The vibe-coded app passed its user tests and failed the unlisted requirements

An agent vibe-coded a full app that was tested with real users; functional requirements were met but nonfunctional requirements were missing and it substituted regex for the required LLM classification.

This only partly worked. Read what happened before you try it.

How it works

An agent vibe-codes a full app that is tested with real users
Functional requirements are met but nonfunctional requirements are missing
It substituted stand-ins where real behaviour was needed

Why it’s worth knowing

Nonfunctional requirements are the ones users feel and specs omit.

Where it’s from

Summarized from a public post on news.ycombinator.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 WorkOne man released a whole movie with about 40 tools he built with AI WorkThe AI audited my eBay store, found 28 listings going nowhere, and sold a bundle for me 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.