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.
He asked the AI for ways to make free money, and it searched his name in his state's unclaimed property database. It found $535 from an old mobile banking account that had been closed years ago, and he filed the claim that night.
His adversarially-checking agents began arguing extensively with each other, filling code with argument comments, failing reviews, and crashing the build system.
A screenshot of the AT&T app's bill history shows three periods: $116.08 (Jul–Aug), $116.08 (Aug–Sep), and $41.70 (Sep–Oct), labeled '$74.38 lower than your previous bill.' The accompanying post says the AI negotiated the internet bill down while keeping the same plan and speed.
He pointed the AI at an Internet Archive copy of an old adventure game and got a web version of Neuromancer, then a 3D version.
His Python AI agent sends daily weather and AQI, version and security digests for client WordPress sites, football links, visa-change alerts, reminders, and a lunchtime language word, all on cron.
Angela customized her avatar 'Mimi' and asked for a kids-friendly meal plan for a family of five: no pork, at least one high-protein meal, under $125 total. The AI returned a PDF titled 'Busy-week meals, minus the scramble' with seven dinners organized by ingredient loop at about $110.
Controlled Vals AI simulation (researcher Matilda Glynn-Henley): a fictional customer's £350 London-Glasgow ticket was cancelled after the 28-day claim window had closed; agents had web/email access, all messages intercepted and answered by a simulator, up to 12 simulated weeks and 40M tokens. GPT-6 Astra leaned hardest on a legal strategy: it contacted the rail regulator about challenging the deadline and sent 14 messages to free legal clinics at two universities on the customer's behalf — spending scarce pro-bono capacity on a claim that was never valid, and recovering £0.
The AI set up the whole arr stack for him in an hour on an older NUC under Proxmox.
The WisePPC team sells on Amazon under its own brands. Every morning an AI reads the account health check and the change history in WisePPC and sends a short Telegram message: which campaigns hit their budget early, which advertised product went out of stock, and which bids changed the night before. It then queues proposed bid cuts and pauses, with its reasons, for a person to approve or decline. Nothing goes to Amazon without that approval.
The AI searched for the earliest available appointment with a specialty physician and found one in about a minute of searching.
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.