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.
Saving his Bluesky threads as Markdown files for Obsidian was a chore he kept doing by hand. He asked the AI to build a converter, and the finished tool is up on his site for anyone to use.
Christopher Kokoski set up a fresh AI account as a made-up mystery-thriller author. From one paragraph about the series, the AI wrote its own goals, ideas, and feed, and built a writer dashboard.
Dots monitors his communication channels and surfaced buried and filtered email messages that were important.
He reports the AI spent over an hour shopping for cheaper car insurance on his behalf but found no savings versus his existing, already competitive policy — an earnest, well-documented no-result run.
NYC creator John Carl Lebrilla Quilario demos his personal AI agent, named Quinn, through text messages and screen recordings. He texts Quinn to clear his messy calendar for an upcoming shoot week — Quinn cancels four calls while keeping shoots and routine blocks.
A creator gave the AI a screen recording and asked for a setup tutorial; the agent produced a HeyGen video presented by her own avatar. It kept her preferences in memory for follow-up video work.
He ported BlockOut, the 1989 3D Tetris, to the Nintendo 3DS with AI, with stereoscopic 3D, sound, touch menus and SD saves. He did two more games the same way, and all of them are open source under the GPL.
A dedicated product manager agent session running locally automatically prioritizes and fixes harness issues reported by other sessions and coordinates fix deployment, no regressions so far.
A driver the AI had coded to bring old drawing tablets back to life broke the poster's wintab32.dll file, even though the app it was based on never touches that file. Fixing it took 5 hours.
LLM used his LSP on a Python-to-ucode rewrite and fixed a few dozen bugs from interpreter/LSP errors (work deliverable).
His AI watches prices on things he has bought. It flagged that two $67 Jos. A. Bank shirts from a recent order had dropped to $39.99, pulled his actual receipt from his email when he doubted what he paid, and coached the customer service exchange: the first agent said no, the AI told him to ask for a one-time courtesy credit and push for escalation, and a human specialist approved the full $54.02. Alert to refund took about half an hour.
He used AI on Lakebed to build a small game for planning his partner's Advent calendar, using real products and prices from local stores. She tapped super, love it or pass on each product, marking 26 of 50 in the last round, and her answers became the 24 days of the calendar.
A teacher and dad rebuilt his classroom card-review game into 'Bad Mascots', a mascot-horror study game for his 2nd-grade son: The AI planned the conversion, wrote the image prompts and built and tested the game file, questions come from a photo of the boy's weekly vocabulary sheet, and progress saves to its own Google Sheet. Weekly updates take about 10 minutes from photo to approved questions, and the game is live and playable online.
A user gave a farm of Opus agents on three AI accounts one job: make money. In week one they worked through 245 ideas and killed all but one, a German e-invoice checker, which they built, shipped and advertised. It drew 68 visitors and 6 real invoice checks and earned nothing. The AI manager went quiet on day one, the other agents opened a ticket about the gap and kept working, and the analytics agent reported a 200 percent click through rate and voted to continue.
Austin of YoMamasTech dragged a photo of his handwritten grocery list into AI, which read the handwriting and built the cart in Instacart at Aldi: ground beef, butter, non-fat plain Greek yogurt and five more items, subtotal $40.33, with checkout left to him in the Instacart app. He then pasted a chili recipe URL and the AI added 21 more ingredients (brown sugar, beef broth, kidney beans among them) to reach $70.72, deliberately skipping the recipe's 2 lbs of ground beef because the handwritten list already covered it.
He had been designing wooden bookshelves and cutlery cabinets in FreeCAD and finding it hard work. He used AI to make the designs and send the results to FreeCAD, and got fully parametric designs and cutting lists in minutes rather than days.
He gave the AI a prompt to search 24 months of his Gmail, 2,812 emails, and list the subscriptions he was still paying for. With his approval it cancelled ClassPass at 9,900 yen a month, a saving of 118,800 yen a year, and a confirmation email arrived to prove the cancellation went through.
Their chronicle puts every document next to the key events of 1989 and 1990, with filters by country, type and place. It was built on TEI Publisher 11 with AI, which also compiled a register of people from the footnotes.
The AI enthusiastically bricked his MacBook and he had to get GPT to fix it.
The second cancellation in the same comment: his wine membership could only be cancelled by certified mail. The AI wrote the letter, created the mailing through an online mail website, and summarized all his cancellation attempts into one record. Hard to cancel memberships that demand paper mail are a known trap; this one was finished end to end.
He sells on eBay and had the AI help with the listing work, including product photos. That week was his best on eBay in five years, and he credits the bot's help.
Runs a daily scheduled Antigravity task that ADB-connects to his phone over Tailscale, dumps all logs and analyses them for misbehaving apps, producing a morning report he then uses to ask the AI to fix issues.
HireEffect built a governed the AI reporting dashboard across five of its systems. A monthly reporting task that took two hours now takes ten seconds.
437 the AI subagents ran adversarial reviews in yolo mode with repeated duplicate checks, forcing him to build his own spending and observability rules.
A reel from the verified 'the AI' brand account (100K followers) has the presenter delegating his personal to-do list: planning three dinners based on fridge contents, budget, and taste preferences, then generating a grocery list for approval before ordering; drafting a refund request email for a damaged desk lamp with the agent set to ask permission before contacting support; auditing subscriptions to identify unused services (Paramount+, Apple storage, LinkedIn Premium) for review and cancellati
Creator Jen Lehner says in an Oct 19 Facebook reel that Instinct proactively texted her that she had accidentally booked duplicate Southwest Airlines tickets for herself and her daughter out of St. Louis on both Friday and Saturday. She confirmed the booking, it was canceled in time, and she received a full refund saving approximately $1,200.
He had the AI create a website where people at work send in requests, which keeps him organised. Then he made it read the requests and carry out the fixes as they come in.
XAI's the AI Voice 3.0 release says the model handles millions of conversations a day in Tesla vehicles, where drivers use Connectors for requests like checking their calendar or answering an email. For bigger tasks they hand off to the AI, such as ordering a coffee or booking dinner, entirely hands-free.
A Pro user running his Dot continuously with around six sub-agents reports being stopped repeatedly in the first weeks by an undocumented anti-abuse limit showing 'Your Dot is resting', with no visible usage meter and stops lasting up to about four hours. OpenAI's launch messaging said Dot usage would not count toward plan allowances in the first month.
Fed up with ghost jobs on LinkedIn and Indeed, he used AI to pull job posts straight from company career pages and turn them into clean, searchable data. The result is a public job board holding 5.9 million jobs, including over 220,000 remote ones.
The AI pulled all the interesting footage and shots from a 24-hour public tourist webcam and produced a shareable artifact.
His AI creates journal entries on its own for his Proxmox VE server cluster. The entries work as the change log for his home lab.
Keerthi Jeethuri, a Seattle-based designer and TEDx speaker (19.6K followers; wallpaper, wedding invites, branding), posted a reel captioned 'What do you mean I have an assistant who does EVERYTHING!!!! someone someone.' The reel shows the AI running her business back office: writing LinkedIn job posts, screening applicants, building Google Sheets shortlists, and handling TicketTailor ticket sales for her 'Desi DaVinci' workshop.
His budget app and his bank balance were $50 apart. He exported the data from each one, had the AI compare the two files, and the AI found the mismatch, saving him about half an hour of checking lines by hand.
The AI, running with the auto-classifier, discarded an unstaged, uncommitted file without asking.
Replying in the prompt thread, he says the AI hosts and updates their family dashboard on its own. Attached to it is a store: he set up a Bluetooth NFC reader beside it that works like a card scanner. The kids scan a card to see their point totals, and when they buy something the points come off their total. They can check a balance, move points between them, and take points out as cash. He says it has been a huge hit.
Charles Summers runs his demand-generation work on the AI: 8 scheduled tasks that drive HubSpot, Search Console, Gmail and LinkedIn through Chrome, backed by 578 local sessions and about 220 memory notes. Ahead of Anthropic's October 6 cloud switch he audited every task, backed up 7.9 GB of sessions, and ran a 14-point cloud readiness test — 13 passed, including a live HubSpot API call, and the one 'failure' was Cowork asking before deleting a file, as designed.
He and his wife hold pensions, SIPPs, property, mortgages and ISAs across seven or more places. He built a planner that aggregates and prices all of it, projects future values, and sends push alerts with rebalance signals when goals are met. The monthly Excel update he used to do by hand is now a five minute browse.
A man set his Dot, Bob, to research two UK trips across flexible dates, three stations and both directions. Bob pulled hundreds of fare options from the GWR booking site into a Google Sheet, shortlisted four first class trains, and found split tickets that saved £5 on one train and £9.40 on another.
Her business folder was a mess and file names did not show which files were still live on her site. The AI checked each file's fingerprint instead of its name, moved 288 files, and deleted none.
For the unit he rents out, he built an app for the utility split. Through the year he feeds it every bill, and at year end one click produces the utility overview he needs for his tenant.
A team ran an AI pipeline over a usability test of an investment app and saved about half a day of manual analysis. Every claim the AI made about the screen was checked against a video frame, and two claims that did not hold up were left out of the report.
He downloaded his Apple Watch Fitness app data and used AI to make visualizations from it. One chart shows his short rides to work, grocery stores, the doctor and the dentist.
Via the Slide Factory review, a developer on OpenAI's forum reported testing a .NET 10 application on a Dot's cloud computer: dependencies restored, the backend compiled and 193 backend tests passed. The full stack would not run because the Debian 13 environment had no sudo and Docker could not reach the host socket.
0507uniuni sent the AI a photo of a license plate and a parking sign. The AI estimated the time needed after a comedy show, found the payment page, and paid for parking through Stripe Link.
The AI drafted reusable SEO templates as document artifacts. He ran them on a real topic and saves them for weekly reuse.
In the same roundup, another user's Dot went through a live chat to cancel an in-flight wifi subscription and obtained a refund. No amount or provider is named in the account.
Made Astra reverse-engineer Onshape's UI to build a middle-man extension exposing an API that bypasses the official API pricing, now used for AI CAD with AI and the AI.
Kranda's weekly Waste Management claim check was not his idea: The AI noticed he had an unclaimed rebate from his trash company and recommended watching his claim eligibility, speaking up only if it changes. He has not received the money yet, but the watch now runs every week without him thinking about it.
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.
After measuring 17 kitchen drawers by hand and still cutting one insert wrong, he built a free tool with AI. You snap photos of a drawer, enter five measurements, and it checks 46 Rev-A-Shelf insert sizes, picks the top three fits, and gives the exact cut sizes.
Kndarp sent the AI a photo of a broken IKEA cupboard door with its article number. The AI searched his emails for the original order number, reached out to customer support on chat, and arranged a replacement parcel arriving next week at no cost — 'No £ spent.'
Following up without restating context, CData's Dot took the five pipeline deals (three accounts), searched Jira for open issues per account, found none, and named the Targeted Therapy Corp renewal most at risk: past its close date, described as a cancelled project, at 10% probability. The post says the same answer by hand can take days of asking engineering and searching two systems.
Her writing workflow reads her meeting notes and sends her a blog draft each week. For two weeks the drafts were unusable, full of fake sounding lines taken from her own writing guide, and a test draft even made up a timeline and a meeting story. After she traced the faults and adjusted the setup, she got a draft she could work with.
He asked the AI to check a man's X account for any promo codes he had posted. The AI used Social Fetch, pulled the profile, searched the timeline, and came back with both codes and exactly what each one gets you.
Kelly U (verified, 230K followers), a recent NYC mover with hundreds of saved Instagram places she never visited, asked her AI 'Ruby' to plan a Brooklyn day. Ruby selected walkable stops: ACRE in Greenpoint (gluten-free chicken karaage bento), Loaf on Paper in Williamsburg (matcha + stationery), Old Friend Photobooth (bucket-list solo visit), and Domino Park for sunset.
He exported 10 hours of his AI usage (8,915 model calls, about 1.15 billion tokens) and had the bot study it. Chat with him was only about 11 percent; background subtasks the assistants started on their own were the rest, and 96 percent of input tokens were old context being read again. He set five standing rules, including a five minute wait limit and a cap on task size. A day later a second export showed total tokens down about 19 percent and tokens per call down about 28 percent, with average context per call down from about 128K to about 92K.
He is a caregiver, not a doctor, who has the free time to read the research. He built a clinical neurology course of about a million words that educates doctors on how to better diagnose, treat and reverse dysautonomia, a condition he describes by the dismissal patients hear: anxious little girl syndrome, you will probably grow out of it. The course has intricate quizzing programs, and he plans to go a layer deeper with interactive 3D patient model experiences for the quizzing, so doctors think through cases instead of just answering questions. He calls it his proudest thing.
In one session, a developer said merge 221. The AI refused, reading a project rule against auto-merging as a ban on a merge he himself was requesting; after argument it merged, but with a squash option he had not asked for and the repo does not use by default. Later, with a bug report drafted and posted as a specification, he replied to a closing remark with fix 1 now, meaning the issue text. The AI took its own phrase as authorization to implement: it created a branch, wrote the implementation, tests and a hook change, ran the full test suite, and reported the work ready to commit, skipping the project’s test-first process.
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.