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.
His company asks for a review after every job. He says that one habit gave them about two to three times as many five star reviews as any competitor.
A triathlete uses a Garmin MCP through AI Desktop - forked because the stock version couldn't build his workout types - so the AI creates and schedules his swim, bike, run, and gym sessions, pushing them to his Garmin calendar, which syncs straight to the watch on his wrist.
After his dad was cut in the federal layoffs at 54 and spent months scrolling job boards, his 19 year old son built a job search engine that runs through AI. It pulls postings from about 50 employer hiring systems and job boards, reads every new posting against a resume and plain English preferences, and gives a verdict, on a schedule or on demand. In two months 1,000 people signed up and 20 pay; most importantly his dad got hired, and another user just got an offer at Databricks.
He joined the AI’s cloud computer to his Tailscale network and gave it SSH access to a restricted user on his home Ubuntu box. After a series of proceed replies from him, the AI set the rest up itself. It can now run commands and browser work through his own hardware, and he uses it as the control point for his homelab: Docker, VMs, his NAS and Proxmox. The setup uses a dedicated non sudo user and SSH keys, with no open ports.
His agent pipeline wrote and published his blog in Turkish and English for six months, putting out 1,276 posts in each language across 3,300 commits. Of 99 merged pull requests, 67 were his repairs, and he once had to clean up 641 posts with fake numbers and made up stories.
A local Whisper model on his iMac writes out an episode with timecodes. The AI 2.5 reads the transcript, marks the ad blocks, and sends the timecodes back as JSON so his app can build a cut list.
GLM fixed a real issue in his app that Opus 5 could not solve, though a sub-agent tried to cheat with sleep and echo along the way.
Opens an LLM in his dotfiles and complains until his broken LSP config works again, usually in a few minutes, a recurring fix over months.
He resells Amazon liquidation pallets on Facebook Marketplace. With the AI he built one system for the whole flow: before buying, a browser extension pulls a lot’s manifest, retail prices and photos and says whether the lot is worth the asking price; after buying, it generates the Marketplace bulk upload files with pricing; in his garage he checks items in, photographs damage on his phone and prints QR labels; and dashboards track sales, tax, profit and sell through. It is about 10,000 lines of code across more than 35 versions, running on his home server.
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.