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.
An AI Dot messaged its owner on its own about a 3 year old GitHub issue from their time at Flipper, which had new developments. They say they never told the Dot their GitHub username, that they worked at Flipper, or anything about the issue.
A user first caught the AI sending his email address to a website in the request header for no reason. He built a dummy site that asks for contact info to test it, and Sonnet put his email in the header again more than once, then admitted the slip in its own report.
Rosey updates the kids chore chart on a Skylight frame every morning.
The AI modernized a 22-year-old legacy system, updating dependencies, auditing security and adding features, raising test coverage from about 65 percent to about 80 percent.
OpenAI's launch post reports that an early tester's Dot noticed he had forgotten to invoice a publication, prepared the invoice itself, and sent it after his approval. No amount or publication is named.
A listener had the AI build him a personal podcast feed he follows in his podcast app. Each day it looks for one episode he would actually enjoy, based on his taste and recent talks, and skips the day if nothing is good enough. It downloads the pick, writes out the words locally, finds the sponsor blocks and cuts them out, checks the joins, and adds the episode to his private feed with a note on why it was picked.
The AI built a recording app that screencasted the interactive diagrams in his blog article and added titles, turning the article into a published video, though it took many hours.
A user runs a long-lived agent session over Telegram: more than 4,000 messages and about $231 of usage in one session. Replies had been delivered normally until late in the session, when for 3 consecutive turns the agent produced text but never made the Telegram reply call, so nothing reached him at all. In the same stretch it also stopped saving decided design decisions to memory, as its standing instructions required, and he had to re-explain the decisions in a later session. A manual service restart and a log review found the cause.
Beef, sheep and cotton farmer Andrew Gill dictates voice notes and takes photos in the paddock, and the Farm Assistant agent files them alongside his paddock sensor data, livestock market prices, weather and cash flow. Automating the admin alone saves him and his wife about five hours a month.
A musician's the AI band manager runs a weekly crawl of musician websites, hunting and sorting possible new members for his band. It keeps the options list updated in his notes app, watches for changes he makes like crossing someone out or noting talks, and prompts him to follow up on the parts only a human can do.
The AI saw that Caddy was nearly out of memory on his service, checked the traffic, and found bots hitting IP addresses his customers never use. It tested a block through a live failover, applied it with no downtime, wrote it up, and merged the pull request.
Gave the AI photos of a broken microwave handle part against a 1-inch grid, it made a 3D model, and his test print works perfectly instead of buying two 30 dollar parts.
The AI fixed a bug that would have made him abandon the distro, but the PR was closed by maintainers and he continues running his own fork with the fix.
He fed Work mode a spreadsheet with a tab for each month of two years of retail, corporate and internet sales and asked for an executive summary for the owner. It ran in the background while he did other work and came back with trend analysis and percentages written for a non accountant. The owner loved it, and he figures it saved him days.
The AI claims the week's free games from the Epic Games Store for the user on a recurring Thursday schedule, so the freebies are never missed.
A developer runs his own repos and production server under a written constitution file in every repo. Automated runs check production logs daily and file bug reports. When he types one short check in message, the system scans and ranks his open issues, sends sub-agents to fix the top ones, and code deploys to production twice a day without him pushing it. A read only agent on the production box acts as his dashboard, checked through a chat app.
Someone in the house heard a beep a little before 12:13 AM. He handed the question to an agent with access to the camera recorder. It came back with the sound, the source and a short list of reasons: a smoke alarm that sounded once, at 3417 Hz for 0.87 seconds, about two metres from one camera. It was not a fire, not carbon monoxide and not a dying battery.
Peace Call's log of its AI agent's cold email (Oct 13-17): 74 one-time emails sent, 6 bounces, 1 'stop' reply, 1 out-of-office — and 0 positive replies. The first night bounced 22% (2 of 9), tripping the site's own 5% pause rule until the owner approved pre-send address checks; even after the fix, every night produced exactly one bounce and no interest.
Mufti Hassan had the AI clean up his full Gmail inbox. The chapter title gives the size of the job: 12,000 emails.
A reviewer uses AI as producers for his projects, with the bots managing multiple Cursor Cloud Agents doing the underlying 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.