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 homelab owner used AI on his Immich photo setup, which can only remove duplicates inside one user library. The AI found the duplicates across multiple libraries and quarantined them, found his grid based images from his iPhone 4 days, wrote the conversion software, and turned them into animated WebP files.
Alongside his homemade TMS, Wes Oberman built a settlement payroll program that calculates every driver's pay automatically. His wife Laura's Thursday settlement run, previously a 12-hour day of manual calculation, now takes under an hour, and the automatic math removes the risk of underpaying drivers.
Creator someone gave the AI her Florida bucket list. The AI booked a 9pm reservation for two at Japón at The Setai via OpenTable, then booked a beach horseback ride plus dinner afterward.
His studio runs much of its back office on agents, each with its own instruction file. The email step reported success on sends that had failed, and they later found 44 messages still sitting as drafts. Scheduled jobs were marked done before their output existed, which cost five deliverables in one day. They fixed it with a plain check after each risky step: after sending, look for the message in the Sent folder; before marking a job done, check the file is actually there. Now only a failed check needs a person's eyes.
The AI built him a Bluesky bot that posts HN Wikipedia articles and posts an archive pick after 48 quiet hours; it is live and posting.
When a person fixes something one of his bots wrote, the bot writes down what it said and what the person changed it to. A nightly task reads those changes and writes the rule it thinks they point to, and in a year the bots have picked up more than 40 rules this way.
He pointed the AI at a downloads folder with over 1,000 media files and at his Jellyfin library. The AI made a queue file he could import into HandBrake, and he says it saved him a lot of time.
A man reimplemented his GIS science code from Python into Rust using LLMs, with a hard test: identical inputs and outputs at 10,000 points. Where the rewrite differed, the agent researched other implementations and tried again. The result runs 10 to 70 times faster with far less memory, and the service now does the work essentially instantly.
He set the AI to check OpenTable every 10 minutes for a restaurant table for 3, using the OpenTable connector to keep token use down. When a slot opened in the morning for the next day, it booked it immediately. He got no confirmation in the chat, but found the booking confirmed in his OpenTable account. The watch used 1.48 million tokens in total.
The AI built an internal productivity tool that would not otherwise exist, then its ad hoc sync logic got so tangled he stopped feature work for about 4 weeks while the AI built and tested a proper sync engine.
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.