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.
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.
The maker of a small game viewer tool had the AI play the game with scripted commands and write playtest reports. One report, from a manifest file the game loaded, documented a crash on exit, a bad default window size, dead inputs, and several rendering bugs.
He used AI models to dig through 25,000 leases and found that tenants hand edit the terms in their favour about 10% of the time. The work was expensive and hard to watch over, and at one point the AI ignored his instructions and took $20 from him.
OpenAI's launch post reports that an early tester's Dot noticed he had forgotten to invoice a publication, prepared the invoice itself, and sent it after his approval. No amount or publication is named.
Built with agents over about a year: a production billing system for his small telecom company, a multiplatform app, internal tools in use, and a coding agent harness now used by non-technical colleagues.
He pasted one prompt into AI, and the AI read the Carly email setup docs itself, finished the signup, and took the verification code. The inbox, named Loopy, now takes tasks by email and asks before replying to anyone outside.
The AI modernized a 22-year-old legacy system, updating dependencies, auditing security and adding features, raising test coverage from about 65 percent to about 80 percent.
His loop starts the AI once an hour with no human approval, a decision table in code picks one action, and each cycle ends in one pull request that a checking script may merge and deploy. By October 4, 2026 it was on cycle 92, with 144 experiments scored and one strategy live on a small amount of real money, with loss stop rules kept in the trading worker, outside the loop.
He sends his RingConn 3 wearable data to his AI email address. It sends back a dashboard and tips to improve his health.
While Julius was at the gym, his AI negotiated his Verizon bill from $296.71 to $246.77 a month. The $49.94 monthly cut totals $299.64 over the 6-month term.
He used AI to build an analysis of his own Substack posts. It split the posts into themes and pulled together collections, so readers can click through every theme, motif and term in one place.
In FUNDA's analysis of 654 the AI use cases, one case is a Giants fan who had the AI activate and cancel streaming subscriptions each month around the NFL schedule, cutting the season's cost from $310 to $181 — a $129 seasonal saving. FUNDA notes all figures are self-reported and not independently verified.
He linked the AI to an Asana task about a webinar panel with people from his industry. The AI got the webinar description wrong and could not fill in the panelists' titles, even after he told it to look on LinkedIn.
He has the AI run the upkeep on his main machine and his virtual servers: patches, cleanup, backups, and firewall checks. He reviewed about nine hours of its work sessions and says it may be the best systems administrator he has ever had.
A job seeker let the AI apply for jobs for him over 3 days, Sept 22 to 24. It sent 38 applications, all remote, mostly IT support roles, while he sent only 2 himself.
He gets 215 GitHub notifications a day, so he built a bot to triage them.
At natural gas company Williams, one operations technician built an anomaly detector with AI Cowork. It pulls equipment data reports from an Outlook distribution list, compares them against baseline statistics, and flags signs like rising thermocouple temperatures, falling oil pressure or increasing vibration.
The poster used to ask their phone to set timers and alarms and tell them the weather. Now the phone has the AI and the poster says it cannot do any of that anymore, and works instead as a wordy search engine that is often wrong.
She tried three AI tools and found the AI in Word the most helpful. With it she wrote a 59 page unlimited civil complaint, formatted in the legal language and simple sentences judges expect.
The AI is his gym trainer: he reports his sets and reps as he does them, and later that day Astra logs them into an Excel tracker, then uses the updated tracker to refresh an HTML app it built that shows his progress over time and his missed workouts.
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.