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 man was paying about $30 a month to RocketMoney and the AI just to find subscriptions he had forgotten about, and using them only now and then. He had the AI connect to Plaid, where it found more subscriptions than the two apps ever had, and set up a weekly email listing his current subscriptions and any price changes.
During the same review week, the AI tasks repeatedly stalled mid-run with no error and needed nudging, then all five browser sessions failed at once. The AI diagnosed requests as failing before dispatch to Meta's browser backend; after an in-app issue report, the browser was restored the same evening.
He set up a monthly check for himself and his close family. The AI searches state unclaimed property sites and open class action settlements that fit the products and services they use. It found $250 from an old utility company in his name and $1,500 in his mom's name from an insurance company, and it found three class actions he could join and filled out the forms for him. It only pings him when something new shows up.
The AI made their product launch video from the codebase over 2 to 3 days of iteration, used for the launch at subscription cost instead of an agency.
Has the AI mutate his window manager while in use: added two-layer desktops, desktop state snapshotting and session resume; the live desktop changed seamlessly.
Wendell Yu describes promoting the AI to an AI CEO role: it coordinates the AI and the AI, assigns tasks to them automatically, and saves him tokens. It is the second of five first-hand the AI cases in his video.
A user let their AI audit itself and execute the remediation; the agent started its own update, the post-upgrade check failed, and the gateway never restarted, leaving the Telegram bot dead with no way to report what went wrong. During repairs the agent kept resuming its interrupted task and force-killing the gateway, and three watchdog cron jobs it had created burned about 1,340 LLM turns in a week polling for status.
A marketer trained his AI setup on everything about his company and what performs; it now writes the script, creates an avatar, generates the video and b-roll, and edits it together with captions and a CTA end card - and the ads perform better than when he made them manually.
Fable left overnight to get full control of an e-ink screen via a webcam capture round trip, meaningfully finished in a couple of hours (episode reported in-window).
His business scans every invoice into a Google Drive folder. The AI reconciles them there: checking they were billed correctly, that credits for returned goods actually arrived, and that there is no slippage. He says it is far faster than reconciling by hand.
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.