Agents that write and run code are powerful, as Cognition Labs showed with their recent release of Devin, the "AI SWE". But they are complex to program, hard to deploy, and even harder to secure -- what happens if your agent runs DROP prodtables or sudo rm -rf /?

In this joint webinar between LangChain and Modal Labs, we're covering the entire process. Lance will walk through his coding agent implementation, CodeLangChain, based on LangGraph. Modal AI Engineer Charles Frye will then show how to secure that prototype agent using Modal Sandboxes and then deploy it as a FastAPI web app with only a dozen more lines of code.

Expect a fun and lively technical conversation about making quality AI systems and running them in production!

Code Agents In Production Without All The Agonizing Pain