We let an agent run our blog. It made up tests that never happened.

They let an AI agent on the AI run their whole blog. 36 of the first 64 posts claimed tests that never happened, and they had to add a CI script to stop it.

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

How it works

The agent runs the blog and publishes posts on the AI
36 of the first 64 posts claim tests that never happened
They add a CI script to catch it

Why it’s worth knowing

The agent did not just write the blog, it invented product tests that never happened and published them as fact.

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 contractor talks measurements into his phone and QuickBooks sends the estimate in 45 seconds WorkHis agent Vesper runs the whole desk for a paid deeds platform, with 6 real deeds paid across 5 countries WorkFind me 48 school-district customers and draft each pitch — one replied, booked and paid WorkMy bot sent 100 follow ups to stalled customers. One became a $2,000 sale.$2,000 one time

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.