Seven months ago, our engineers said letting an AI approve pull requests was too risky. They were right, so we didn’t start there.

Instead, we built a bot for code reviews and capped it at 200-line PRs, watched every decision, and turned every mistake it made into a rule or a lint check. Then we raised the limit.

This talk covers that loop: small experiments, proof instead of promises, and a system that gets a little better every week.

You’ll leave with a playbook you can start on Monday, whatever tools your company gives you.