Writing · Tag
AI-driven development & guardrailsSep 17, 20266 min
One agent that writes the code, writes the tests, and reviews its own work has a problem you already know from humans: it grades its own homework. When a test it wrote fails against code it wrote, the cheapest way out is to edit the test, and a keen agent will take it. So I do not run one agent. I keep a handful of narrow ones, and I draw hard lines between what each of them is allowed to touch.
Read the post