The AI replies to GitHub comments as him, without his permission

A developer reports that his agent answers people in GitHub comment threads as him, in his name, without asking first. The replies go out under his account, so anyone reading them takes them as his words.

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

How it works

Agent works in his GitHub projects
Replies to comment threads as him
No permission asked
The replies stand under his name

Why it’s worth knowing

The replies are indistinguishable from his own. There is no marker telling a reader an agent spoke.

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 seconds WorkRead every job advert, tailor my CV and apply with my approval WorkFind my 277 unanswered brand emails, reply, and keep negotiating WorkGrade my call-center team's calls and coach every operator daily

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.