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 builder created an agent skill that files a user's saved Instagram reels into topic collections. It was battle-tested against a real backlog of roughly 3,280 saved reels, which it sorted into 13 collections.
Opus spent about 30 minutes and 25 dollars in tokens producing a 9-file refactor that collapsed to a 4-line change, with no time benefit to him.
An 8-second looping pixel animation accompanies the post: the author used AI to book a multi-leg, multi-airline open-jaw flight itinerary that neither Google Flights nor airline websites surfaced. It was ticketed through Duffel's API and came out cheaper.
Their freezer died and they lost all the food in it, and needed to make an insurance claim. He took photos of all the food items and told the AI to create a spreadsheet, estimating prices where it could not read them. The AI did it all, and the insurance company accepted the beautifully detailed claim immediately.
He spent about 5 minutes picking the mods he wanted for GTA4. The AI then went through the mods, chose which mods and which files inside each mod could work together, and installed them, work he says could have taken a full day by hand.
Sandboxed agent checks spec and code drift daily, triages findings, and surfaces issues; it revealed product miscommunications on the team.
He started with a drawer full of hard drives, flash drives and camera cards. The AI built a catalog of every drive, then an index with a hash for every file across all his backups: 8.1 million files, 3.6 million of them unique, going back about 20 years.
He asked his Dot to build a list of sales leads for his industry, limited to the business types he actually sells to. In five hours it had 1,400 leads and was still going, on its way to about 3,500 across the 20 biggest metro areas. He had paid $223 for about 350 leads before, and the Dot's list was cleaner.
He let the AI log into his atproto PDS with a temporary password and fix his messy Bookhive reading data against his Obsidian vault. Ten minutes later, everything was in sync.
He manages IT for 54 locations and was trying to maintain documentation in 11 or 12 different spreadsheet tabs and various cloud apps: vendors, equipment, bills, contracts. He used AI to build a web portal that syncs with the cloud apps he already uses, reads all of that data and organizes it into a summary page for each site. It alerts him when contracts or service agreements are about to expire, and it also shows devices that have not checked in to device management, any recent network changes, any recent support tickets for the site, and a printable inventory sheet for any location.
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.