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.
Cannabis prices near him change daily across four dispensaries and four delivery services, each running its own sales. He built a script with AI that checks them all and finds the best deal at the time; he says it saves him about $20 to $40 every time he buys.
The AI audited the poet's 6,500 Threads posts against the master file for his collection and found 525 poems that had never made it into the file.
He wanted one place where people can find all the apps he is working on. The AI built the site, beardfm.app, in about 15 minutes.
A parent describes a standing weekly loop: The AI checks the store he uses and builds an ingredient list that feeds him, his wife and their kid for under $30 a week, hands him a recipe each day, then updates the running inventory of what they still have to cook with - so next week's list starts from the actual pantry, not from scratch.
Pointed the AI at an abandoned MS-DOS game directory; it understands the data formats, unpacks graphics and sound assets, and is reconstructing the game logic.
The AI enabled a camera on a test device and he taught it to reboot into the previous kernel on build failure so it could iterate for days; ended with a usable setup and camera login working.
A poster on the Dots forum thread reports that while he was on vacation, his Dot, Axiom, handled a high-complexity local-model job lasting six to eight hours: downloading, testing, unloading and redownloading models, and keeping him updated model after model.
His parents’ ten blinds ran off one dumb radio remote. With a Flipper Zero he recorded the signals, the AI spec’d an ESP32 board to send them, wrote and flashed the software, and designed a printed case; the blinds now open and close at sunrise and sunset with a small web page for overrides. Later the AI built a phone app so his parents can just ask Siri to open or close them.
A home-lab owner reported on X (via WhatAgentsCanDo, Oct 19) that, still in bed, he sent the AI a link to a post containing a setup recipe for a new DeepSeek model (DeepSeek-V4.1-Flash-1017, EXL3) across two NVIDIA DGX Spark machines and asked it to do the setup. The AI was not installed on the Sparks, but they shared a network with its computer, and everything was ready to test by the time he got up; he says he does not know exactly how the bot reached the machines.
His company's system was bouncing active SMS clickers who threw too many 30003 errors. The AI Ultracode found the cause, and the fix means the sunsetting code now ignores active clickers.
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.