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 father set the AI up to read 7 school WhatsApp groups twice a day on school days and post only the items about his daughter into a private chat he shares with his wife. It reads PDFs and images too, and caught his name on a volunteer roster he would have missed.
A poster in the showcase hub built two the AI skills that fetch real Facebook targeting IDs for the Meta Ads MCP, which cannot fetch them itself. End-to-end testing caught the first version silently dropping 25 of 135 valid targeting options, including the highest-intent behavior.
He told the AI the ebook he is writing only had endnotes with no links, not footnotes linked in the text. The AI checked how the book was published, then rewrote the epub file with proper clickable footnotes matched to the text and page.
A UK teacher set out to answer his students’ question about whether coding still matters by building a large system using only AI. Seven months later it had become rgbloom, a real company printing real photo books, built over 600 AI sessions and 6,700 prompts, with over 100,000 lines of code and about the same again in tests.
Niraj Rajgor's unused 10th generation Kindle is now a photo frame. Working through AI over Wi-Fi, GPT-6 Astra built tools to run custom software on the Kindle and installed a slideshow app that cycles ten photos, four minutes each, and picks up where it left off after sleep.
He gave an agent $50 and 24 hours to book meeting leads by messaging founders who had posted about scaling problems. A bug dropped its polite sales template after about 15 rounds, and it started sending blunt two sentence critiques of each founder's site and code instead. The reply rate was 62%, 8 founders booked calls, and he closed 2 audits at $300 each.
He connected the AI to DevonThink, the app where he keeps his documents. That gave him the help he needed for the huge job of sorting and tagging old documents he had saved before he used DevonThink, some of them from January 2020.
TP-Link has no official way for an agent to control its Tapo devices, so he took the app apart, worked out how it talks to the lights, plugs, sensors and cameras on his home network, and built a connector the AI can use. The AI now runs his house, and even drafts a floor plan from the device names that becomes a live 3D map: doors open in the model when the real sensor opens, and tapping a camera plays its video after a privacy check.
His company Feature Upvote already does regular pen tests and monthly backup restore checks. He pointed the AI at their source code for a security review, and it found some serious problems.
The AI filled out his car insurance application for him. Where an answer was not in what it knew, it stopped and asked him instead of guessing.
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.