I prefer to have my agents review my agents output and progress, and have them improve the prompts for future runs.

Yeah totally, you don't have to auto-merge anything - you can review the PRs yourself

Yeah, I think that's the most important part in these new types of processes. Although it is tempting to just let an agent run with it for a while.

This project should be called the Rube Goldeberg machine creator.

The Hitchhiker's Guide to issue-tracking.