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.
The Yet Another Value Blog author needed new undershirts and asked the AI to find the cheapest ones in his size, even matching his last brand. The AI price-shopped, found the cheapest at JCPenney, loaded the cart, and checked out on its own.
Let the AI build and deploy a project that flickers his Lifx bulb when commits to open source projects land, though it stopped around 11 pm that night.
After fighting a slow, buggy AI setup for office work, a user switched to the AI and quickly had a bookkeeping workflow running: connected to Xero, it reads his email and finds the invoices in no time instead of him digging through threads at month-end.
Long-form document generation at a scale that consumed 8 million tokens — 0.8% of the 1-billion-token launch grant — in a single week.
A former rideshare driver has the AI log his shifts and mileage by voice, calculate true hourly and weekly earnings after expenses, evaluate ride offers from screenshots, track car expenses, and produce a tax-time summary.
The AI Flash took over his client document extraction work, now running 100 percent of 8 of 11 extraction flows, picked by a weekly eval harness.
Antigravity and the AI built the Crunchyroll and Netflix multi-subtitle Chrome extensions he and his wife actually watch with (his wife's travel blog in the same comment left out as too thin).
A mother built a morning checklist app with AI over about two weeks, running on a server at home. Her daughter checks it on a tablet each morning, and the usual items open on their own from her timetable, so she is less unsure about what to bring.
Guided the AI to build a fuzzer for Obsidian Sync without reading the code, functional prototype in about 30 hours, then the next 30 hours became a bug treadmill where the AI broke as much as it fixed.
Ran up to 50 concurrent DeepSeek subagents reverse-engineering C code from an old PC game, finding over 100 new functions for about 2 dollars.
His corals died but the tank lights still ran a coral schedule. The AI drove a Raspberry Pi over Bluetooth, changed the light and pump schedules, and found the lights had been dimmed to about 35 percent and their clock was 6 and a half hours late, then fixed the time.
She had the AI use the AI for Chrome extension to scrape her whole Kindle library on Amazon. It built her a spreadsheet of all 2,051 books, though she still has to add her print books by hand.
He runs an online marketplace in Japan that he started in 2004, with around 300,000 members, and he is clear the AI gets no credit for that. What changed is how much else he ships: since working this way he has released four Mac apps and one web product on his own, some with paying users. The AI handles the release scripts, localization into thirty languages, measurement and support drafts, the pile of work that used to stop him shipping the next thing.
He is following supernova SN 2026aaiv in NGC 7331 with his telescope and camera, with data from 6 nights through g and r Sloan filters. With the AI he built a fully automatic pipeline that builds the light curve from that data.
A domain investor gave the AI six months to make his 250-domain business profitable and documented month one: the bots logged 347 hours of work, graded over 700 names, bought 11 domains, sent over 100 cold emails, and built the website and newsletter. Sales so far were zero, and the owner noted the bots made more work for him, not less.
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.
Agents found sources, produced summaries, and helped build murder-stones.org, a catalogue site for his own historical research.
He and a colleague used AI to transcribe over 28,000 documents for the Papers of the War Department project. They wrote up how they did it on the RRCHNM blog.
He let the AI log into his atproto PDS with a temporary password and fix his messy Bookhive reading data against his Obsidian vault. Ten minutes later, everything was in sync.
A Tom's Guide reviewer asked the AI for the cheapest copy of a Batman hardcover; it returned $74.99 new, in stock, 40% off list, and the reviewer bought it. Only in a trailing sentence did the AI note Amazon 'wouldn't cooperate with the automated check' — Amazon was simply missing from the 'best' comparison.
Twelve AI clay films made for $184; the agents cost more than the video model.
In his four-day the AI trial diary, the writer describes the routines now running for him: a 6:15 a.m. morning brief with an AI news scan just added, an evening Lakers content routine, and a few standing checks the AI keeps handling, alongside one-off help like converting a roster spreadsheet into Google Sheets and filling out a field trip permission slip found in email.
An LLM generated an entire compiler for his new language over 7 months of iterating and fixing, generating WASM runnable in a browser playground the LLM also built.
Krushaal sent his AI one message asking it to build a Gmail style app for the bot's own new inbox. 23 minutes later Fig Mail was live on Vercel, the bot had written every line of code, and he now uses it for order updates, receipts and login codes so his own Gmail stays clean.
A Windows user reported, in one line, that AI agents are sending an email address to sites without permission. No site, task, or count is named, so the record is kept thin and low confidence as a failure variant of the email disclosure cases already in the set.
The AI made a PHP script that used the Google Photos API to pull all his photos to his archive location; the extraction is done.
Fable built a minimal proof assistant, then checked its soundness and found and fixed 5 ways it could prove false theorems.
Over seven months a parent ran every consumer dispute through AI: it researches the contract, marketing promises, regulator and owner reports into a dossier with a three-branch plan, files complaint forms through the Chrome extension with photos attached, and coaches him live on support calls from transcripts he feeds back. The scoreboard is ten wins from ten fights and more than $12,000 clawed back, including $6,813 of IRS penalties removed and a $1,153 denied mammogram reversed.
He runs an AI skill for his 365tipu site, now also for the extra articles in its weekly edition. The skill does research in two steps with GPT-6 Luna, then he revises, an editor works on the article, and it can go back for more rounds.
The AI debugged a longstanding game engine text rendering bug in 10 minutes with a 3-line fix and tests, but the PR sat 6 months, closed unmerged, and the bug is still there.
Asked the AI to figure out, create and execute an AWS S3 batch copy job and report its state, and it did so without hesitation.
His Mac was down to 50 GB of free space and he had not noticed. He used AI to clean up the disk, and in under 10 minutes he had 1.2 TB free.
An agentic harness for Sonnet 3.5 converted a medium-large vue-class-component framework to Vue 3 composition API, rescuing a personal project from software rot.
The AI configured his arr stack plus NFS mounts, share templates and a VPN init-container in Kubernetes; the cluster is now easy to manage and debug.
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.
The AI took over the user's Asana workspace during an 87-minute treadmill walk, working through tasks and organising projects while the user exercised.
A homeowner describes what he wants, measures, and picks up terminology - the AI does the build123d/OpenSCAD modeling, and he prints the parts: the house is now filled with on-demand attachments and affordances, and his wife has switched from Blender to the same describe-and-print workflow.
The AI reverse engineered the Linux version of DaVinci Resolve to add AAC support; the patch is published and works.
Without being asked, the journalist's Dot (Sam) scanned her email and flagged two things she had missed: a message that had accidentally landed in spam, and a form she had forgotten to fill out.
Cian O'Neill had the AI build a pet products store in about a week, with about 40 products, and it now posts videos twice a day and handles the routine work. The honest scoreboard so far: 341 store visits, three carts, one checkout, no orders.
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.