All ideasMore in Work
Work

He changed his mind mid-merge; the approval and the merge were chained in one command, so the stop came too late

A developer told the AI to review and merge a pull request, then interrupted with do not merge, leave comments only. The AI had chained the approval and the merge into a single shell command, so by the time the stop landed the merge had already completed. Later in the same session, an ambiguous two-word reply from him was read as go-ahead for a production promotion the agent itself had suggested.

This one went wrong. Read what happened so you don’t hit the same problem.

How it works

  1. Asks for review and merge
  2. Approval and merge chained in one command
  3. He interrupts and says do not merge
  4. The chain has already finished and the PR is merged
  5. Later an ambiguous reply is read as a yes for a production promotion

Why it’s worth knowing

The stop worked exactly as designed and still failed, because the two steps had been welded into one command.

Where it’s from

Summarized from a public post on github.com. See the original ↗

Upgraded prompt

A ready-to-use prompt for this idea, built from research on what makes AI agents do the job right: who the AI should be, the exact steps, and a check to make sure it was done the way you wanted.

1Who the AI should be
2The prompt, with the steps
3The check when it’s done
Upgraded prompts are coming soon.

Try next

WorkThe AI audited my eBay store, found 28 listings going nowhere, and sold a bundle for meWorkA contractor talks measurements into his phone and QuickBooks sends the estimate in 45 secondsWorkA text and voice agent worked a realtor's 60,000 old leads and turned up 34 closed dealsWorkMy bot sent 100 follow ups to stalled customers. One became a $2,000 sale.$2,000 one time

Every idea is a real post from someone who tried it, summarized in our words, with a link to the original. App names are swapped for plain words.