The AI diagram shipped without the claim it was meant to show

He asked the AI to make a technical diagram with gpt-image-1. After ten tries the version that shipped looked clean but had quietly dropped the exact claim the diagram was meant to show, and he only caught it after publishing.

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

How it works

Asks the AI to generate the diagram with gpt-image-1
Ten regenerations
A clean looking version ships
He spots the missing claim after publishing

Why it’s worth knowing

Ten tries fixed how the diagram looked, and the clean version quietly left out the one claim it existed to show.

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

WorkA review engine asked his past customers for reviews and got three five star ones on day one WorkForemen file the daily log with a three-minute phone call, and the agent chases anyone who forgets30 min saved WorkA contractor talks measurements into his phone and QuickBooks sends the estimate in 45 seconds WorkA text and voice agent worked a realtor's 60,000 old leads and turned up 34 closed deals

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.