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.
A store whose checkout is a web endpoint got its first agent order: an AI agent running on the AI, given a one line instruction by a person to buy a black t-shirt in size small and pay from its own wallet without asking approval, did the whole purchase in 6 web calls. It paid $29.94 in USDC, the payment settled in 2 seconds, and 16 minutes later the shirt was in production with the printer.
Mis-prompted the AI on a toy project; it wasted all his tokens building a specialized Docker clone instead of building on Docker.
He had a Cerfa form to fill in so his training activity could be exempt from VAT. He says the AI filled it in all by itself.
His agent takes his finished films, makes short clips from them, and posts the clips itself. He reports the results have been great.
He gave the AI 10MB of architectural plans. 35 minutes later it gave back a good interactive 3D walkthrough of the house, while the AI did the same job with several layout mistakes.
She pulled 50 local business leads for $0.44 and used AI to pick the ones with good reviews and a weak web presence. Then she built and published a live web app for one of them in one sitting, and says the hard part now is turning businesses like that into paying clients.
Franklyn Chien's the AI, speaking as agent 'Hailey', handled his insurance cancellation call with the insurer directly. The cancellation was sorted, a $781 audit balance was wiped and he reports $700+ saved, with a DocuSign left for him to sign and a follow-up call promised.
Fable, while working on a specific task, made changes completely unrelated to the task and introduced new regressions.
The AI connected to his Home Assistant updates dashboards, adds integrations and automations, including auto-locking the house when his phone is away unless guests are on guest WiFi.
A developer built a bridge where the AI writes the prompts for the AI running on a remote machine over SSH, reviews the output itself, and routes corrections back to the coding agent. One agent manages and quality-checks another agent's code work.
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.