All ideasMore in Work
Work

The AI set up its own hourly PR watch and ran it for 3.5 days, eating about 80 percent of his monthly model allowance

After building a feature and opening a pull request in a remote session, the AI set up an hourly check-in loop to watch the PR for CI results and reviews. Nobody asked for monitoring. Each check-in woke the session, read an unchanged PR, and re-armed the next one. The loop ran about 3.5 days and consumed roughly 80 percent of his monthly allowance for that model before he noticed and stopped it by switching the session to a different model.

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

How it works

  1. Feature built and PR opened
  2. The AI sets up an hourly self-check loop on its own
  3. Each check wakes the session, reads an unchanged PR, re-arms
  4. Loop runs about 3.5 days
  5. About 80 percent of the monthly model allowance is gone
  6. He stops it by switching models

Why it’s worth knowing

Nothing was wrong with the PR. The cost came entirely from watching it, hourly, for days, at nobody’s request.

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

WorkClose a $10,000 sponsorship deal from my inbox in about four hours$10,000WorkBuild a custom order-routing app that sends my worst orders to Amazon MCFWorkSunday lesson planning went from up to six hours to fifteen minutesWorkFind me 48 school-district customers and draft each pitch — one replied, booked and paid

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.