Show Us Your (Agent) Skills Ep 8

​What are people at the top of the game building with AI agents, and how are they doing it?

​Are they Claudemaxxing with eight terminals open at once? Are they adversarially testing agent-generated code with Codex? Do they define suites and swarms of sub-agents, or rely on AGENTS.md and agent skills?

​What do they love about building with agents? What do they hate? Which workflows, prompts, scripts, tools, and review loops have survived contact with real work?

​Thomas Wiecki (PyMC Labs) and Hugo Bowne-Anderson (Vanishing Gradients) are on a mission to find out. Think Excel World Championships meets Eurovision.

​In Episode 8, Chip Huyen and Tim Hopper join us to show how they work with agents.

​Chip is a writer and computer scientist focused on bringing AI into production. She taught Machine Learning Systems Design at Stanford, founded and sold an AI infrastructure company, and wrote Designing Machine Learning Systems and AI Engineering, the most-read book on the O'Reilly platform in 2025.

​Tim is a machine learning platform engineer and Python developer who has spent more than a decade helping teams shorten feedback loops across machine learning, developer tooling, and production systems. He writes about AI-assisted development, Python tooling, and the systems that let researchers and data scientists spend less time fighting infrastructure.

​Register to join live or get the recording afterwards.