Agent wired into a shop inbox answered a supplier invoice as a cake order
A man wired an AI agent into a small business's order inbox and it passed every test he wrote. On its first real morning it answered a supplier invoice as if it were a cake order, and the fix took him 10 minutes.
This one went wrong. Read what happened so you don’t hit the same problem.
How it works
- He wires an agent into the business's order inbox
- It passes his whole test set
- On the first real morning a supplier invoice lands
- The agent answers it as a cake order
- He fixes it in 10 minutes
Why it’s worth knowing
The agent passed every test its builder wrote, then failed on a plain supplier invoice on its first real morning.
Where it’s from
Summarized from a public post on bsky.app. See the original ↗