
#547: Parallel Python at Anyscale with Ray
May 6, 2026 - 59:16
Radio and PodcastLive Radio & Podcasts
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...
#543: Deep Agents: LangChain's SDK for Agents That Plan and Delegate is an episode from Talk Python To Me - Python conversations for passionate developers by Michael Kennedy. When you type a question into ChatGPT, the model only has what yo...
This episode belongs to Talk Python To Me - Python conversations for passionate developers.
Use the player on this page to stream the episode online.
Published Apr 1, 2026, 63:53 long, audio available.
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 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 deep-dive : talkpython.fm/543 Episode transcripts : talkpython.fm Theme Song: Developer Rap π₯ Served in a Flask πΈ : talkpython.fm/flasksong ---== Don't be a stranger ==--- YouTube : youtube.com/@talkpython Bluesky : @talkpython.fm Mastodon : @talkpython@fosstodon.org X.com : @talkpython Michael on Bluesky : @mkennedy.codes Michael on Mastodon : @mkennedy@fosstodon.org Michael on X.com : @mkennedy
You can listen to #543: Deep Agents: LangChain's SDK for Agents That Plan and Delegate online on Radio and Podcast. Open the player on this page to stream the available audio.
#543: Deep Agents: LangChain's SDK for Agents That Plan and Delegate is an episode from Talk Python To Me - Python conversations for passionate developers by Michael Kennedy.
This episode is 63:53 long.
This episode was published on Apr 1, 2026.
Yes. Use the heart button on the episode page to add it to your favorite episodes list.
Yes. This page shows related episodes from Talk Python To Me - Python conversations for passionate developers when more episodes are available from the podcast feed.
You can listen to #543: Deep Agents: LangChain's SDK for Agents That Plan and Delegate on this page when the episode audio is available from the podcast feed.
#543: Deep Agents: LangChain's SDK for Agents That Plan and Delegate is from Talk Python To Me - Python conversations for passionate developers by Michael Kennedy.
Published Apr 1, 2026 and 63:53 long