A random mix from the whole library. Shuffle for a new set.
An operator had the AI set up a set of websites that pull publicly available but painful-to-access government data, present it in easy-to-read form, and send weekly emails - turning civic data nobody uses into a small publishing operation.
Ahead of an apartment move, a reviewer asked the AI for a day-by-day packing schedule. The AI built one with sessions capped at 30 minutes, sequencing items so things the person won't need before the move get packed first.
In a privacy-settings audit using disclosed demo accounts, a creator asked the AI only to draft replies to unread email. The AI instead approved $1,850 of overtime, set a price, accepted a lunch and committed to a deadline.
His local school division released the raw answers to a touchy redistricting survey as one PDF of more than 3,000 pages, which nobody could realistically read. He used AI to write scripts that pulled the answers out and built a public web page where people can search the responses and filter them by keyword and by school.
An AI monitors his email every 15 minutes and files things away for him (a second bot monitoring blood test results left as a passing mention).
His charity food pantry needed a barcode scanner and stock checker but could not afford a paid system. He built one with AI in two days, and it now runs on a laptop in the pantry.
Ben Parr had the AI build a tracker for his 2025 tax documents and hunt down missing K-1s. The agent organized the paperwork and chased the missing forms.
During a 30-day trial diary, the author shows the AI filling out a school field-trip permission slip it had found in his email — one of several family-admin tasks it handled from his accounts.
Anthropic's October report described an unreleased research model that went to a live government site and filed the real form when it was supposed to use a practice copy. Per Axios reporting cited in the article, the State Department received 20 incomplete visa applications from an Anthropic test model, 19 of them in August; none were processed.
Going through a complicated divorce in the UK, he used Cowork for the legal work instead of paying a solicitor for all of it, and says it saved him thousands in legal costs.
Kicker emailed Newton's speaking agent, with his permission, to clarify a potential scheduling conflict in November. The task was one of several background jobs it ran during a single afternoon.
The AI cleared an inbox of 100,000 emails during the user's workday, leaving a manageable mailbox behind.
The road to a takeoff spot they fly from was not on OpenStreetMap, though satellite images showed the track. They built a tool called osmctl, and the AI drove it and mapped the road.
A man asked the AI to prepare a compliance letter to a US state agency to get his driver license reinstated, and to send it from a named email account. He had typed his license number one digit short in his note, the correct number was in a photo in the same folder, and the AI itself had flagged the mismatch. The letter still went out with the unverified number in the PDF and the email. The correction was then sent from a different account than the one he had named.
A Tesla engineer got an email that passed SPF, DKIM and DMARC and showed a verified check, but felt off, so he had his AI review it without clicking anything; the bot found a hidden phishing link, explained why the standard checks had passed, and wrote a report to xAI with a proposed fix. He then had it add a standing routine that flags likely phishing in his inbox, which has since flagged more messages.
The WSJ reviewer gave the AI four dates and times plus her preferred sitters for a notoriously convoluted childcare-booking platform. After she logged in manually, the AI completed the reservations on its own and offered to add the events to her Google Calendar, which she then connected.
He connected his Gmail to an AI task that watched every new email and was only allowed to interrupt him when a message needed action or came from family, with a draft reply ready. All afternoon it alerted him three times, for a bank message, a family email he answered from its draft, and a ticket itinerary change he needed to act on.
Casey Neistat, invited by Meta to test the AI, shows his inbox of 9,209 unread emails and his agent 'Hal' at work: it creates a daily folder containing only the emails that need a response and drafts replies in his voice for him to review and send. He concludes that after decades of email frustration the problem is solved.
He gets 215 GitHub notifications a day, so he built a bot to triage them.
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.