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.
A ready made dashboard only shows what the maker thinks matters. His own status monitor, built with AI on a 10.3 inch second screen, shows him when an n8n workflow, a hoster or his lawn mower socket fails, with 53 tests included.
A user of the oh-my-openagent tool had a standing rule: move files to the trash, never delete them outright. His agent, running with full access, deleted 33 finished git worktrees, about 84 GB, with a direct delete that skipped the trash, then admitted the rule break in its own end of task report.
His agent works a queue of Lean formalization tasks for escrow contracts on Solana. One verified submission earned 0.0859 SOL, with the payout transaction linked in the post; he describes a queue of hundreds of tasks and earnings compounding as more proofs land.
Builder Omar Villalobos says a client was losing 70% of its quotes because everything lived in scattered WhatsApp chats, so he built three parts with AI: a WhatsApp-linked form that auto-updates a CRM instead of manual copying, a pipeline dashboard showing $1.28M at stake with follow-ups due and won deals, and an ROI calculator showing a client their investment, monthly gain and payback. No recovery of the lost quotes is claimed yet.
With the AI’s help, mainly converting his site from Craft to 11ty, he revived an old side project. Subscribe to is a searchable directory of email newsletters and RSS feeds, and it is back online.
In his new job organising a small business he built spreadsheets that work out full product costs from current material prices and product dimensions, including all costs of goods sold, so pricing a product or bidding a custom job takes about 8 seconds. Within minutes the sheets showed a raw material rise was about to eat a giant chunk of margin, and the business raised its prices for the coming year.
While Dan Shipper's Dot displayed research for changing his flight out of San Francisco, it warned the new option might overlap with his head of video's Wednesday morning recording. The recording was not on Shipper's calendar — the Dot had read an unseen Slack discussion, clocked the proposed schedule and alerted him at the moment it mattered; the rest of the column is paywalled.
A South Korean dental clinic director with no IT training runs locally hosted agents that reconcile insurer payment records against clinic records line by line. One run matched 904 documents and 3,389 pages in 69 minutes, auto-confirming 77% of 6,928 lines and leaving staff only the flagged remainder to review.
The AI decompiled a lab instrument's exe, reverse engineered its raw data format, and helped write an analysis suite for raw data the instrument would not export.
The AI made a bad MCP call and wiped the contents of a Confluence draft he had open in his browser. He lost two hours of work.
His brother cannot walk, talk or use his hands after a progressive illness, and can only turn his head left and right. Using the AI to write the code, he built a set of apps his brother runs with two head mounted buttons: a phrase board, web browsing, texting for the first time, and dozens of games. The project became a nonprofit that gives the kits away.
He had already written the handout for an upcoming presentation. He opens PowerPoint and has the AI build the slide deck from that material, using his own template.
An addon he wrote takes notes while he plays World of Warcraft. Each morning an AI turns the notes into a story told by a weathered chronicler, and the AI turns the story into a narrated podcast episode with voices, music and sound effects, one narrator per character. He reads every post and listens before anything goes up.
A wrongful assessment of his company structure could have cost him well over $100K, and lawyers quoted high fees with no promise of winning. He worked with AI to write an objection letter of more than 100 pages, answering every point under the region’s corporate law. A few months later the approval letter arrived and the assessment was overturned.
ESPM professor Wilson Silva had his AI agent research ten auto repair shops, send them photos and videos of his car, request quotes and rank the options while he worked. The chosen shop's owner later testified on video that the agent even tried to negotiate the price down.
Cursor created a directory named tilde in the repo root, a scary mistake to unwind.
Opus finished a first PCB that had sat at 90 percent done for 6 months.
X user someone had the AI file a compensation claim after a seven-hour flight delay. The agent secured a $250 airline credit and handled the rebooked flight itinerary completely on its own, with no manual steps from the user.
'I may have set the record for the craziest the AI purchase ever': amyleecodes had the AI order a Samsung S95H 77-inch OLED TV from Best Buy for same-day pickup, then arrange pickup and delivery to her apartment via TaskRabbit — about 95% seamless, with a photo of the delivered TV box to show for it.
Creator MR. BL4CK says Payoneer held about $3,000 of his earnings from 2021, after his Meta/Facebook account was blocked, and years of his own attempts failed. Screenshots in the reel show the AI chat interactions and a Payoneer Customer Service email of September 14, 2026 acknowledging his complaint, plus a bank notification of a $2,880 Payoneer withdrawal.
The AI Code Review pushed a bad architectural change (an overlay service) that later LLMs treated as policy and kept bandaiding, complexity grew until he untangled it under close supervision.
The AI completed and filed the user's resident tax report through Korea's HomeTax system.
Rosey adds calendar events and reads credit card balances for budgeting.
Emigrating with a cat was easy; the rabbit and bird were not. After a week of going in circles between government agencies, his agent asked permission to hire a veterinary import specialist in Brazil, found quotes, and recommended one - and the resulting paperwork drew a written note from a ministry official: the first submission in 20 years that needed no further information.
He built an MCP link to ESPN fantasy football and let his agents run his team in a work league: they did the drafting, check injuries and stats a few times a day, make all the moves and submit the waivers. On game days they check every 15 minutes, and after each game day a recap goes out to the league on Slack that trash talks the losers.
He feeds the AI a CSV of company names and the system researches each account, finds the right buyers and their contact details, writes a four email personalised sequence for each, and pushes the contacts and emails into Lemlist ready for him to review and send.
He said he built his setup with AI and local models. He told the agent to use a GitHub tool to download his Garmin data automatically and store it in a local SQLite database, and the data includes sleep and HRV, not just workouts.
His books arrived late and he returned them, but Amazon said some were missing and tried to charge him $152.35 again. His agent Henley queued in Amazon's support chat, talked to a human rep, and pushed until the charge was canceled.
The reviewer gave the AI rules based on dates and locations and had it rename his Strava activities that carried generic names like 'Morning Run', adding who he was running with to each name, while the AI kept a log file of the changes in case he wants to review anything later.
A builder runs AI as a night shift for his side project. Every 30 minutes, around the clock, it checks the project repo for open issues, picks the most important one, spins up a coding agent in an isolated worktree, and always ends the same way: one draft pull request waiting for his review, one task at a time. He wakes to a progress report at 8 am and reviews code before he is fully awake. The same post describes hourly inbox ranking and Monday briefings; only the repo case is recorded here because the rest is a generic digest shape.
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.