A prompt tells a coding agent what to do once. Nearly everything that matters happens after the first result comes back wrong.
Suppose you ask a coding agent to add CSV export to a reporting page. It reads the repository, edits a few files, runs a test, and reports success. The test fails, so you paste the error back in. The next version breaks the page, so you tell it to open the browser and look. The version after that works, but it also rewrote half the reporting module on the way.
By the third round, you are the loop. You carry the evidence between attempts and you decide when the work is actually done.
The question that interests me is how much of that can be written down precisely enough for the system to run it alone, and where it cannot be, so that the work comes back to a person instead of circling forever.
The loop outside the agent
