{"id":325281,"date":"2025-11-30T23:52:30","date_gmt":"2025-11-30T23:52:30","guid":{"rendered":"https:\/\/peraltafinancing.com\/analytics\/deep-agents-tutorial-langgraph-for-smarter-ai\/"},"modified":"2025-11-30T23:52:30","modified_gmt":"2025-11-30T23:52:30","slug":"deep-agents-tutorial-langgraph-for-smarter-ai","status":"publish","type":"post","link":"https:\/\/fivemor.com\/?p=325281","title":{"rendered":"Deep Agents Tutorial: LangGraph for Smarter AI"},"content":{"rendered":"<p> <br \/>\n<\/p>\n<div id=\"article-start\">\n<p>Imagine an AI that doesn\u2019t just answer your questions, but thinks ahead, breaks tasks down, creates its own TODOs, and even spawns sub-agents to get the work done. That\u2019s the promise of Deep Agents. AI Agents already take the capabilities of <a href=\"https:\/\/www.analyticsvidhya.com\/blog\/2023\/03\/an-introduction-to-large-language-models-llms\/\" target=\"_blank\" rel=\"noreferrer noopener\">LLMs<\/a> a notch higher, and today we\u2019ll look at Deep Agents to see how they can push that notch even further. Deep Agents is built on top of <a href=\"https:\/\/www.analyticsvidhya.com\/blog\/2024\/07\/langgraph-revolutionizing-ai-agent\/\" target=\"_blank\" rel=\"noreferrer noopener\">LangGraph<\/a>, a library designed specifically to create agents capable of handling complex tasks. Let\u2019s take a deeper look at Deep Agents, understand their core capabilities, and then use the library to build our own AI agents.<\/p>\n<h2 class=\"wp-block-heading\" id=\"h-deep-agents-nbsp\">Deep Agents\u00a0<\/h2>\n<p>LangGraph gives you a graph-based runtime for stateful workflows, but you still need to build your own planning, context management, or task-decomposition logic from scratch. DeepAgents (built on top of LangGraph) bundles planning tools, virtual file-system based memory and subagent orchestration out of the box.\u00a0\u00a0<\/p>\n<p>You can use DeepAgents via the standalone\u00a0<code>deepagents<\/code>\u00a0library. It includes planning capabilities, can spawn sub-agents, and uses a filesystem for context management. It can also be paired with <a href=\"https:\/\/www.analyticsvidhya.com\/blog\/2024\/07\/ultimate-langsmith-guide\/\" target=\"_blank\" rel=\"noreferrer noopener\">LangSmith<\/a> for deployment and monitoring. The agents built here use the \u201cclaude-sonnet-4-5-20250929\u201d model by default, but this can be customized. Before we start creating the agents, let\u2019s understand the core components.<\/p>\n<h2 class=\"wp-block-heading\" id=\"h-core-components\">Core Components<\/h2>\n<ul class=\"wp-block-list\">\n<li><strong>Detailed System Prompts<\/strong> \u2013 The Deep agent uses a system prompt with detailed instructions and examples.\u00a0\u00a0<\/li>\n<li><strong>Planning Tools<\/strong> \u2013 Deep agents have a built-in tool for Planning, the TODO list management tool is used by the agents for the same. This helps them stay focused even while performing a complex task.\u00a0\u00a0<\/li>\n<li><strong>Sub-Agents<\/strong> \u2013 Subagent spawns for the delegated tasks and they execute in context isolation.\u00a0<\/li>\n<li><strong>File System<\/strong> \u2013 Virtual filesystem for context management and memory management, AI Agents here use files as a tool to offload context to memory when the context window is full.\u00a0<\/li>\n<\/ul>\n<h2 class=\"wp-block-heading\" id=\"h-building-a-deep-agent-nbsp\">Building a Deep Agent\u00a0<\/h2>\n<p>Now let\u2019s build a research agent using the \u2018deepagents\u2019 library which will use tavily for websearch and it\u2019ll have all the components of a deep agent.\u00a0<\/p>\n<p><strong>Note: <\/strong>We\u2019ll be doing the tutorial in Google Colab.\u00a0\u00a0<\/p>\n<h3 class=\"wp-block-heading\" id=\"h-pre-requisites-nbsp\">Pre-requisites\u00a0<\/h3>\n<p>You\u2019ll need an OpenAI key for this agent that we\u2019ll be creating, you can choose to use a different model provider like Gemini\/Claude as well. Get your OpenAI key from the platform:\u00a0https:\/\/platform.openai.com\/api-keys <\/p>\n<p>Also get a Tavily API key for websearch from here:\u00a0https:\/\/app.tavily.com\/home<\/p>\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-full is-resized\"><img loading=\"lazy\" decoding=\"async\" width=\"624\" height=\"140\" src=\"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/11\/API-Key-for-Deep-Agents.webp\" alt=\"Tavily API key\" class=\"wp-image-247064\" style=\"width:731px;height:auto\" srcset=\"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/11\/API-Key-for-Deep-Agents.webp 624w, https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/11\/API-Key-for-Deep-Agents-300x67.webp 300w, https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/11\/API-Key-for-Deep-Agents-150x34.webp 150w\" sizes=\"auto, (max-width: 624px) 100vw, 624px\"\/><\/figure>\n<\/div>\n<p>Open a new notebook in Google Colab and add the secret keys:\u00a0<\/p>\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"624\" height=\"460\" src=\"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/11\/Enter-your-secret-keys.webp\" alt=\"Enter your secret key\" class=\"wp-image-247065\" srcset=\"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/11\/Enter-your-secret-keys.webp 624w, https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/11\/Enter-your-secret-keys-300x221.webp 300w, https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/11\/Enter-your-secret-keys-150x111.webp 150w\" sizes=\"auto, (max-width: 624px) 100vw, 624px\"\/><\/figure>\n<\/div>\n<p>Save the keys as OPENAI_API_KEY, TAVILY_API_KEY for the demo and don\u2019t forget to turn on the notebook access.\u00a0\u00a0<\/p>\n<p>Also Read: <a href=\"https:\/\/www.analyticsvidhya.com\/blog\/2025\/11\/gemini-api-file-search\/\" target=\"_blank\" rel=\"noreferrer noopener\">Gemini API File Search: The Easy Way to Build RAG<\/a><\/p>\n<h3 class=\"wp-block-heading\" id=\"h-requirements-nbsp\">Requirements\u00a0<\/h3>\n<pre class=\"wp-block-code\"><code>!pip install deepagents tavily-python langchain-openai\u00a0<\/code><\/pre>\n<p>We\u2019ll install these libraries needed to run the code.\u00a0\u00a0<\/p>\n<h3 class=\"wp-block-heading\" id=\"h-imports-and-api-setup-nbsp\">Imports and API Setup\u00a0<\/h3>\n<pre class=\"wp-block-code\"><code>import os \nfrom deepagents import create_deep_agent \nfrom tavily import TavilyClient \nfrom langchain.chat_models import init_chat_model \nfrom google.colab import userdata \n \n\n# Set API keys \nTAVILY_API_KEY=userdata.get(\"TAVILY_API_KEY\") \nos.environ[\"OPENAI_API_KEY\"]=userdata.get(\"OPENAI_API_KEY\") <\/code><\/pre>\n<p>We are storing the Tavily API in a variable and the OpenAI API in the environment.\u00a0<\/p>\n<h3 class=\"wp-block-heading\" id=\"h-defining-the-tools-sub-agent-and-the-agent-nbsp\">Defining the Tools, Sub-Agent and the Agent\u00a0<\/h3>\n<pre class=\"wp-block-code\"><code># Initialize Tavily client \ntavily_client = TavilyClient(api_key=TAVILY_API_KEY) \n \n# Define web search tool \ndef internet_search(query: str, max_results: int = 5) -&gt; str: \n   \"\"\"Run a web search to find current information\"\"\" \n   results = tavily_client.search(query, max_results=max_results) \n   return results  \n\n# Define a specialized research sub-agent \nresearch_subagent = { \n   \"name\": \"data-analyzer\", \n   \"description\": \"Specialized agent for analyzing data and creating detailed reports\", \n   \"system_prompt\": \"\"\"You are an expert data analyst and report writer. \n   Analyze information thoroughly and create well-structured, detailed reports.\"\"\", \n   \"tools\": [internet_search], \n   \"model\": \"openai:gpt-4o\", \n}  \n\n# Initialize GPT-4o-mini model \nmodel = init_chat_model(\"openai:gpt-4o-mini\") \n# Create the deep agent \n# The agent automatically has access to: write_todos, read_todos, ls, read_file, \n# write_file, edit_file, glob, grep, and task (for subagents) \nagent = create_deep_agent( \n   model=model, \n   tools=[internet_search],  # Passing the tool \n   system_prompt=\"\"\"You are a thorough research assistant. For this task: \n   1. Use write_todos to create a task list breaking down the research \n   2. Use internet_search to gather current information \n   3. Use write_file to save your findings to \/research_findings.md \n   4. You can delegate detailed analysis to the data-analyzer subagent using the task tool \n   5. Create a final comprehensive report and save it to \/final_report.md \n   6. Use read_todos to check your progress \n\n   Be systematic and thorough in your research.\"\"\", \n   subagents=[research_subagent], \n) <\/code><\/pre>\n<p>We have defined a tool for websearch and passed the same to our agent. We\u2019re using OpenAI\u2019s \u2018gpt-4o-mini\u2019 for this demo. You can change this to any model.\u00a0\u00a0<\/p>\n<p>Also note that we didn\u2019t create any files or define anything for the file system needed for offloading context and the todo list. These are already pre-built in \u2018create_deep_agent()\u2019 and it has access to them.\u00a0\u00a0<\/p>\n<h3 class=\"wp-block-heading\" id=\"h-running-inference-nbsp\">Running Inference\u00a0<\/h3>\n<pre class=\"wp-block-code\"><code># Research query \nresearch_topic = \"What are the latest developments in AI agents and LangGraph in 2025?\"  \n\nprint(f\"Starting research on: {research_topic}\\n\") \nprint(\"=\" * 70)  \n\n# Execute the agent \nresult = agent.invoke({ \n   \"messages\": [{\"role\": \"user\", \"content\": research_topic}] \n}) \n\nprint(\"\\n\" + \"=\" * 70) \nprint(\"Research completed.\\n\") <\/code><\/pre>\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-full is-resized\"><img loading=\"lazy\" decoding=\"async\" width=\"624\" height=\"96\" src=\"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/11\/Deep-Agents-Output.webp\" alt=\"Deep Agents Output\" class=\"wp-image-247069\" style=\"width:840px;height:auto\" srcset=\"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/11\/Deep-Agents-Output.webp 624w, https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/11\/Deep-Agents-Output-300x46.webp 300w, https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/11\/Deep-Agents-Output-150x23.webp 150w\" sizes=\"auto, (max-width: 624px) 100vw, 624px\"\/><\/figure>\n<\/div>\n<p><strong>Note: <\/strong>The agent execution might take a while.\u00a0\u00a0<\/p>\n<h3 class=\"wp-block-heading\" id=\"h-viewing-the-output\">Viewing the Output<\/h3>\n<pre class=\"wp-block-code\"><code># Agent execution trace \nprint(\"AGENT EXECUTION TRACE:\") \nprint(\"-\" * 70) \nfor i, msg in enumerate(result[\"messages\"]): \n   if hasattr(msg, 'type'): \n       print(f\"\\n[{i}] Type: {msg.type}\") \n       if msg.type == \"human\": \n           print(f\"Human: {msg.content}\") \n       elif msg.type == \"ai\": \n           if hasattr(msg, 'tool_calls') and msg.tool_calls: \n               print(f\"AI tool calls: {[tc['name'] for tc in msg.tool_calls]}\") \n           if msg.content: \n               print(f\"AI: {msg.content[:200]}...\") \n       elif msg.type == \"tool\": \n           print(f\"Tool '{msg.name}' result: {str(msg.content)[:200]}...\") <\/code><\/pre>\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"624\" height=\"527\" src=\"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/11\/viewing-the-output.webp\" alt=\"Viewing the Output\" class=\"wp-image-247071\" srcset=\"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/11\/viewing-the-output.webp 624w, https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/11\/viewing-the-output-300x253.webp 300w, https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/11\/viewing-the-output-150x127.webp 150w\" sizes=\"auto, (max-width: 624px) 100vw, 624px\"\/><\/figure>\n<\/div>\n<pre class=\"wp-block-code\"><code># Final AI response \nprint(\"\\n\" + \"=\" * 70) \nfinal_message = result[\"messages\"][-1] \nprint(\"FINAL RESPONSE:\") \nprint(\"-\" * 70) \nprint(final_message.content) <\/code><\/pre>\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"624\" height=\"456\" src=\"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/11\/Deep-Agents-Output-2.webp\" alt=\"Deep Agents Output 2\" class=\"wp-image-247075\" srcset=\"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/11\/Deep-Agents-Output-2.webp 624w, https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/11\/Deep-Agents-Output-2-300x219.webp 300w, https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/11\/Deep-Agents-Output-2-150x110.webp 150w\" sizes=\"auto, (max-width: 624px) 100vw, 624px\"\/><\/figure>\n<\/div>\n<pre class=\"wp-block-code\"><code># Files created \nprint(\"\\n\" + \"=\" * 70) \nprint(\"FILES CREATED:\") \nprint(\"-\" * 70) \nif \"files\" in result and result[\"files\"]: \n   for filepath in sorted(result[\"files\"].keys()): \n       content = result[\"files\"][filepath] \n       print(f\"\\n{'=' * 70}\") \n       print(f\"{filepath}\") \n       print(f\"{'=' * 70}\") \n       print(content) \nelse: \n   print(\"No files found.\") \n\nprint(\"\\n\" + \"=\" * 70) \nprint(\"Analysis complete.\") <\/code><\/pre>\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-full is-resized\"><img loading=\"lazy\" decoding=\"async\" width=\"624\" height=\"227\" src=\"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/11\/Deep-Agents-Output-3.webp\" alt=\"Deep Agents Output 3\" class=\"wp-image-247076\" style=\"width:816px;height:auto\" srcset=\"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/11\/Deep-Agents-Output-3.webp 624w, https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/11\/Deep-Agents-Output-3-300x109.webp 300w, https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/11\/Deep-Agents-Output-3-150x55.webp 150w\" sizes=\"auto, (max-width: 624px) 100vw, 624px\"\/><\/figure>\n<\/div>\n<p>As we can see the agent did a good job, it maintained a virtual file system, gave a response after multiple iterations and thought it should be a \u2018deep-agent\u2019. But there is scope for improvement in our system, let\u2019s look at them in the next system.\u00a0\u00a0<\/p>\n<h2 class=\"wp-block-heading\" id=\"h-potential-improvements-in-our-agent-nbsp\">Potential Improvements in our Agent\u00a0<\/h2>\n<p>We built a simple deep agent, but you can challenge yourself and build something much better. Here are few things you can do to improve this agent:\u00a0<\/p>\n<ol start=\"1\" class=\"wp-block-list\">\n<li><strong>Use Long-term Memory<\/strong> \u2013 The deep-agent can preserve user preferences and feedback in files (\/memories\/). This will help the agent give better answers and build a knowledge base from the conversations.\u00a0<\/li>\n<li><strong>Control File-system<\/strong> \u2013 By default the files are stored in a virtual state, you can this to different backend or local disk using the \u2018FilesystemBackend\u2019 from deepagents.backends\u00a0<\/li>\n<li><strong>By refining the system prompts<\/strong> \u2013 You can test out multiple prompts to see which works the best for you.\u00a0<\/li>\n<\/ol>\n<h2 class=\"wp-block-heading\" id=\"h-conclusion-nbsp\">Conclusion\u00a0<\/h2>\n<p>We have successfully built our Deep Agents and can now see how <a href=\"https:\/\/www.analyticsvidhya.com\/blog\/2024\/10\/what-are-ai-agents\/\" target=\"_blank\" rel=\"noreferrer noopener\">AI Agents<\/a> can push LLM capabilities a notch higher, using LangGraph to handle the tasks. With built-in planning, sub-agents, and a virtual file system, they manage TODOs, context, and research workflows smoothly. Deep Agents are great but also remember that if a task is simpler and can be achieved by a simple agent or LLM then it\u2019s not recommended to use them.\u00a0\u00a0<\/p>\n<h2 class=\"wp-block-heading\" id=\"h-frequently-asked-questions\">Frequently Asked Questions<\/h2>\n<div class=\"schema-faq wp-block-yoast-faq-block\">\n<div class=\"schema-faq-section\" id=\"faq-question-1764498377918\"><strong class=\"schema-faq-question\">Q1. Can I use an alternative to Tavily for web search?\u00a0<\/strong> <\/p>\n<p class=\"schema-faq-answer\">A. Yes. Instead of Tavily, you can integrate SerpAPI, Firecrawl, Bing Search, or any other web search API. Simply replace the search function and tool definition to match the new provider\u2019s response format and authentication method.\u00a0<\/p>\n<\/p><\/div>\n<div class=\"schema-faq-section\" id=\"faq-question-1764500156925\"><strong class=\"schema-faq-question\">Q2. Can I change the default model used by the deep agent?\u00a0<\/strong> <\/p>\n<p class=\"schema-faq-answer\">A. Absolutely. Deep Agents are model-agnostic, so you can switch to Claude, Gemini, or other OpenAI models by modifying the model parameter. This flexibility ensures you can optimize performance, cost, or latency depending on your use case.\u00a0<\/p>\n<\/p><\/div>\n<div class=\"schema-faq-section\" id=\"faq-question-1764500180533\"><strong class=\"schema-faq-question\">Q3. Do I need to manually set up the filesystem?\u00a0<\/strong> <\/p>\n<p class=\"schema-faq-answer\">A. No. Deep Agents automatically provide a virtual filesystem for managing memory, files, and long contexts. This eliminates the need for manual setup, although you can configure custom storage backends if required.\u00a0<\/p>\n<\/p><\/div>\n<div class=\"schema-faq-section\" id=\"faq-question-1764500195268\"><strong class=\"schema-faq-question\">Q4. Can I add more specialized sub-agents?\u00a0<\/strong> <\/p>\n<p class=\"schema-faq-answer\">A. Yes. You can create multiple sub-agents, each with its own tools, system prompts, and capabilities. This allows the main agent to delegate work more effectively and handle complex workflows through modular, distributed reasoning.\u00a0<\/p>\n<\/p><\/div>\n<\/p><\/div>\n<div class=\"border-top py-3 author-info my-4\">\n<div class=\"author-card d-flex align-items-center\">\n<div class=\"flex-shrink-0 overflow-hidden\">\n                                    <a href=\"https:\/\/www.analyticsvidhya.com\/blog\/author\/mounish12439\/\" class=\"text-decoration-none active-avatar\"><br \/>\n                                                                       <img decoding=\"async\" src=\"https:\/\/av-eks-lekhak.s3.amazonaws.com\/media\/lekhak-profile-images\/converted_image_ZFxQ96b.webp\" width=\"48\" height=\"48\" alt=\"Mounish V\" loading=\"lazy\" class=\"rounded-circle\"\/><\/p>\n<p>                                <\/a>\n                                <\/div>\n<\/p><\/div>\n<p>Passionate about technology and innovation, a graduate of Vellore Institute of Technology. Currently working as a Data Science Trainee, focusing on Data Science. Deeply interested in Deep Learning and Generative AI, eager to explore cutting-edge techniques to solve complex problems and create impactful solutions.<\/p>\n<\/p><\/div>\n<\/p><\/div>\n<p><h4 class=\"fs-24 text-dark\">Login to continue reading and enjoy expert-curated content.<\/h4>\n<p>                        <button class=\"btn btn-primary mx-auto d-table\" data-bs-toggle=\"modal\" data-bs-target=\"#loginModal\" id=\"readMoreBtn\">Keep Reading for Free<\/button>\n                    <\/p>\n\n","protected":false},"excerpt":{"rendered":"<p>Imagine an AI that doesn\u2019t just answer your questions, but thinks ahead, breaks tasks down, creates its own TODOs, and even spawns sub-agents to get the work done. That\u2019s the promise of Deep Agents. AI Agents already take the capabilities of LLMs a notch higher, and today we\u2019ll look at Deep Agents to see how [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":325282,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[12033],"tags":[11530,1636,31128,11137,13955],"dealstore":[],"offerexpiration":[],"class_list":["post-325281","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-analytics","tag-agents","tag-deep","tag-langgraph","tag-smarter","tag-tutorial"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v26.4 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Deep Agents Tutorial: LangGraph for Smarter AI - Som2ny Network<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/fivemor.com\/?p=325281\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Deep Agents Tutorial: LangGraph for Smarter AI - Som2ny Network\" \/>\n<meta property=\"og:description\" content=\"Imagine an AI that doesn\u2019t just answer your questions, but thinks ahead, breaks tasks down, creates its own TODOs, and even spawns sub-agents to get the work done. That\u2019s the promise of Deep Agents. AI Agents already take the capabilities of LLMs a notch higher, and today we\u2019ll look at Deep Agents to see how [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/fivemor.com\/?p=325281\" \/>\n<meta property=\"og:site_name\" content=\"Som2ny Network\" \/>\n<meta property=\"article:published_time\" content=\"2025-11-30T23:52:30+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/11\/Deep-Agents-Tutorial-Create-Advanced-AI-Agents-with-LangGraph-and-Web-Search-Tools-.png\" \/>\n\t<meta property=\"og:image:width\" content=\"872\" \/>\n\t<meta property=\"og:image:height\" content=\"473\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"admin\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"admin\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"8 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/fivemor.com\/?p=325281#article\",\"isPartOf\":{\"@id\":\"https:\/\/fivemor.com\/?p=325281\"},\"author\":{\"name\":\"admin\",\"@id\":\"https:\/\/fivemor.com\/#\/schema\/person\/b85e3c3dc0e1daea076524dc8810c371\"},\"headline\":\"Deep Agents Tutorial: LangGraph for Smarter AI\",\"datePublished\":\"2025-11-30T23:52:30+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/fivemor.com\/?p=325281\"},\"wordCount\":1055,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\/\/fivemor.com\/#organization\"},\"image\":{\"@id\":\"https:\/\/fivemor.com\/?p=325281#primaryimage\"},\"thumbnailUrl\":\"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/11\/Deep-Agents-Tutorial-Create-Advanced-AI-Agents-with-LangGraph-and-Web-Search-Tools-.png\",\"keywords\":[\"agents\",\"Deep\",\"LangGraph\",\"smarter\",\"Tutorial\"],\"articleSection\":[\"Analytics\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\/\/fivemor.com\/?p=325281#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/fivemor.com\/?p=325281\",\"url\":\"https:\/\/fivemor.com\/?p=325281\",\"name\":\"Deep Agents Tutorial: LangGraph for Smarter AI - Som2ny Network\",\"isPartOf\":{\"@id\":\"https:\/\/fivemor.com\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/fivemor.com\/?p=325281#primaryimage\"},\"image\":{\"@id\":\"https:\/\/fivemor.com\/?p=325281#primaryimage\"},\"thumbnailUrl\":\"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/11\/Deep-Agents-Tutorial-Create-Advanced-AI-Agents-with-LangGraph-and-Web-Search-Tools-.png\",\"datePublished\":\"2025-11-30T23:52:30+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/fivemor.com\/?p=325281#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/fivemor.com\/?p=325281\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/fivemor.com\/?p=325281#primaryimage\",\"url\":\"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/11\/Deep-Agents-Tutorial-Create-Advanced-AI-Agents-with-LangGraph-and-Web-Search-Tools-.png\",\"contentUrl\":\"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/11\/Deep-Agents-Tutorial-Create-Advanced-AI-Agents-with-LangGraph-and-Web-Search-Tools-.png\",\"width\":872,\"height\":473},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/fivemor.com\/?p=325281#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/fivemor.com\/?bp_activities=1\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Deep Agents Tutorial: LangGraph for Smarter AI\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/fivemor.com\/#website\",\"url\":\"https:\/\/fivemor.com\/\",\"name\":\"Som2ny Network\",\"description\":\"Daily Deals\",\"publisher\":{\"@id\":\"https:\/\/fivemor.com\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/fivemor.com\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/fivemor.com\/#organization\",\"name\":\"Som2ny Network\",\"url\":\"https:\/\/fivemor.com\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/fivemor.com\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/fivemor.com\/wp-content\/uploads\/2026\/07\/4a0953c4-logo-300x86-1.png\",\"contentUrl\":\"https:\/\/fivemor.com\/wp-content\/uploads\/2026\/07\/4a0953c4-logo-300x86-1.png\",\"width\":300,\"height\":86,\"caption\":\"Som2ny Network\"},\"image\":{\"@id\":\"https:\/\/fivemor.com\/#\/schema\/logo\/image\/\"}},{\"@type\":\"Person\",\"@id\":\"https:\/\/fivemor.com\/#\/schema\/person\/b85e3c3dc0e1daea076524dc8810c371\",\"name\":\"admin\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/fivemor.com\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/729ae85bf62b9917e93538db2f2688ca?s=96&r=g&default=https%3A%2F%2Ffivemor.com%2Fwp-content%2Fplugins%2Fbuddypress-first-letter-avatar%2Fimages%2Fdefault%2F96%2Flatin_a.png\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/729ae85bf62b9917e93538db2f2688ca?s=96&r=g&default=https%3A%2F%2Ffivemor.com%2Fwp-content%2Fplugins%2Fbuddypress-first-letter-avatar%2Fimages%2Fdefault%2F96%2Flatin_a.png\",\"caption\":\"admin\"},\"sameAs\":[\"https:\/\/fivemor.com\"],\"url\":\"https:\/\/fivemor.com\/?author=1\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Deep Agents Tutorial: LangGraph for Smarter AI - Som2ny Network","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/fivemor.com\/?p=325281","og_locale":"en_US","og_type":"article","og_title":"Deep Agents Tutorial: LangGraph for Smarter AI - Som2ny Network","og_description":"Imagine an AI that doesn\u2019t just answer your questions, but thinks ahead, breaks tasks down, creates its own TODOs, and even spawns sub-agents to get the work done. That\u2019s the promise of Deep Agents. AI Agents already take the capabilities of LLMs a notch higher, and today we\u2019ll look at Deep Agents to see how [&hellip;]","og_url":"https:\/\/fivemor.com\/?p=325281","og_site_name":"Som2ny Network","article_published_time":"2025-11-30T23:52:30+00:00","og_image":[{"width":872,"height":473,"url":"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/11\/Deep-Agents-Tutorial-Create-Advanced-AI-Agents-with-LangGraph-and-Web-Search-Tools-.png","type":"image\/png"}],"author":"admin","twitter_card":"summary_large_image","twitter_misc":{"Written by":"admin","Est. reading time":"8 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/fivemor.com\/?p=325281#article","isPartOf":{"@id":"https:\/\/fivemor.com\/?p=325281"},"author":{"name":"admin","@id":"https:\/\/fivemor.com\/#\/schema\/person\/b85e3c3dc0e1daea076524dc8810c371"},"headline":"Deep Agents Tutorial: LangGraph for Smarter AI","datePublished":"2025-11-30T23:52:30+00:00","mainEntityOfPage":{"@id":"https:\/\/fivemor.com\/?p=325281"},"wordCount":1055,"commentCount":0,"publisher":{"@id":"https:\/\/fivemor.com\/#organization"},"image":{"@id":"https:\/\/fivemor.com\/?p=325281#primaryimage"},"thumbnailUrl":"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/11\/Deep-Agents-Tutorial-Create-Advanced-AI-Agents-with-LangGraph-and-Web-Search-Tools-.png","keywords":["agents","Deep","LangGraph","smarter","Tutorial"],"articleSection":["Analytics"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/fivemor.com\/?p=325281#respond"]}]},{"@type":"WebPage","@id":"https:\/\/fivemor.com\/?p=325281","url":"https:\/\/fivemor.com\/?p=325281","name":"Deep Agents Tutorial: LangGraph for Smarter AI - Som2ny Network","isPartOf":{"@id":"https:\/\/fivemor.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/fivemor.com\/?p=325281#primaryimage"},"image":{"@id":"https:\/\/fivemor.com\/?p=325281#primaryimage"},"thumbnailUrl":"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/11\/Deep-Agents-Tutorial-Create-Advanced-AI-Agents-with-LangGraph-and-Web-Search-Tools-.png","datePublished":"2025-11-30T23:52:30+00:00","breadcrumb":{"@id":"https:\/\/fivemor.com\/?p=325281#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/fivemor.com\/?p=325281"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/fivemor.com\/?p=325281#primaryimage","url":"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/11\/Deep-Agents-Tutorial-Create-Advanced-AI-Agents-with-LangGraph-and-Web-Search-Tools-.png","contentUrl":"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/11\/Deep-Agents-Tutorial-Create-Advanced-AI-Agents-with-LangGraph-and-Web-Search-Tools-.png","width":872,"height":473},{"@type":"BreadcrumbList","@id":"https:\/\/fivemor.com\/?p=325281#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/fivemor.com\/?bp_activities=1"},{"@type":"ListItem","position":2,"name":"Deep Agents Tutorial: LangGraph for Smarter AI"}]},{"@type":"WebSite","@id":"https:\/\/fivemor.com\/#website","url":"https:\/\/fivemor.com\/","name":"Som2ny Network","description":"Daily Deals","publisher":{"@id":"https:\/\/fivemor.com\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/fivemor.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/fivemor.com\/#organization","name":"Som2ny Network","url":"https:\/\/fivemor.com\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/fivemor.com\/#\/schema\/logo\/image\/","url":"https:\/\/fivemor.com\/wp-content\/uploads\/2026\/07\/4a0953c4-logo-300x86-1.png","contentUrl":"https:\/\/fivemor.com\/wp-content\/uploads\/2026\/07\/4a0953c4-logo-300x86-1.png","width":300,"height":86,"caption":"Som2ny Network"},"image":{"@id":"https:\/\/fivemor.com\/#\/schema\/logo\/image\/"}},{"@type":"Person","@id":"https:\/\/fivemor.com\/#\/schema\/person\/b85e3c3dc0e1daea076524dc8810c371","name":"admin","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/fivemor.com\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/729ae85bf62b9917e93538db2f2688ca?s=96&r=g&default=https%3A%2F%2Ffivemor.com%2Fwp-content%2Fplugins%2Fbuddypress-first-letter-avatar%2Fimages%2Fdefault%2F96%2Flatin_a.png","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/729ae85bf62b9917e93538db2f2688ca?s=96&r=g&default=https%3A%2F%2Ffivemor.com%2Fwp-content%2Fplugins%2Fbuddypress-first-letter-avatar%2Fimages%2Fdefault%2F96%2Flatin_a.png","caption":"admin"},"sameAs":["https:\/\/fivemor.com"],"url":"https:\/\/fivemor.com\/?author=1"}]}},"_links":{"self":[{"href":"https:\/\/fivemor.com\/index.php?rest_route=\/wp\/v2\/posts\/325281","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/fivemor.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/fivemor.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/fivemor.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/fivemor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=325281"}],"version-history":[{"count":0,"href":"https:\/\/fivemor.com\/index.php?rest_route=\/wp\/v2\/posts\/325281\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/fivemor.com\/index.php?rest_route=\/wp\/v2\/media\/325282"}],"wp:attachment":[{"href":"https:\/\/fivemor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=325281"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/fivemor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=325281"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/fivemor.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=325281"},{"taxonomy":"dealstore","embeddable":true,"href":"https:\/\/fivemor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fdealstore&post=325281"},{"taxonomy":"offerexpiration","embeddable":true,"href":"https:\/\/fivemor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fofferexpiration&post=325281"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}