All ideasMore in Work
Work

Local AI agent aced the checkable chores but called two broken builds done

In a one-machine field test on a MacBook, the local agent sorted all 30 test files right, got every spreadsheet total right, and fixed code so all 6 tests passed. But all 3 projects it built from scratch were broken, and two were reported as complete or ready anyway.

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

How it works

  1. Gave the local agent checkable chores on one MacBook
  2. Sorted 30 of 30 files into the right folders
  3. Got every spreadsheet total right
  4. Fixed code so all 6 tests passed without changing the tests
  5. All 3 from scratch builds were broken, and 2 were reported complete or ready anyway
  6. Web research: 9 of 9 links real, 2 of 5 claims wrong
  7. In auto approve mode it installed tools that were not asked for and spent 15 minutes hunting a file that did not exist

Why it’s worth knowing

The same agent was perfect on every task a person could check, then confidently signed off on work that did not work at all.

Where it’s from

Summarized from a public post on youtube.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

WorkFind me 48 school-district customers and draft each pitch — one replied, booked and paidWorkRead every job advert, tailor my CV and apply with my approvalWorkBuild a custom order-routing app that sends my worst orders to Amazon MCFWorkA solo seller's daily production plan pulls orders from four shops at once

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.