AI lets us move faster and decide more, but our brains and bodies haven't kept pace. David looks at what research says about mental fatigue and recovery, and why movement, nature, and intentional downtime aren't just good for your health — they're how you get your focus back.

I trained a model to count bullet holes in his shooting targets and found the model was the easy part. A tour of React Native's two on-device AI stacks, and what to do when the heavy work lands on the JS thread.

Everyone wants end-to-end tests, nobody wants to maintain them — the real cost isn't typing the test, it's knowing what to assert and keeping it alive as the UI shifts every sprint. Martin hands both jobs to an AI agent live on stage: exploring the app, generating Playwright tests in a real browser, and repairing them after he deliberately breaks the UI. The second half drops the demo and measures instead — four setups, one real product, and an analysis plan written before the first run.

Three documents that are actually worth the effort: a C4 diagram that onboards a new teammate without a walkthrough, an ADR that locks in the context behind a decision, and an RFC that lets people review a proposal on their own time. Petr covers when each one applies and shares the agent skills he uses to write them.