technologyApr 1, 20261:03:53failed
#543: Deep Agents: LangChain's SDK for Agents That Plan and Delegate
About this episode
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.
Episode sponsors
Sentry Error Monitoring, Code talkpython26
Agentic AI Course
Talk Python Courses
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.
Episode sponsors
Sentry Error Monitoring, Code talkpython26
Agentic AI Course
Talk Python Courses
Links from the show
Guest
Sydney Runkle: github.com
Claude Code uses: x.com
Deep Research: openai.com
Manus: manus.im
Blog post announcement: blog.langchain.com
Claudes system prompt: github.com
sub agents: docs.anthropic.com
the quick start: docs.langchain.com
CLIs: github.com
Talk Python's CLI: talkpython.fm
custom tools: docs.langchain.com
DeepAgents Examples: github.com
Custom Middleware: docs.langchain.com
Built in middleware: docs.langchain.com
Improving Deep Agents with harness engineering: blog.langchain.com
Prebuilt middleware: docs.langchain.com
Watch this episode on YouTube: youtube.com
Episode #543 deep-dive: talkpython.fm/543
Episode transcripts: talkpython.fm
Theme Song: Developer Rap
🥁 Served in a Flask 🎸: talkpython.fm/flasksong
---== Don't be a stranger ==---
YouTube: youtube.com/@talkpython
Bluesky: @talkpython.fm
Mastodon: @[email protected]
X.com: @talkpython
Michael on Bluesky: @mkennedy.codes
Michael on Mastodon: @[email protected]
Michael on X.com: @mkennedy
Sydney Runkle: github.com
Claude Code uses: x.com
Deep Research: openai.com
Manus: manus.im
Blog post announcement: blog.langchain.com
Claudes system prompt: github.com
sub agents: docs.anthropic.com
the quick start: docs.langchain.com
CLIs: github.com
Talk Python's CLI: talkpython.fm
custom tools: docs.langchain.com
DeepAgents Examples: github.com
Custom Middleware: docs.langchain.com
Built in middleware: docs.langchain.com
Improving Deep Agents with harness engineering: blog.langchain.com
Prebuilt middleware: docs.langchain.com
Watch this episode on YouTube: youtube.com
Episode #543 deep-dive: talkpython.fm/543
Episode transcripts: talkpython.fm
Theme Song: Developer Rap
🥁 Served in a Flask 🎸: talkpython.fm/flasksong
---== Don't be a stranger ==---
YouTube: youtube.com/@talkpython
Bluesky: @talkpython.fm
Mastodon: @[email protected]
X.com: @talkpython
Michael on Bluesky: @mkennedy.codes
Michael on Mastodon: @[email protected]
Michael on X.com: @mkennedy
Get every episode summarized
Each time Talk Python To Me publishes, we email you a written briefing from the transcript — the topics, who appeared, and any specific claims, with the ad reads skipped.
Email me new episodesFree for 3 shows. No card needed.
Hosts & guests
No transcript yet
This episode has not been transcribed. Request it and it moves to the front of the queue.
More episodes
More from Talk Python To Me
#562: DuckLake: The Lakehouse That's Just SQL and Parquet
Talk Python To Me
Sep 10, 20261:11:09completed
#561: TonIO, a Multi-threaded Async Runtime for Python
Talk Python To Me
Sep 4, 20261:15:47completed
#560: Building a Research OS: From Django to 30,000 Samples
Talk Python To Me
Aug 26, 20261:02:49pending
#559: 12 Things You Should (and Shouldn't) Do in AWS
Talk Python To Me
Aug 19, 20261:07:51pending