Tutorials
Below are tutorials for common use cases, organized by framework.Managed Deep Agents
Managed Deep Agents is the recommended way to build and deploy deep agents. You write the agent; LangSmith runs the harness and runtime.Deep research
Build a multi-step web research agent with Managed Deep Agents or the Deep Agents SDK.
Content builder
Build a content writing agent with brand voice, skills, and image tools using Managed Deep Agents or the Deep Agents SDK.
Deep Agents
For maximum flexibility while using the same Deep Agents harness as Managed Deep Agents, use the Deep Agents SDK and host agents yourself, or run a custom LangSmith Deployment.Deep research
Build a multi-step web research agent with Managed Deep Agents or the Deep Agents SDK.
Content builder
Build a content writing agent with brand voice, skills, and image tools using Managed Deep Agents or the Deep Agents SDK.
Data analysis
Build a data analysis agent that sends reports to Slack with the Deep Agents SDK.
LangChain
LangChain agent implementations make it easy to get started for simple use cases.Semantic Search
Build a semantic search engine over a PDF with LangChain components.
RAG Agent
Create a Retrieval Augmented Generation (RAG) agent.
SQL Agent
Build a SQL agent to interact with databases with human-in-the-loop review.
Voice Agent
Build an agent you can speak and listen to.
LangGraph
LangChain’s agent implementations use LangGraph primitives. If deeper customization is required, agents can be implemented directly in LangGraph.Custom RAG Agent
Build a RAG agent using LangGraph primitives for fine-grained control.
Custom SQL Agent
Implement a SQL agent directly in LangGraph for maximum flexibility.
Multi-agent
These tutorials demonstrate multi-agent patterns, blending LangChain agents with LangGraph workflows.Subagents: Personal assistant
Build a personal assistant that delegates to sub-agents.
Handoffs: Customer support
Build a customer support workflow where a single agent transitions between different states.
Router: Knowledge base
Build a multi-source knowledge base that routes queries to specialized agents.
Skills: SQL assistant
Build an agent that loads specialized skills progressively using on-demand context loading.
Conceptual overviews
These guides explain the core concepts and APIs underlying LangChain and LangGraph.Memory
Understand persistence of interactions within and across threads.
Context engineering
Learn methods for providing AI applications the right information and tools to accomplish a task.
Graph API
Explore LangGraph’s declarative graph-building API.
Functional API
Build agents as a single function.
Additional resources
LangChain Academy
Courses and exercises to level up your LangChain skills.
Case Studies
See how teams are using LangChain and LangGraph in production.
Connect these docs to your agent of choice via MCP for real-time answers.