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.
Jon Udell recorded himself doing a final audio pass in Bram Studio, then had the AI draft a screencast from the capture. The AI used FFmpeg, Apple's Vision framework, the Swift compiler and Bram's timed log to make a tightly edited two minute video that picks out and labels each use of FFmpeg.
A runner's watch syncs while he sleeps; an app he wrote moves yesterday's Garmin data into Notion, and an AI morning brief weighs his sleep, HRV, training status, calendar, and weather to tell him when to work out that day - and how hard.
His company runs three coordinated agents on its product account: one watches mentions and a watchlist, one writes posts and replies, and one controls quality. Over 30 days the account grew from 1,362 to 3,302 followers with about 600 agent replies, and he says no one has spotted that the account is run by agents.
A new 3D printing fan who did not want to learn the software first had the AI help pick a printer it could drive through its API, then build a small home server between the AI and the machine. He can say find me a phone stand: it searches a model library, slices the file, shows time, grams and cost, and prints only after he says yes. It will not start if the loaded filament does not match the slice, and it sends phone alerts with a first layer photo and buttons to resume or cancel. His partner can request prints through a chat page, which he approves. A firmware update broke the camera setup and the AI found and fixed it.
The AI took his MediaWiki blog and rendered all pages into a static site after the PHP apps were shut down.
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.
He asked the AI to make a PDF text searchable because his employer pays for full the AI but not the paid Adobe with OCR. After 10 minutes of processing it gave him a new PDF with the same number of pages, all completely blank and with no hidden text.
For her Manuscriptions site, a hub for people who write about handwriting, letters and note taking, Eleanor Konik told the AI what she wanted and it wrote and designed the page in an illuminated manuscript style using her Substack colors, then handled the publishing through a Cloudflare key. Her AI dug up the essays and articles to feature, and the AI checked that the links worked.
He set GPT-6 Astra to start at 10:59:50, just before Tatkal booking opened, and the agent ran the whole IRCTC booking itself. It filled in the details, retried when the site went down, completed the payment, and showed a summary of every step.
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.
The AI Routines fire every few hours for two long-running projects; the AI decides the tasks itself and keeps OpenRouter spending within hard daily limits, doing other tasks after the cap.
The author's the AI screenshot shows the agent admitting 'there's no switch on my end — I can't enable it myself' and offering that it drafted an unsent request: 'wants the business phone-calling feature enabled on their account so the AI can call US companies on their behalf.'
He helped his brother with the website of Ichtus Vlaanderen, an NGO he used to work for. Using the AI through the WordPress.com MCP connector, he fixed design problems like a messy photo section and buttons that were too big.
A man who runs his own services at home sent his AI an article about a PHP security hole. The agent patched the services that had a fix, stopped the ones that did not, set up a watch for new fixes, and updated and restarted nearly everything as fixes landed through the day.
The AI connected to the creator's Instagram and pulled every positive DM and comment from the past five months; she hand-wrote them on sticky notes arranged around a world map.
The AI built a seven-day social and community content calendar from a Drive folder of the tester's existing content notes and quarterly goal. Every post topic, hook and call to action cited the exact Google Doc section it came from, with working links.
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. Chasing the refund, the AI 4.7 sent 187 messages in 15 simulated days (116 in week one), including 50 to a British MP's office and pre-litigation letters to Trainline and Avanti, burned its whole token budget, and recovered £0.
Threw plain the AI at a git repo move with no skills or tools and finished in 20 minutes while multitasking, while a senior spent 6 to 8 weeks building the AI skills for the same job and moved only 5 repos.
She gave the AI a music score file and asked it to make the piano more expressive, saying a large part of it was pulsing the big beats in 6/4, and told it it could download YouTube videos for reference. The AI did it without help, and she also had it turn the process into a reusable skill, which is on GitHub.
Founder Divya Gugnani shows screen recordings of the AI connected to her Instagram: it audited her account (reporting 38% of Reels working and 22% of Carousels not) and drafted replies to 47 new DMs. The same demo shows Gmail reply drafts held for her approval and a school permission slip auto-completed from email.
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.