
+ - if: $ len(_.messages) > 0
then:
workflow: run_browser
arguments:
- messages: _.messages
- julep_session_id: _.julep_session_id
- cdp_url: _.cdp_url
- workflow_label: "'run_browser'"
+ messages: $ _.messages
+ julep_session_id: $ _.julep_session_id
+ cdp_url: $ _.cdp_url
+ workflow_label: "run_browser"
```
@@ -266,7 +266,20 @@ This recursive pattern ensures that the browser automation continues until eithe
```yaml YAML
# yaml-language-server: $schema=https://raw.githubusercontent.com/julep-ai/julep/refs/heads/dev/schemas/create_task_request.json
- name: computer-use-task
+ name: Julep Browser Use Task
+ description: A Julep agent that can use the computer tool to interact with the browser.
+
+ ########################################################
+ ################### INPUT SCHEMA #######################
+ ########################################################
+
+ input_schema:
+ type: object
+ properties:
+ goal:
+ type: string
+ required:
+ - goal
########################################################
####################### TOOLS ##########################
@@ -312,18 +325,6 @@ This recursive pattern ensures that the browser automation continues until eithe
resource: session
operation: chat
- ########################################################
- ################### INPUT SCHEMA #######################
- ########################################################
-
- input_schema:
- type: object
- properties:
- goal:
- type: string
- required:
- - goal
-
########################################################
################### MAIN WORKFLOW ######################
########################################################
@@ -333,51 +334,51 @@ This recursive pattern ensures that the browser automation continues until eithe
# Step #0 - Create Julep Session
- tool: create_julep_session
arguments:
- agent: str(agent.id)
- situation: "'Juelp Browser Use Agent'"
+ agent: $ str(agent.id)
+ situation: "Juelp Browser Use Agent"
recall: 'False'
# Step #1 - Store Julep Session ID
- evaluate:
- julep_session_id: _.id
+ julep_session_id: $ _.id
# Step #2 - Create Browserbase Session
- tool: create_browserbase_session
arguments:
- project_id: "'c35ee022-883e-4070-9f3c-89607393214b'"
+ project_id: "c35ee022-883e-4070-9f3c-89607393214b"
# Step #3 - Store Browserbase Session Info
- evaluate:
- browser_session_id: _.id
- connect_url: _.connect_url
+ browser_session_id: $ _.id
+ connect_url: $ _.connect_url
# Step #4 - Get Session View URLs
- tool: get_session_view_urls
arguments:
- id: _.browser_session_id
+ id: $ _.browser_session_id
# Step #5 - Store Debugger URL
- evaluate:
- debugger_url: _.urls.debuggerUrl
+ debugger_url: $ _.urls.debuggerUrl
# Step #6 - Navigate to Google
# Navigate to google to avoid sending a blank
# screenshot when computer use starts
- tool: perform_browser_action
arguments:
- connect_url: outputs[3].connect_url
- action: "'navigate'"
- text: "'https://www.google.com'"
+ connect_url: $ steps[3].output.connect_url
+ action: "navigate"
+ text: "https://www.google.com"
# Step #7 - Run Browser Workflow
- workflow: run_browser
arguments:
- julep_session_id: outputs[1].julep_session_id
- cdp_url: outputs[3].connect_url
+ julep_session_id: $ steps[1].output.julep_session_id
+ cdp_url: $ steps[3].output.connect_url
messages:
- - role: "'user'"
+ - role: "user"
content: |-
- """
+ $ """
* You are utilising a headless chrome browser to interact with the internet.
* You can use the computer tool to interact with the browser.
@@ -385,12 +386,12 @@ This recursive pattern ensures that the browser automation continues until eithe
* You are already inside the browser.
* You can't open new tabs or windows.
* For now, rely on screenshots as the only way to see the browser.
- * You can't don't have access to the browser's UI.
+ * You don't have access to the browser's UI.
* YOU CANNOT WRITE TO THE SEARCH BAR OF THE BROWSER.
- *""" + inputs[0].goal + NEWLINE + ""
- workflow_label: "'run_browser'" # <----- REMOVE THIS
+ *""" + steps[0].input.goal + NEWLINE + ""
+ workflow_label: "run_browser" # <----- REMOVE THIS
########################################################
@@ -402,60 +403,62 @@ This recursive pattern ensures that the browser automation continues until eithe
# Step #0 - Agent Interaction
- tool: session_chat
arguments:
- session_id: _.julep_session_id
- messages: _.messages
+ session_id: $ _.julep_session_id
+ messages: $ _.messages
recall: 'False'
# Step #1 - Evaluate the response from the agent
- evaluate:
- content: _.choices[0].message.content
- tool_calls: "[ \
- { \
- 'tool_call_id': tool_call.id, \
- 'action': load_json(tool_call.function.arguments)['action'], \
- 'text': load_json(tool_call.function.arguments).get('text'), \
- 'coordinate': load_json(tool_call.function.arguments).get('coordinate') \
- } \
- for tool_call in _.choices[0].message.tool_calls or [] if tool_call.type == 'function']"
+ content: $ _.choices[0].message.content
+ tool_calls: |-
+ $ [
+ {
+ 'tool_call_id': tool_call.id,
+ 'action': load_json(tool_call.function.arguments)['action'],
+ 'text': load_json(tool_call.function.arguments).get('text'),
+ 'coordinate': load_json(tool_call.function.arguments).get('coordinate')
+ }
+ for tool_call in _.choices[0].message.tool_calls or [] if tool_call.type == 'function']
# Step #2 - Perform the actions requested by the agent
- foreach:
- in: _.tool_calls
+ in: $ _.tool_calls
do:
tool: perform_browser_action
arguments:
- connect_url: inputs[0].cdp_url
- action: _.action if not (str(_.get('text', '')).startswith('http') and _.action == 'type') else 'navigate'
- text: _.get('text')
- coordinate: _.get('coordinate')
+ connect_url: $ steps[0].input.cdp_url
+ action: $ _.action if not (str(_.get('text', '')).startswith('http') and _.action == 'type') else 'navigate'
+ text: $ _.get('text')
+ coordinate: $ _.get('coordinate')
# Step #3 - Convert the result of the actions into a chat message
- evaluate:
- contents: "[\
- { \
- 'type': 'image_url', \
- 'image_url': { \
- 'url': result['base64_image'], \
+ contents: >-
+ $ [ \
+ { \
+ 'type': 'image_url', \
+ 'image_url': { \
+ 'url': result['base64_image'], \
+ } \
+ } if result['base64_image'] is not None else \
+ { \
+ 'type': 'text', \
+ 'text': result['output'] if result['output'] is not None else 'done' \
} \
- } if result['base64_image'] is not None else \
- { \
- 'type': 'text', \
- 'text': result['output'] if result['output'] is not None else 'done' \
- } \
- for result in _]"
+ for result in _]
# Step #4 - Convert the result of the actions into a chat message
- evaluate:
- messages: "[{'content': [_.contents[i]], 'role': 'tool', 'name': 'computer', 'tool_call_id': outputs[1].tool_calls[i].tool_call_id} for i in range(len(_.contents))]"
+ messages: "$ [{'content': [_.contents[i]], 'role': 'tool', 'name': 'computer', 'tool_call_id': steps[1].output.tool_calls[i].tool_call_id} for i in range(len(_.contents))]"
# Step #5 - Check if the goal is achieved and recursively run the browser
- workflow: check_goal_status
arguments:
- messages: _.messages
- julep_session_id: inputs[0].julep_session_id
- cdp_url: inputs[0].cdp_url
- workflow_label: "'check_goal_status'"
+ messages: $ _.messages
+ julep_session_id: $ steps[0].input.julep_session_id
+ cdp_url: $ steps[0].input.cdp_url
+ workflow_label: "check_goal_status"
########################################################
@@ -465,14 +468,14 @@ This recursive pattern ensures that the browser automation continues until eithe
check_goal_status:
# Step #0 - Check if the goal is achieved and recursively run the browser
- - if: len(_.messages) > 0
+ - if: $ len(_.messages) > 0
then:
workflow: run_browser
arguments:
- messages: _.messages
- julep_session_id: _.julep_session_id
- cdp_url: _.cdp_url
- workflow_label: "'run_browser'"
+ messages: $ _.messages
+ julep_session_id: $ _.julep_session_id
+ cdp_url: $ _.cdp_url
+ workflow_label: "run_browser"
```
diff --git a/documentation/docs/tutorials/crawling-web-pages-with-rag.mdx b/documentation/docs/tutorials/customer-support-rag.mdx
similarity index 82%
rename from documentation/docs/tutorials/crawling-web-pages-with-rag.mdx
rename to documentation/docs/tutorials/customer-support-rag.mdx
index ade787dc3..722e0f959 100644
--- a/documentation/docs/tutorials/crawling-web-pages-with-rag.mdx
+++ b/documentation/docs/tutorials/customer-support-rag.mdx
@@ -1,12 +1,13 @@
---
-title: 'Crawling Web Pages with RAG'
-description: 'Learn how to crawl web pages and implement RAG (Retrieval Augmented Generation) with Julep'
+title: 'Customer Support Chatbot using RAG'
+description: 'Learn how to build a customer support chatbot using RAG with Julep'
icon: 'display'
---
## Overview
This tutorial demonstrates how to:
+
- Set up a web crawler using Julep's Spider integration
- Process and store crawled content in a document store
- Implement RAG for enhanced AI responses
@@ -66,18 +67,18 @@ We're using two tools:
```yaml
- tool: spider_crawler
arguments:
- url: "_['url']"
+ url: $ _['url']
params:
- request: "'smart_mode'"
- limit: _['pages_limit']
- return_format: "'markdown'"
+ request: "smart_mode"
+ limit: $ _['pages_limit']
+ return_format: "markdown"
proxy_enabled: "True"
filter_output_images: "True"
filter_output_svg: "True"
readability: "True"
sitemap: "True"
chunking_alg:
- type: "'bysentence'"
+ type: "bysentence"
value: "15"
```
@@ -95,23 +96,24 @@ We're using two tools:
```yaml
- evaluate:
- documents: _['content']
+ documents: $ _['content']
- - over: "[(_0.content, chunk) for chunk in _['documents']]"
+ - over: $ "[(steps[0].input.content, chunk) for chunk in _['documents']]"
parallelism: 3
map:
prompt:
- role: user
content: >-
+ $ f'''
- {{_[0]}}
+ {_[0]}
- {{_[1]}}
+ {_[1]}
- Please give a short succinct context to situate this chunk within the overall document.
+ Please give a short succinct context to situate this chunk within the overall document.'''
```
This step:
@@ -122,17 +124,17 @@ We're using two tools:
```yaml
- - over: _['final_chunks']
+ - over: $ _['final_chunks']
parallelism: 3
map:
tool: create_agent_doc
arguments:
- agent_id: "'{agent.id}'"
+ agent_id: $ agent.id
data:
metadata:
- source: "'spider_crawler'"
- title: "'Website Document'"
- content: _
+ source: spider_crawler
+ title: Website Document
+ content: $ _
```
This step:
@@ -144,8 +146,22 @@ We're using two tools:
```yaml YAML
- name: Crawl a website and create a agent document
+ # yaml-language-server: $schema=https://raw.githubusercontent.com/julep-ai/julep/refs/heads/dev/schemas/create_task_request.json
+ name: Julep Customer Support RAG Task
+ description: A Julep agent that can crawl a website and store the content in the document store.
+
+ ########################################################
+ ################### INPUT SCHEMA #######################
+ ########################################################
+ input_schema:
+ type: object
+ properties:
+ url:
+ type: string
+ pages_limit:
+ type: integer
+
########################################################
################### TOOLS ##############################
########################################################
@@ -175,26 +191,27 @@ We're using two tools:
# Step #0 - Evaluate the content
- evaluate:
- documents: _['content']
+ documents: $ _['content']
# Step #1 - Process each content chunk in parallel
- - over: "[(_0.content, chunk) for chunk in _['documents']]"
+ - over: $ "[(steps[0].input.content, chunk) for chunk in _['documents']]"
parallelism: 3
map:
prompt:
- role: user
content: >-
+ $ f'''
- {{_[0]}}
+ {_[0]}
Here is the chunk we want to situate within the whole document
- {{_[1]}}
+ {_[1]}
Please give a short succinct context to situate this chunk within the overall document for the purposes of improving search retrieval of the chunk.
- Answer only with the succinct context and nothing else.
+ Answer only with the succinct context and nothing else.'''
unwrap: true
settings:
@@ -203,23 +220,23 @@ We're using two tools:
# Step #2 - Create a new document and add it to the agent docs store
- evaluate:
final_chunks: |
- [
- NEWLINE.join([chunk, succint]) for chunk, succint in zip(_1.documents, _)
+ $ [
+ NEWLINE.join([chunk, succint]) for chunk, succint in zip(steps[1].input.documents, _)
]
# Step #3 - Create a new document and add it to the agent docs store
- - over: _['final_chunks']
+ - over: $ _['final_chunks']
parallelism: 3
map:
tool: create_agent_doc
arguments:
- agent_id: "'00000000-0000-0000-0000-000000000000'" # <--- This is the agent id of the agent you want to add the document to
+ agent_id: "00000000-0000-0000-0000-000000000000" # <--- This is the agent id of the agent you want to add the document to
data:
metadata:
- source: "'spider_crawler'"
+ source: "spider_crawler"
- title: "'Website Document'"
- content: _
+ title: "Website Document"
+ content: $ _
########################################################
################### MAIN WORKFLOW ######################
@@ -230,11 +247,11 @@ We're using two tools:
# Step #0 - Define a tool call step that calls the spider_crawler tool with the url input
- tool: spider_crawler
arguments:
- url: "_['url']" # You can also use 'inputs[0]['url']'
+ url: $ _['url'] # You can also use 'steps[0].input['url']'
params:
- request: "'smart_mode'"
- limit: _['pages_limit'] # <--- This is the number of pages to crawl (taken from the input of the task)
- return_format: "'markdown'"
+ request: "smart_mode"
+ limit: $ _['pages_limit'] # <--- This is the number of pages to crawl (taken from the input of the task)
+ return_format: "markdown"
proxy_enabled: "True"
filter_output_images: "True" # <--- This is to execlude images from the output
filter_output_svg: "True" # <--- This is to execlude svg from the output
@@ -242,16 +259,16 @@ We're using two tools:
readability: "True" # <--- This is to make the output more readable
sitemap: "True" # <--- This is to crawl the sitemap
chunking_alg: # <--- Using spider's bysentence algorithm to chunk the output
- type: "'bysentence'"
+ type: "bysentence"
value: "15" # <--- This is the number of sentences per chunk
# Step #1 - Evaluate step to document chunks
- foreach:
- in: _['result']
+ in: $ _['result']
do:
workflow: index_page
arguments:
- content: _.content
+ content: $ _.content
```
@@ -459,4 +476,4 @@ For additional support or to learn more:
## Next Steps
-Try this task yourself, check out the full example, see the [crawling-and-rag cookbook](https://github.com/julep-ai/julep/blob/main/cookbooks/10-crawling-and-rag.ipynb).
\ No newline at end of file
+Try this task yourself, check out the full example, see the [Customer Support Chatbot using RAG cookbook](https://github.com/julep-ai/julep/blob/main/cookbooks/08-rag-customer-support-chatbot.ipynb).
\ No newline at end of file
diff --git a/documentation/docs/tutorials/trip-planning.mdx b/documentation/docs/tutorials/trip-planning.mdx
index 1ce9bfb78..921f2cb92 100644
--- a/documentation/docs/tutorials/trip-planning.mdx
+++ b/documentation/docs/tutorials/trip-planning.mdx
@@ -65,11 +65,11 @@ We're using two integrations:
```yaml
- - over: inputs[0].locations
- map:
- tool: weather
- arguments:
- location: _
+ - over: $ steps[0].input.locations
+ map:
+ tool: weather
+ arguments:
+ location: $ _
```
@@ -77,11 +77,11 @@ We're using two integrations:
For example:
```yaml
- - over: ["Paris", "London"]
+ - over: $ ["Paris", "London"]
map:
tool: weather
arguments:
- location: _ # _ will be "Paris", then "London"
+ location: $ _ # _ will be "Paris", then "London"
```
@@ -94,11 +94,11 @@ We're using two integrations:
```yaml
- - over: inputs[0].locations
- map:
- tool: internet_search
- arguments:
- query: "'tourist attractions in ' + _"
+ - over: $ steps[0].input.locations
+ map:
+ tool: internet_search
+ arguments:
+ query: $ 'tourist attractions in ' + _
```
@@ -110,16 +110,16 @@ We're using two integrations:
- ```yaml
- - evaluate:
- zipped: |-
- list(
- zip(
- inputs[0].locations,
- [output['result'] for output in outputs[0]],
- outputs[1]
- )
+ ```yaml
+ - evaluate:
+ zipped: |-
+ $ list(
+ zip(
+ steps[0].input.locations,
+ [output['result'] for output in steps[0].output],
+ steps[1].output
)
+ )
```
@@ -133,27 +133,27 @@ We're using two integrations:
```yaml
- - over: _['zipped']
- parallelism: 3
- # Inside the map step, each `_` represents the current element in the list
- # which is a tuple of (location, weather, attractions)
- map:
- prompt:
- - role: system
- content: >-
- You are {{agent.name}}. Your task is to create a detailed itinerary
- for visiting tourist attractions in some locations.
- The user will give you the following information for each location:
-
- - The location
- - The current weather condition
- - The top tourist attractions
- - role: user
- content: >-
- Location: "{{_[0]}}"
- Weather: "{{_[1]}}"
- Attractions: "{{_[2]}}"
- unwrap: true
+ - over: $ _['zipped']
+ parallelism: 3
+ # Inside the map step, each `_` represents the current element in the list
+ # which is a tuple of (location, weather, attractions)
+ map:
+ prompt:
+ - role: system
+ content: >-
+ $ f'''You are {agent.name}. Your task is to create a detailed itinerary
+ for visiting tourist attractions in some locations.
+ The user will give you the following information for each location:
+
+ - The location
+ - The current weather condition
+ - The top tourist attractions'''
+ - role: user
+ content: >-
+ $ f'''Location: "{_[0]}"
+ Weather: "{_[1]}"
+ Attractions: "{_[2]}"'''
+ unwrap: true
```
@@ -168,10 +168,10 @@ We're using two integrations:
- ```yaml
- - evaluate:
- final_plan: |-
- '\\n---------------\\n'.join(activity for activity in _)
+ ```yaml
+ - evaluate:
+ final_plan: |-
+ $ '\\n---------------\\n'.join(activity for activity in _)
```
@@ -186,7 +186,8 @@ We're using two integrations:
```yaml YAML
# yaml-language-server: $schema=https://raw.githubusercontent.com/julep-ai/julep/refs/heads/dev/schemas/create_task_request.json
- name: Tourist Plan With Weather And Attractions
+ name: Julep Trip Planning Task
+ description: A Julep agent that can generate a detailed itinerary for visiting tourist attractions in some locations, considering the current weather conditions.
########################################################
################### INPUT SCHEMA #######################
@@ -229,59 +230,56 @@ We're using two integrations:
################### MAIN WORKFLOW ######################
########################################################
- main:
- # Step #0 - Get weather data for each location
- - over: inputs[0].locations
- map:
- tool: weather
- arguments:
- location: _
-
- # Step #1 - Search for tourist attractions for each location
- - over: inputs[0].locations
- map:
- tool: internet_search
- arguments:
- query: "'tourist attractions in ' + _"
-
- # Step #2 - Zip locations, weather, and attractions into a list of tuples [(location, weather, attractions)]
- - evaluate:
- zipped: |-
- list(
- zip(
- inputs[0].locations,
- [output['result'] for output in outputs[0]],
- outputs[1]
- )
+main:
+- over: $ steps[0].input.locations
+ map:
+ tool: weather
+ arguments:
+ location: $ _
+
+- over: $ steps[0].input.locations
+ map:
+ tool: internet_search
+ arguments:
+ query: $ 'tourist attractions in ' + _
+
+# Zip locations, weather, and attractions into a list of tuples [(location, weather, attractions)]
+- evaluate:
+ zipped: |-
+ $ list(
+ zip(
+ steps[0].input.locations,
+ [output['result'] for output in steps[0].output],
+ steps[1].output
)
-
- # Step #3 - Generate itineraries for each location
- - over: _['zipped']
- parallelism: 3
- # Inside the map step, each `_` represents the current element in the list
- # which is a tuple of (location, weather, attractions)
- map:
- prompt:
- - role: system
- content: >-
- You are {{agent.name}}. Your task is to create a detailed itinerary
- for visiting tourist attractions in some locations.
- The user will give you the following information for each location:
-
- - The location
- - The current weather condition
- - The top tourist attractions
- - role: user
- content: >-
- Location: "{{_[0]}}"
- Weather: "{{_[1]}}"
- Attractions: "{{_[2]}}"
- unwrap: true
-
- # Step #4 - Format the final output
- - evaluate:
- final_plan: |-
- '\\n---------------\\n'.join(activity for activity in _)
+ )
+
+
+- over: $ _['zipped']
+ parallelism: 3
+ # Inside the map step, each `_` represents the current element in the list
+ # which is a tuple of (location, weather, attractions)
+ map:
+ prompt:
+ - role: system
+ content: >-
+ $ f'''You are {agent.name}. Your task is to create a detailed itinerary
+ for visiting tourist attractions in some locations.
+ The user will give you the following information for each location:
+
+ - The location
+ - The current weather condition
+ - The top tourist attractions'''
+ - role: user
+ content: >-
+ $ f'''Location: "{_[0]}"
+ Weather: "{_[1]}"
+ Attractions: "{_[2]}"'''
+ unwrap: true
+
+- evaluate:
+ final_plan: |-
+ $ '\\n---------------\\n'.join(activity for activity in _)
```
diff --git a/documentation/docs/tutorials/video-processing.mdx b/documentation/docs/tutorials/video-processing.mdx
index 47c4334e3..e44992ce0 100644
--- a/documentation/docs/tutorials/video-processing.mdx
+++ b/documentation/docs/tutorials/video-processing.mdx
@@ -80,16 +80,16 @@ We're using three main integrations:
```yaml
- - tool: cloudinary_upload
- arguments:
- file: '_0.upload_file'
- public_id: '_0.public_id'
- upload_params:
- resource_type: "'video'"
+ - tool: cloudinary_upload
+ arguments:
+ file: $ steps[0].input.video_url
+ public_id: $ steps[0].input.public_id
+ upload_params:
+ resource_type: video
```
-
- The `_0` variable refers to the initial input object passed to the task. It's used to access the input parameters defined in the input schema.
+
+ The `steps[0].input` variable refers to the initial input object passed to the task. It's used to access the input parameters defined in the input schema.
This step:
@@ -102,13 +102,13 @@ We're using three main integrations:
```yaml
- tool: cloudinary_upload
arguments:
- file: '_0.upload_file'
- public_id: '_0.public_id'
+ file: $ steps[0].input.upload_file
+ public_id: $ steps[0].input.public_id
upload_params:
- resource_type: "'video'"
+ resource_type: video
transformation:
- - start_offset: "0"
- end_offset: "30"
+ - start_offset: 0
+ end_offset: 30
```
This step:
@@ -123,7 +123,7 @@ We're using three main integrations:
content:
- type: image_url
image_url:
- url: "{{trimmed_video_url}}"
+ url: trimmed_video_url
- type: text
text: |-
Which speakers are speaking in the video? And where does each of them sit?
@@ -139,7 +139,7 @@ We're using three main integrations:
```yaml
- evaluate:
speakers_transformations: |-
- [
+ $ [
transform
for speaker in _.speakers_json
for transform in [
@@ -169,10 +169,10 @@ We're using three main integrations:
```yaml
- tool: cloudinary_upload
arguments:
- file: '_0.upload_file'
- public_id: '_0.public_id'
+ file: $ steps[0].input.upload_file
+ public_id: $ steps[0].input.public_id
upload_params:
- resource_type: "'video'"
+ resource_type: video
transformation: _.speakers_transformations
```
@@ -186,7 +186,8 @@ We're using three main integrations:
```yaml YAML
# yaml-language-server: $schema=https://raw.githubusercontent.com/julep-ai/julep/refs/heads/dev/schemas/create_task_request.json
- name: Video Processing With Natural Language
+ name: Julep Video Processing Task
+ description: A Julep agent that can process and analyze videos using Cloudinary
########################################################
################### INPUT SCHEMA #######################
@@ -228,10 +229,10 @@ We're using three main integrations:
# Step #0 - Upload the video to cloudinary
- tool: cloudinary_upload
arguments:
- file: '_0.video_url'
- public_id: '_0.public_id'
+ file: $ steps[0].input.video_url
+ public_id: $ steps[0].input.public_id
upload_params:
- resource_type: "'video'"
+ resource_type: video
# Step #1 - Analyze the video content with a prompt
- prompt:
@@ -268,12 +269,12 @@ We're using three main integrations:
``
- type: image_url
image_url:
- url: "{{{{_.url}}}}"
+ url: $ _.url
- type: text
text: |-
- Hey, check the video above, I need to apply the following transformations using cloudinary.
- {{{{_0.transformation_prompt}}}}
+ $ f'''Hey, check the video above, I need to apply the following transformations using cloudinary.
+ {steps[0].input.transformation_prompt}'''
unwrap: true
settings:
@@ -281,20 +282,22 @@ We're using three main integrations:
# Step #2 - Extract the json from the model's response
- evaluate:
- model_transformation: load_json(_[_.find("```json")+7:][:_[_.find("```json")+7:].find("```")])
+ model_transformation: >-
+ $ load_json(
+ _[_.find("```json")+7:][:_[_.find("```json")+7:].find("```")])
# Step #3 - Upload the video to cloudinary
- tool: cloudinary_upload
arguments:
- file: '_0.video_url'
- public_id: '_0.public_id'
+ file: $ steps[0].input.video_url
+ public_id: $ steps[0].input.public_id
upload_params:
- transformation: '_.model_transformation'
- resource_type: "'video'"
+ transformation: $ _.model_transformation
+ resource_type: video
# Step #4 - Evaluate the transformed video url
- evaluate:
- transformed_video_url: '_.url'
+ transformed_video_url: $ _.url
```
diff --git a/documentation/mint.json b/documentation/mint.json
index 7e2f72c7e..99a7b5428 100644
--- a/documentation/mint.json
+++ b/documentation/mint.json
@@ -57,6 +57,10 @@
{
"name": "Support",
"url": "mailto:developers@julep.ai"
+ },
+ {
+ "name": "🚨 New Syntax Update",
+ "url": "/docs/advanced/new-syntax"
}
],
"topbarCtaButton": {
@@ -118,7 +122,7 @@
"group": "Tutorials",
"pages": [
"docs/tutorials/browser-use",
- "docs/tutorials/crawling-web-pages-with-rag",
+ "docs/tutorials/customer-support-rag",
"docs/tutorials/trip-planning",
"docs/tutorials/video-processing"
]
@@ -172,7 +176,8 @@
"docs/advanced/python-expression",
"docs/advanced/types-of-task-steps",
"docs/advanced/multi-agent-multi-user-sessions",
- "docs/advanced/files"
+ "docs/advanced/files",
+ "docs/advanced/new-syntax"
]
},
{