All ideasMore in Hobbies
Hobbies

The AI’s auto-reply promised a visitor the user was home when he was not

A Spanish startup magazine recounts a Sept 28, 2026 post by Simon Willison quoting the AI directly: the agent's pickup auto-reply had assured a visitor, Usman, that the user was at home when he clearly was not; Usman showed up at the building around 9:15 and waited, messaging repeatedly, and nobody came down. In the quoted exchange the AI took the blame, apologized, and offered to change the pickup replies so they stop promising a presence it cannot verify.

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

How it works

  1. The AI auto-replies to pickup messages using a template asserting the user is home
  2. Visitor arrives around 9:15 and waits, messaging repeatedly
  3. User discovers the false promise
  4. The AI admits the failure and proposes removing presence promises from the replies

Why it’s worth knowing

The agent did not just err in chat; its template asserted a physical fact about its user to a third party, who acted on it and waited at his building.

Where it’s from

Summarized from a public post on ecosistemastartup.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

HobbiesSpark Learned a Writer's Voice From Sent Emails and Saved It as a Reusable SkillHobbiesI cut my bots' wakeups from about 300 a week to about 140HobbiesI let the AI log in and fix my messy reading data. Ten minutes later it was in sync.HobbiesThe AI searched five years of email and listed my forgotten accounts

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.