I made CC part of my deterministic quality gate[0] for agents. Not sure how much of it is placebo, but overall I've seen the gate catch a lot of cases where the agent strayed from the constraints of the particular project.
FWIW In my setup I have just the one coding agent, and umpteen others for support and/or testing. I still do a human testing pass on everything though, if only to find errors in the testing process.
Yes, I do that too, but the value of a gate is that there's a tedious deterministic process which is the same every time. So it is harder for agents, including the reviewing ones, to stray and invent things or miss something.
ivm · · focus · HN ↗
[0]: <a href="https://github.com/ivmirx/agentic-quality-loop" rel="nofollow">https://github.com/ivmirx/agentic-quality-loop
Kim_Bruning · · focus · HN ↗
ivm · · focus · HN ↗