LangChain · Course
Introduction to Deep Agents
Introduction to Deep Agents teaches how to build long-running agents for complex workflows with Deep Agents, LangChain’s open-source agent harness, and how to use LangSmith to improve them.
Who it suits
- Developers building agents that run for a long time on complex tasks.
- Teams that want to understand what an agent harness is and how it speeds development.
What it covers
- Building a deep agent: models, the system prompt, tools, MCP, messages, threads, checkpointers and human in the loop.
- The execution environment: filesystem backends, sandboxes and an interpreter.
- Context management: summarisation and offload, skills and memory.
- Delegation: building a subagent team and dynamic and asynchronous subagents.
- A final project putting it together, including local deployment.
Watch here
From LangChain’s own channel, so you can start without leaving Infrato. Nothing loads from YouTube until you press play.
LangChain · 2026
Introduction to Deep Agents | LangChain Academy New Course
Common questions about Introduction to Deep Agents
- Is it free?
- LangChain Academy labels the course Free.
- How long is Introduction to Deep Agents?
- The course page lists its modules and lessons; check it for the length.
- Who runs it?
- LangChain Academy, run by the company behind LangChain, LangGraph and LangSmith.
More like this
Keep learning on Infrato
- Path: AI for software developers
- More from LangChain: all LangChain listings in the directory
- Explore all AI courses
Where this comes from
Written from LangChain’s own pages, read on 2026-10-13. Content, prices and availability change, so the provider’s page is the source. We are not affiliated with LangChain and this is not an endorsement.