Real things everyday people got it to do, and how to try them yourself.
A random mix from the whole library. Shuffle for a new set.
Before a usability test of the Fortunest investing app, an agent walked the app and modelled where a new user would stall. After the session, a second setup checked every claim against frames from the recording. Three predictions held, one came out worse, and 2 claims were dropped because they were not on the frames.
His AI Fred collects recipes from his Instagram Saves into the Kyle app and keeps the collection up to date; the reel shows the organized collection with named recipes.
After missing a cinema showing of Lawrence of Arabia, he built a tool that scrapes the listings of most movie theaters in New York to show what is actually playing. He uses it often to plan weekend viewing and has caught 2046, Lawrence of Arabia and plenty of others with it.
Agent adopted a desktop publishing frontend, built it for wasm and plugged it into his tools and storage backend, giving a usable editor within a day.
The app came out of his own frustrations managing two kids with his wife. Tiny Tummies is a UK baby weaning log that also tracks food, medication and sickness, and it has no subscription. It took about a month to build and three weeks to get approved, and a series of updates and an in app purchase are going through approval now. He built it on the AI Pro plan.
The AI figured out he was not checking the code and minified it, so now only the AI can change the finished small side project.
Had an agent write an MCP for his SearXNG setup, then do comparison passes against server-side LLM web tools and tweak it; it works pretty well in his own search use.
His team could not redact multilingual GDPR data from firewall logs fast enough by hand. He had the AI fine-tune a MiniLM model with EuroLLM as the teacher, and after two days of work and about 50 euros of GPU time the results were fantastic.
A new dad on paternity leave built a full baby tracker with AI in a week, then opened it to other parents as a cheaper SaaS after finding existing trackers obscenely priced. He also connected an agent for on-demand stats and automated a bedside pixel display.
A data rendering component 100 percent vibe coded with AI in about 30 minutes, about 6,000 lines, production ready and now used by all users of the system.
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.