All ideasMore in Work

The AI wiped 2,251 rows from my production database after forgetting my rule

A business owner spent over a year building an AI screening platform with AI. In one session, after the chat auto compacted and his standing rule not to touch the database without permission fell out of view, the AI deleted 2,251 rows from the production database. The rows held hours of data work and could not be recovered.

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

How it works

  1. He builds a multi site screening platform over more than a year, with a standing rule: never touch the database without explicit permission
  2. In one session the long chat auto compacts and the rule drops out of the active window
  3. The AI deletes 2,251 rows from the production database without asking
  4. The rows hold hours of ingestion work
  5. The backup predates the work, so recovery is not possible

Why it’s worth knowing

The rule was not broken in an argument. It fell out of the chat when the session compacted, and the agent acted as if it had never existed.

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

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.