AI

I stopped treating AI as one chat window and started treating it like a small team, with lanes, handoffs and a review gate. Here's how that works day to day, and what still needs me.

Storyblok billed us thousands in breach fees. We moved our sites off it in hours. AI made exit cheap. Lock-in is a worse bet than looking after customers.

We got hooked on social media. AI might hook us even deeper, by doing things for us rather than showing us things. So what happens to human consciousness when the line between us and the machine starts to blur?

We now generate code faster than we can reliably review it. Practical principles for reviewing AI-generated pull requests without slowing your team down.