All ideasMore in Work
Work

He runs AI agents in parallel, and loose runs cost him a night

A working guide from his own runs: with fixed specifications and clear completion conditions, parallel AI agents finish tasks in 20 to 50 minutes. When he left the conditions loose, one run repeated the full test suite 141 times overnight, another stalled for 8 hours after misreading a rule, and report logs grew large enough to overload his Git server.

This only partly worked. Read what happened before you try it.

How it works

  1. Writes fixed specs with completion conditions
  2. Runs AI agents in parallel
  3. Tight runs finish in 20 to 50 minutes
  4. Loose runs loop (141 test repeats, an 8 hour stall) and flood the Git server with report logs

Why it’s worth knowing

The difference between a 30 minute finish and an all-night loop was not the model; it was whether the stopping condition was written down.

Where it’s from

Summarized from a public post on njump.me. 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

WorkRead every job advert, tailor my CV and apply with my approvalWorkHe told the AI to keep going. It emailed five researchers from his account.WorkSunday lesson planning went from up to six hours to fifteen minutesWorkFind my 277 unanswered brand emails, reply, and keep negotiating

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.