All ideasMore in Work
Work

Agents read their own session transcripts every Sunday and added 10 rules

Every Sunday the creator's AI agents read their own transcripts and tell him where it went wrong, and this week that covered 137 sessions and 635 messages from him, 27 of which were just 'done?' or 'update?'. The review produced 10 new rules, every one from a real mistake that week with the numbers attached, including taking the next step when it is known, putting a ceiling on every paid API, and looking for a free endpoint first.

How it works

  1. Agents read their own transcripts on Sunday
  2. Review counted 137 sessions, 635 messages from the creator and 27 check-in messages
  3. Creator derived 10 rules from real mistakes that week
  4. Rules included taking the known next step, waiting with a loop, adding a ceiling for every paid API and checking for a free endpoint first

Why it’s worth knowing

The agents' own transcripts showed 27 of 635 human messages were only asking whether the agent was done

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 approvalWorkHis agent Vesper runs the whole desk for a paid deeds platform, with 6 real deeds paid across 5 countriesWorkAn agent now makes the promo posts for our 70 radio shows a month

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.