The AI-in-production safety playbook
Fourteen posts of being wrong in production, compressed to checkboxes
The agent is running in *your* shell
A surprising share of AI-in-the-terminal failures aren't the AI. They're zsh, and a version of bash from 2006.
The scaffolding that made it safe
None of the safety came from the model. It came from six boring habits.
Those are the other app's keys
Twenty minutes recovering secrets that never existed, and the one sentence from a human that ended it
The coverage audit before you delete the safety net
31 config keys, two audits, and why the first one was wrong in both directions
Rotating a leaked credential, in the right order
Everyone looks at the Dockerfile. The file that actually leaked the key was the project file.
Never let the AI print a secret
The most important rule wasn't about what I could change. It was about what I was allowed to display.
What counts as proof
"Verify your work" isn't an instruction. It's a mood. Here's the version that's an instruction. Verify with a different mechanism than the one that made the claim.
The deploy that merged but never deployed
A green PR, a controller reporting success, and not one line of the new code running