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 Facebook screenshot shows the AI's pending-order screen: 'the AI wants to place an order at Duffel' for an American Airlines round trip, Raleigh/Durham to Dallas departing Monday Oct 19, 2026 at 11:39am nonstop and returning Friday Oct 30, 2026 at 9:35am nonstop, one passenger (Paul Armstrong), total $607.09, payable by Mastercard or Link.
He says the AI got a loyalty discount offered pretty quickly, about $40 a month, but could not finish the job: it let the chat time out instead of asking him to approve or confirming directly. Having the discount in writing let him point to it and finish the switch the old fashioned way himself after the AI’s later attempts failed. He still counts the $40 a month as saved.
Set the AI the task of running Parseable locally against another of his apps; it worked around a protobuf limitation by running a proxy, he switched his stack to JSON and got it running.
A runner replaced uploading Garmin screenshots into AI with a self-hosted agent on a Mac mini that reads his Garmin data (sleep, HRV, resting heart rate, VO2 trend, laps) through MCP plus his Strava uploads: it messages him at 8am, designs the day's run and writes it to Garmin Connect, then grades each session against the prescription when it lands on Strava and decides when training load goes up. He hit his sub-20-minute 5K goal about a month later, and it saves him the hour a week he used to spend planning.
His company runs an agentic software factory handling low-level chore tickets and merging about a third of their PRs, with no slop downtime incident he is aware of.
A creator who makes hundreds of NPC entries for an application, work that takes hours, handed the archiving to the AI; it archived 780 entries in two weeks.
The agent-built data pipeline he inherited was riddled with errors and producing bad data, and the coding agent's fixes typically introduced new defects.
Pavuluri Gopikrishna had the AI build a photo-based calorie tracker, then cancelled his paid calorie-tracking subscription because the agent-built one replaced it. The build-to-cancel pattern shows the AI replacing a recurring SaaS cost.
AI agents rewrote a production Node service handling 92M messages a day into Go (Checkly company blog, result stated in the title itself).
A user’s the AI negotiated a $200 mortgage late-fee refund for him; the same setup also auto-books his kids’ activities, runs his calendar and inbox, and nudges him three times a day. The refund came from the bot arguing his case with the lender.
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.