Writing

Notes from the engineering work. What breaks when AI-generated systems meet production, how to make agent collaboration hold across sessions, and the infrastructure it takes to make agent output reliable.

• Renovating a vibe-coded app: readable code, no reasoning behind itAn education platform built in Lovable for months, an audit with 319 findings, and four separate engines computing the same daily score with nothing saying which one is the real one. September 2026.
• Telling an agent to be honest isn't enoughA memory rule wasn't enough to stop Claude Opus 5 from turning quietly agreeable in deep sessions. On the four-leg doctrine I put in place instead, and a July paper that reframes what I built. August 2026.