When I was building a skill to evaluate repo readiness, I moved all the scoring into a script, because I needed determinism and didn't want the scored tied to how generous the LLM was feeling that day. I've been thinking about that same division of responsibility across the agents I build. Some work needs judgment, while other work needs to be deterministic. We already know how to write software that does that. The article demonstrates this with a flaky test detector where the agent helps…

megadevhq@megadevhq1d ago

"Don't make the agent remember how to do its job." @kentcdodds and @sulich_olaf, Day 2 of MEGA Drops 🩸 @theo, you've said context management is the skill. Is this the answer or the dodge? @johnlindquist, your loops run on the opposite instinct. @techgirl1908 what is your take?