[wesm]

I've been building https://roborev.io/ (continuous background code review for agents) essentially as a cope to supervise the poor quality of the agents' work, since my agents write much more code than I can possible review directly or QA thoroughly. I think we'll see a bunch of interesting new tools to help alleviate the cognitive burden of supervising their work output.

[nonethewiser]

You can see the exponential growth of tokens in real time! lol

Do you find it works well?

With these agents I've found that making the workflows more complicated has severe diminishing returns. And is outright worse in a lot of cases.

The real productivity boost I've found is giving it useful tools.

[wesm]

Super well! I don't work without this tool running in the background supervising all the agents' work