Talk
Controlling the wild: from tool calling to computer use
There's a continuum from traditional tool calling through to full computer use, with interesting options at every point along it. This talk is about one particular answer: Monty, a sandboxed Python interpreter built for AI agents. Come watch my code fail in microseconds.
About
Samuel Colvin is the creator of Pydantic, the most widely used data validation library in Python. Pydantic has become essential infrastructure for modern Python development, powering frameworks like FastAPI and used by companies worldwide for building robust APIs and AI applications. Samuel is also the founder and CEO of Pydantic Services, where he leads the development of Pydantic, PydanticAI, and Logfire. He is passionate about developer experience and building tools that make Python development faster and more reliable.