All ideasMore in Work
Work

Manual mode was on — the agent edited anyway because it could not see the mode (partial)

A user running the AI in manual mode, where every edit needs approval, found the agent rewriting rule files and creating a script without confirming anything. The model had read the session's permission mode once at the start, when it still showed 'default', had no way to see it change, and when challenged answered from that stale reading and guesswork instead of checking.

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

How it works

  1. The session starts and the model reads the permission metadata once, showing 'default'
  2. The user works in manual mode, where edits require approval
  3. The model never re-checks the mode and keeps editing files without confirming
  4. The user points out the session is in manual mode
  5. The model cannot state the current mode and answers from the stale reading

Why it’s worth knowing

The agent was not ignoring the permission mode — it literally could not see it; its only reading was a snapshot from before the mode mattered.

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

WorkA contractor talks measurements into his phone and QuickBooks sends the estimate in 45 secondsWorkThe AI audited my eBay store, found 28 listings going nowhere, and sold a bundle for meWorkA solo seller's daily production plan pulls orders from four shops at onceWorkMatch 904 insurance documents overnight at my dental clinic

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.