Privacy

Accept optional first-party analytics or decline. Functional journey and sound preferences stay on this device.

Read the privacy notice
WorkshopSeptember 26, 2026

AI writes code. You still own the failure.

A hands-on session on the gates that catch what code review misses when a model writes part of your code.

Three real bugs AI-assisted code handed me: a React hook after an early return, oversized chunks that silently wiped an index, and a reranker that died with an expired key. None of them were caught by reading the diff.

We look at what did catch them (lint rules, evaluation sets, circuit breakers, traces) and work out how to decide what to hand to a model and what to keep.

Conferences, meetups and internal engineering days are welcome. Invite me through the contact page.