#543: Deep Agents: LangChain's SDK for Agents That Plan and Delegate

#543: Deep Agents: LangChain's SDK for Agents That Plan and Delegate

From Talk Python To Me by Michael Kennedy

April 1, 2026 · 1h 4m · Episode 543

About this episode

Sydney Runkle discusses LangChain's new open source library, Deep Agents, which enables the creation of advanced AI agents.

When you type a question into ChatGPT, the model only has what you typed to work with. But tools like Claude Code can plan, iterate, test, and recover from mistakes. They work more like we do. The difference is the agent harness: Planning tools, file system access, sub-agents, and carefully crafted system prompts that turn a raw LLM into something genuinely capable. Sydney Runkle is back on Talk Python representing LangChain and their new open source library, Deep Agents: A framework for building your own deep agents with plain Python functions, middleware hooks, and MCP support. This is how the magic works under the hood.

People in this episode

Host: Michael Kennedy

Guest: Sydney Runkle

Topics covered

  • LangChain
  • Deep Agents
  • AI agents
  • planning tools
  • open source
  • Python

Keywords

  • LangChain
  • Deep Agents
  • AI
  • Python
  • Claude Code
  • ChatGPT
  • agents

Mentioned in this episode

Organizations: LangChain

Products: Deep Agents, Claude Code

Books & works: ChatGPT

More episodes of Talk Python To Me

Explore listener stats, chart rankings, contacts and more on the Talk Python To Me podcast page.