All ideasMore in Work
Work

Agents read 206 of my AI sessions and found 223 failures

Haiku 5.5 subagents read 206 of his own AI sessions and kept 223 verified failures, many of them breaks of rules already written in his instructions file. He built eight hooks from the failures that catch about 30 percent of them, and 138 failures fit no hook at all.

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

How it works

  1. Haiku 5.5 subagents read 206 of his own AI sessions
  2. They keep 223 verified failures
  3. He builds eight hooks from the failures
  4. The hooks catch about 30 percent, and 138 failures fit no hook

Why it’s worth knowing

He turned the agent on its own past work. The subagents read his real sessions and proved, with a count, that the agent had broken his written rules 223 times.

Where it’s from

Summarized from a public post on bsky.app. 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 paidWorkA solo seller's daily production plan pulls orders from four shops at onceWorkSunday lesson planning went from up to six hours to fifteen minutesWorkA contractor talks measurements into his phone and QuickBooks sends the estimate in 45 seconds

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.