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.
Jruss707 tested the AI on a Nov 13–18 Yosemite/Sage Lodge trip: the agent browsed the Sage website and completed the hotel booking using a saved Link payment method, found a Southwest flight from Sacramento using reward points (after the author pointed to a preferred flight), and arranged an AWD/4WD rental car from Bozeman.
The AI’s own processes silently wiped and recreated the user's entire ~/.claude configuration directory four times in about three weeks, taking thousands of session transcripts, skills, plugins and hooks each time. The fourth wipe also destroyed a secrets subfolder holding 19 live API token files, one wipe happened mid-session, and each recovery took hours of manual rebuilding.
One of eight hands-on tests run on the reviewer's real accounts; the AI scored 42.5/47 overall across the gauntlet.
The owner of a small technology company called ALAPKO runs AI as the reasoning layer for an internal support worker they call Mabel, with 41 purpose built tools tied into their systems. In a shown run she read a ticket with its customer and asset history, worked out the likely cause, claimed the ticket, replied to the customer with troubleshooting steps, wrote an internal engineering note, and set the ticket status, in about 34 seconds. Business actions go through permission scoped tools and every action lands in an audit log; her normal shell access is read only.
Lauren (someone, 32K followers) flies business class but refuses full price, so she tested the AI and named her assistant 'Miles.' On-screen chat showed Miles quoting a ~$3,750 baseline and confirming it would monitor for three months; statuses cycled through 'Tracking fares' and 'Searching fares.' Later a phone notification showed Miles's 'Good morning!' briefing listing five Icelandair fares under $2k from SEA and SFO to Rome. B-roll showed her on a business-class flight.
He triages email with Outlook categories and uses them as task assignments for agents. When an invoice arrives it gets two categories: one agent saves it as a PDF in his credit card folder, another emails it to his accountant. Each agent watches its category and updates it when the job is done, so the inbox itself shows what is pending and what is finished.
He was paying for several streaming services all year but only watching each one a few months a year. The AI worked out each service's real on window from what he watches and when seasons land, did the monthly versus annual math, and now does the toggling itself on dates he approved in advance. Each job rechecks the premiere date before acting, picks the right tier, and reports back what happened. If a cancel fails it tells him instead of retrying forever. Setup took about ten minutes, and he expects it to save a few hundred dollars a year.
He had the AI build a 15 second showreel with music from a single prompt, using an animation skill and his own list of banned things. The AI checked its own images and fixed them before he saw anything, and he says After Effects is on his delete list.
Chelsea Yamase documented the AI re-planning her Sardinia trip after a rental-car breakdown: re-routing through the mountains, choosing a boutique hotel near a boat launch, and booking restaurants via WhatsApp in Italian. The AI also monitored flights and deliveries and emailed about customs.
Before the holiday rush, the AI audited Polk's email automations, shut down duplicate flows that were double-emailing customers, recreated the flows, rebuilt templates, and turned on tracking so she can see which emails drive sales — while she kept running her other businesses.
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.