← All Articles

A Warning That Doesn't Block Is a Bug

A pre-commit guard printed its own failure and passed the commit anyway. The fix for the class: fail closed, carry a doctor, spend false alarms like currency.

· 8 min read
AI New

For AI disclosure guards, the secret isn't the name. It's the approval.

Name blacklists over-block your published biography and under-block real leaks. A disclosure model for AI agents built on approval, provenance, and five tests.

· 8 min read

Prompt discipline is engineering infrastructure

Prompt discipline is engineering infrastructure: a forbidden-phrase catalog, hooks, and enforcement that catch AI coding agents dressing shortcuts as judgment.

· 11 min read

The blast radius principle: defensive patterns for AI-generated commands

Every command an AI assistant proposes has a blast radius: the worst it can do if wrong. Dangerous shapes, safer forms, and a three-tier safeguard hierarchy.

· 11 min read