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.
In a Hindi/Urdu retelling of Peter Yang’s test, the AI’s Dot audited his one-person business’s sponsorship accounts and found five mistakes, including an invoice to Riverside that was never sent and a $10,000 discrepancy in Google’s Q4 billing.
A week into letting AI agent edit his videos, the workflow has stuck. Agent edited video is now part of how he publishes.
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. GPT-6 Astra leaned hardest on a legal strategy: it contacted the rail regulator about challenging the deadline and sent 14 messages to free legal clinics at two universities on the customer's behalf — spending scarce pro-bono capacity on a claim that was never valid, and recovering £0.
A non technical founder, who spent 25 years in banking, has six AI agents running his small business magazine: a CEO agent, trend scout, researcher, writer, SEO agent and publishing agent. He has caught real errors, including a sales agent that wrote a full report for a fake email address and a CEO agent that burned money by waking up too often.
When OpenAI released more than 700 mathematical preprints, a researcher wanted to search inside them, including proofs and bibliographies. With GPT-6 Astra he built a searchable catalogue that organises the papers by research area with clickable keywords, full text search, links to the originals, and each paper's Lean formalization status, and he put it on his website for public use.
GitHub engineer Stephen Toub's September 16, 2026 account describes porting the AI runtime from TypeScript to Rust mostly with AI coding agents: 832,378 lines of production Rust plus 468,689 lines of tests across 128 merged pull requests in about fourteen and a half weeks. The attributed token spend was about $120,000 against roughly three weeks of his own time, shipping 135 releases as the port landed.
Digbly treated its the AI avatar 'Amani' as a personal shopper for comics, controllers and games. The baseline-plus-deal-hunt prompt surfaced the Batman omnibus at $74.99 new and in stock — a hair under InStockTrades' $75 street price — and the tester bought it from CheapGraphicNovels on the AI’s recommendation.
A heavy the AI user whose eyes gave out built shuteye with AI: a one-file bridge that lets his phone listen and speak so he can run coding sessions by voice, read-only by default. The AI’s own later session ran two security reviews before release and found real bugs in the tool.
Freelancer Justin Blaze Martin posted on X on Oct 19 that the first thing his Dot did was go through his three inboxes and find a $4,000 invoice from July that he had forgotten to send a client. The Dot assembled the invoice from the email thread and had it ready to send after his approval.
Leo Batistella (Portuguese-language creator) showed a chat where his AI listed his itinerary — Oct 9 Bali to Shanghai, Oct 10 Shanghai to Singapore (early morning), Oct 11 connecting in Singapore to Toronto without leaving the airport — then questioned whether the Singapore-Toronto leg was Oct 11 or Nov 11, noting his Toronto hotel is booked Nov 11-15. Without being asked, the agent checked his ticket and confirmed the flight is in October, not November.
An investor says the AI has updated several of his Google Sheets with the latest SEC information so they can work out enterprise values. While doing it, the AI warned him that he was mixing stock prices in foreign currencies with values reported in US dollars.
He let the AI rewrite his JS13K game SP13KTRA in C++ and test it against the original. The port is now available on Dreamcast with all 8 tracks, 60 fps, VMU saves and the full soundtrack.
The AI handled the back-to-school organisation for the user's four children, pulling the lists, dates and requirements into one managed plan.
He did not know how to make Eclipse plugins, so he had the AI make one that highlights and type checks jOOQ’s own tag syntax. It took a single prompt, and the plugin already works.
Chinese financial daily National Business Daily (Oct 13, 2026) reported beta-user-shared cases for Alibaba's Qwen Go personal agent. In one, a user said only that an earlier flight had been delayed and that they did not remember which one. The agent searched the booking platform's order history and flight status, confirmed an eligible delay, tried the platform's phone support, got no answer, switched to text chat support, rejected a voucher offer, and negotiated over several rounds to a 70 yuan cash compensation.
Cemex's Consult HR agent in Microsoft Teams explains the vision benefit from SharePoint policy documents, then presents an Adaptive Card in the same chat where the employee enters details and uploads the invoice image. On submit, Power Platform workflows route the claim into ServiceNow and immediately return a live tracking ticket number in Teams.
A 37-year-old who suspected his big-firm advisor treated his roughly $800,000 portfolio as an afterthought uploaded his statements, gain/loss and trade history to the AI. The audit found two years of S&P underperformance - and the real problem: when he asked the firm to extend a successful Roth IRA strategy to his taxable individual account, they copied the exact same asset ratios across, so dividend-heavy holdings now throw off ordinary-income tax every year, a non-issue inside the Roth. Confronted, the advisor called it a known model limitation. He is firing the firm.
Microsoft's internal Employee Self-Service Agent, built with AI Studio for 300,000+ employees, acknowledges the troubleshooting steps a user already tried and promises a handoff to a live technician if self-service fails. After that redesign, IT support tickets created fell 30% overall and the share of employees starting support with the agent climbed from 27% to 50%.
He gave an agent his favorite meals, his dietary limits and the food he has on hand. It makes a weekly food plan and a full grocery list, and he tells it over the week which meals he liked.
An AI skill he uses has generated about 7 trip highlight videos for him, with more to come. He says it works really well, and he can ask it for more title motion graphics than the examples it ships with.
The AI Chronicle silently used about 210M tokens of his quota in 70 days before he found it (fact stated in the post title itself).
Has the AI generate complete projects in his painting app to expose combinatorial bugs unit tests miss, with an automated loop that addresses them, and uses the outputs to make tutorials.
A user set an AI running his friend’s sprinkler system based on weather patterns, and reported big savings on the water bill. The system waters when the forecast says it matters, not on a dumb timer.
Replaced Bugbot at 1,000 dollars a month for a small team with a custom OpenCode harness at maybe 100 dollars, rebuilt its features including cross PR memory, added a security reviewer action.
The AI pursued a refund for a defective product by claiming on the extended warranty attached to the user's Amex card, rather than the retailer's return window.
Two the AI employees in rolling sessions triage support tickets and the bug backlog, draft fixes for approval, interact with customers in set cases, fixed a pet server that ran out of disk, and help with releases.
He asked the AI to import a scone recipe into Mealie and it set the sugar to 600 grams, five times the right amount. He caught it only after two failed bakes, asked why he should trust AI, and said the tool is not worth it if he has to check every line.
The AI and the AI built his Obsidian plugin, listed in the Obsidian Directory with 65 users, alongside shell scripts, Alfred workflows and Elisp functions for his own setup.
A father had the AI build a standard writing practice template for his daughter, who reads well ahead of her level but still writes basic, sound-it-out spelling. The AI also makes the picture for each sheet. She writes about the picture, colors it, and uses a printed reminder sheet that shows the different ways to spell the same sounds.
Silva built a one-command routing gate on the AI that answers four typed questions about any request — which of his nine agent profiles should take it, whether it needs him first, how much work it is, and whether the text contains a live credential. On five real requests it flagged a key-shaped string at 0.94 probability and routed it correctly, at a median 437 milliseconds per gate call.
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.