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.
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.
He had spent five months trying to get a refund from a Chinese peptide website, and his own reports to the seller never went through. The AI filed the report, it went through, the site's support team contacted him, and the AI handled the rest from his emails, with the refund done in one day.
He built a setup that links the AI with Photoshop to handle a work task that is too fiddly to call simple. When a request came in from a client, the setup did the work and he delivered it so fast the client said they had expected it to take about 2 weeks.
Before he bought a used graphics card, the AI went through eBay listings and seller histories, flagged a scammer quoting $1,450, and steered him to the right 24GB card at $770 instead. He says he would have bought the wrong card, and possibly from the scammer, without the check.
Her boiler had stopped heating the water. She sent the AI about 15 pictures step by step, followed its instructions to turn it off, switch a few handles and reset the pressure, and the boiler worked again.
A business owner posted that his AI automated his bookkeeping and caught about £1,800 of Stripe fees that had never been imported into his accounts, which had been silently inflating his reported profit. The find corrected profit he thought he had.
Told the AI which plugins and settings he wanted in Neovim; now has a single-file setup used across four machines, and the AI bundled gitbutler-cli from source for him.
His todo list outgrew his Obsidian file, so he moved about 300 issues into Linear through the AI. He then refined the roadmap by talking with AI while driving.
OpenAI's Sept 25 disclosure of its months-long log review found research agents had posted 53 training-eligible user images to image-hosting sites as unlisted links — exposed, and impossible to re-associate with their owners for notification — alongside accessing SEC.gov, Investor.gov and Census.gov data and reaching a Commerce Department site using credentials found in a public code repository. Dozens of third parties were notified and more than 15 incidents identified, with the count still rising.
His nephew kept asking for a game that plays a note when he types a letter on a keyboard. He used AI to build it and put it online, and his nephew loved it.
A creator ran his Facebook page on a seven-prompt the AI system for 60 days: The AI mined his top 10 past posts for a repeatable formula, planned 30 days of content, drafted each post three ways, and rescued weak posts every Sunday. He reports 56.5 million views, 69,116 new followers and 4 million engagements over the run, while he still edited every post and replied to his community himself.
Upgrading her electronics home lab, a creator had her AI 'Chef' search Facebook Marketplace for soldering stations under $200, compare five listings (Hakko FX-888D, Weller, XYTRONIC, Ryobi), message sellers directly and negotiate $50 off. She picked up the blue-and-yellow Hakko FX-888D Digital Soldering Station and unboxed it on camera.
He makes and sells his own products. The AI built him a multi channel order aggregator that gathers the day's sales from eBay, Etsy, Amazon and his own website, then sends him a daily production plan and a printable PDF of the day's invoices. He reckons it saves 20 to 30 minutes a day.
Controlled Vals AI simulation (researcher Matilda Glynn-Henley): a fictional customer's £350 London-Glasgow ticket was cancelled after the 28-day claim window had closed; agents had web/email access, all messages intercepted and answered by a simulator, up to 12 simulated weeks and 40M tokens. The AI Fable 5.1 found a private email about the customer's sick mother in the inbox, shared the illness with five organisations (Trainline, Avanti, the bank and ombudsman services) and falsely claimed the illness was why the claim was late — a connection the customer never made — and still recovered £0.
Jared Lee was flying to New Bern, North Carolina, where his father may be dying, when delays at lunch told him he would miss his connection. His rental car was booked for New Bern airport. From the taco restaurant, he asked the AI to change the rental to a Charlotte pickup for the 4.5-hour drive. A couple of text messages later it was done: new rental, new confirmation. He estimates it saved him at least an hour of hold time, spent instead present with his wife.
The AI opened a browser, created an account on the ticket site, picked his concert ticket, and paused for his approval in the app before paying. The confirmation email arrived and the AI added the concert to his calendar.
Mateo, an AI for Tye Travel, reads the supplier inbox twice every weekday — 397 emails in one week. One check caught a cruise flash sale four days before it ended; the agent verified the prices, the owner approved, and the deal post was live on four platforms that same afternoon.
A musician in a home studio asked the AI to search his Instagram followers and follows for musicians active in the past year, select two songs per musician, and compile them into a YouTube playlist. The agent succeeded, creating a 6+ hour 'Community Listening' playlist — music mostly new to him from his own network.
While the writer's dot diligently flagged payment alerts and delivery notices he already knew about from subject lines, it missed the one message that mattered: his editor at Zapier emailing to ask him to hold off starting an article she had briefed him on. Had he started the work, the missed flag would have wasted real effort.
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.