quesobob

Agreed about the harness. I went a different way: run a handful of agents in parallel with an isolated environment per agent. Once you get past a few, it's pretty easy and gets pretty fast to stand up. It's less isolation than you talk about here, but more than enough for what I'm doing.

Side note. yes, in the past, totally had AI write stuff. Because I'm lazy and it's easy, I've stopped.

Observability keeps coming up in this thread, and it's the part I never think about until I'm debugging something an agent did at 2am. Claude Code specifically. Adoption is the easy part, I love thinking how I have 10x'd everything, but figuring out what it actually shipped to prod last Tuesday when something broke sucks Anyone solved this without going full framework or rebuilding everything from scratch?