From Supervising AI to Building Systems for It

On Dan Gerlanc's Agents and Engineers Podcast

I joined Dan Gerlanc on the Agents and Engineers podcast for a conversation titled From Supervising AI to Building Systems for It.

It was really fun, and a genuinely interesting conversation. We talked about how my AI-assisted coding practice has changed over the last few months: less close supervision, more building systems that let agents do good work with the right context, guardrails, and verification.

We also covered async cloud-based agents, why deterministic checks matter so much, AGENTS.md and skills, test-driven workflows for agentic coding, language choices like TypeScript and Go, supply-chain concerns, and why software development increasingly feels like a branch of systems engineering.