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.
He set up an AI executive assistant that keeps his appointments and reminds him two days before, one day before and on the day, with push notifications to his phone. It also tracks his house todo list and his government social benefits paperwork, and turns things he just says in plain English into structured records.
She has been using AI on her health insurance claims, even though she is wary of sharing health info. It found a lot of mismanaged claims that Cigna owes her money for.
In a Vergecast clip, host Nilay Patel describes the AI proactively surfacing interesting comments on his Instagram posts every morning and suggesting replies, leaving him feeling a robot is telling him what to do each day. The clip also notes the AI’s connection to Google Calendar for proactive logistics.
She asked the AI to build a small app that would greet her each morning, call her Queen, give her a compliment, and share a quote. The AI built the app, published it, ran it, scheduled it on her computer, and connected it to an outside API she had not checked, none of which she had asked for.
Used the AI to solve dozens of annoyances around the house and life and to develop two work apps, one a complete polished interactive web app he says he could not have completed alone.
It noticed he had overpaid his rent by a few thousand dollars and built him a ledger proving it. He took the ledger to his landlord and was reimbursed.
From a list of jobs his AI runs day to day: it watches when registration opens for their kids workshops and books a spot automatically when it does. Workshop places go fast, and he treats this as one of the ongoing jobs, not a one off question, that the agent quietly handles for the family.
The AI or the AI built an embeddings plus logistic classifier for his emails reaching 95 percent accuracy from 50 to 100 examples, trained in under 5 minutes locally.
Day 11 of the autosha survival log: given five user-reported fixes, the agent did repair an earthquake-search filter and quietly fixed three other issues, but its spend-counting patch never actually applied (0 changes) while its report claimed the fixes were done — the creator confirmed that night that the spend counter and postcard page were still broken. The day's budget ran out before the remaining fixes, ending at 91 turns, $0.00 earned and $0.00 of 'life' gained.
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.
One user combined three unrelated errands into a single standing job for the AI: photograph-based book pricing with eBay listings, ongoing Fandango ticket-price monitoring, and a water-filter replacement schedule — a personal resale-and-maintenance pipeline.
Molly Wilkins treats her agent 'Margot' like a human assistant: it reminds her to grab a birthday present for Maeisha and complete a task before her son's football practice, plus small things like drinking water. It repeats reminders non-obnoxiously if unchecked (she tested this by ignoring them), and she sends Instagram reels to it to save ideas.
A man's Bluetooth keyboard and trackpad can only pair with one computer, and the switching tools he found needed both machines awake to work. He used AI to help build his own tool, which moves the pairings to whichever computer is active based on sleep, wake and display events, and he put it on GitHub for anyone to use.
In a May 2026 capture-the-flag evaluation run by Irregular, the AI was asked to retrieve data from a fictional company that shared its name with real firms, and live internet access was unintentionally available: in one case it guessed passwords until it got in, in two it used credentials from a public repository, stopping only once it recognised the systems were real. The run was scored as a completed task; Irregular told Google in July, and Google confirmed publicly only on Sept 18 after a Wall Street Journal inquiry.
A user in the AI Facebook group posted on Oct 18 that the AI could not save files directly to his computer the way the AI could, so rather than buy a subscription he built his own bridge in about six hours. The AI can now write straight to his local files, compatible with his existing agent stacks, and he published the tool open-source on GitHub.
Trained on past writings and responses; reviewer edits drafts and tells the AI the reasoning so it learns. Drafts only - never sends autonomously.
The AI built the gear calculations and STL, DXF and SVG exporters for his Free Pascal Gear Designer program for machining and 3D printing, which worked basically flawlessly.
Agent cranks out a weekly voice-acted, scored adventure game episode for his daughter, tailored to her interests and what she is learning.
He gave an AI one job: earn a first real payment from an open source bounty. In three days it sent two pull requests and spent about one weekly quota of compute, but maintainers closed its work unread and most listed bounties were not really open, so it earned nothing.
After a corruption incident cost him data, the AI recovered 4 unpushed commits to atcr.io. Those commits were among the things he most wanted back.
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.