AI & Automation Aug 17, 2026 · 1 min read
Everything I Was Afraid of Worked
Last October I published a post arguing that agent safety is an architecture problem: the model proposes, hard-coded code disposes, a human approves. Then I built exactly that for a youth sports club's website and used it for an hour. I found seven things wrong with it. None of them were in the part I had been afraid of.
Read post