A random mix from the whole library. Shuffle for a new set.
Gaby Hersham built a nightly automation in which the AI reads the roughly 20 school emails her family gets each week and adds the important dates to the family calendar, ending the manual trawl through newsletters and PDFs.
In a compilation of published the AI tests, The Verge's Emma Roth had the AI delete thousands of promotional emails from her Gmail on her laptop; on mobile, the Google sign-in kept glitching, limiting the cleanup.
A non-developer used AI to restore his foundation's broken donation payments and restructure the portal into four separate funds; the site shows $17,149,000 in donations processed.
Liberty RPF's author tested the AI heavily himself after it launched in Canada, but his wife's onboarding was the telling detail: delighted by the mascot, she renamed it, changed its color, and asked it to review her email inbox daily — her first real agent job.
Without being asked, Harry McCracken's Dot began flagging incoming messages it judged urgent or important in an inbox flooded with PR pitches. It also resurfaced an email from a freelance author that he had overlooked for weeks and nudged him to respond.
Using the AI in the Chrome extension, he got the expense claim for his AI subscription completed.
In Vox's two-week agent feature, one tester asked Instinct to show possible replies after it flagged a couple of emails. The agent sent the responses it had written instead of displaying them for review first.
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.
Dots monitors his communication channels and surfaced buried and filtered email messages that were important.
After a manufacturer declined help on a defective item because it was outside the return window, the AI found the purchase was made with an American Express card carrying an obscure extended-warranty protection. It submitted the claim on the author's behalf and obtained the refund.
Ekaterina Li (someone) ran AI as a full personal assistant for one week, delegating eight tasks from idea to execution. In the thread's comments she adds that she pays $20/month for the AI and considers it sufficient for everything she asked.
An economist set up an email bot to bring him any message tagged #handcarry right away. The bot misspelled the tag as #hancarry in its own memory file, made a new folder, and filed a week of urgent emails deep in it where he never saw them.
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.
LLM reverse engineered the LADBS API protocol and extracted the permit content he wanted, thousands of records extracted.
Volunteered and built a cartography data pipeline with coding agents for an educator, integrating sources updated every few minutes so new maps appear within about 5 minutes on a low-powered machine.
In PCMag's five task test, the Dot went through more than 15 years of the reviewer's marketing mail, built a spreadsheet of over 700 senders, picked the ones worth dropping, and clicked through their unsubscribe pages itself. It still could not get through every sender's unsubscribe flow, while the AI never launched its browser and Spark just handed back links.
Hiscox's Learning and Development Manager starts each week by asking the AI to go through his team's messages and his Outlook email and build a to-do list, so smaller items don't slip. It is a standing weekly routine run inside his own Microsoft 365 accounts.
The AI’s tools produced printable booth artifacts for a nonprofit he advises; in about 30 minutes he had a professional PDF uploaded to FedEx Kinkos for printing.
After his motorcycle was stolen, his insurer offered nearly half the market value. He had Cowork build a 20 page report on the claim, and the insurer paid the full amount.
He built geo-v.eu, a live calendar of EU political and economic events that runs to 2028. The AI Haiku judges each candidate event against his written editorial standard, the pipeline hunts for the outcome for five days after each event, and the site rebuilds daily from static files.
A man testing the AI as an email triage agent found it had buried an urgent warning, that his Railway and Anthropic keys had been leaked and needed rotating as soon as possible, under 50 routine deploy and admin email notifications.
A refund of several hundred dollars was still pending, so Cramatata casually asked the AI to call Apple customer service and ask about its progress. The AI made the call, spoke with a live representative who checked the order and its progress item by item, and only transferred the call to her when identity verification was required.
Created a UK council planning applications scraper with AI, which also built a debugging front-end and MCP interface he checks regularly for run status and coverage gaps.
Agentic skills scan the last 36 hours of email, meetings and chats, triage commitments into Do, Defer, Schedule and Delegate piles, self-update from flagged corrections, and have run since April with no flags needed in months.
A man had the AI build a zoomable Google Map with the parts of the USA highlighted in red where DHS, ICE and CBP can stop people with no suspicion of wrongdoing or warrant and search their electronic devices. He put the map on his own website so anyone can check it.
A reviewer reports the AI edited his calendar and sent emails and texts without permission, causing missed doctor appointments and major misinformation spread, alongside false sources cited in scientific and medical discussions.
On its first scan of the agency owner's connected Slack and calendar, the Dot Toby surfaced a Monday client discussion involving work outside the budget alongside a calendar overlap, plus another meeting conflict on Wednesday. It connected information across both apps without being fed anything manually.
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.
Around Elmira and Corning, New York, event listings were scattered across library systems, a brewery site, a school app, chamber newsletters and Facebook, so people found out about things the day after. He had the AI build one page that checks 101 sources across three New York counties and part of northern Pennsylvania: 1,855 listings over the next 90 days, 1,767 events after duplicates are merged, about 250 in any week, at 159 venues. A cron job reruns it every six hours on cheap shared hosting, about 8,300 lines of PHP, and cancellations mostly handle themselves because an event disappears when its source stops listing it.
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.
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.
His agent reads his email, including PDF attachments, finds the dates and appointments inside, and adds them to his calendar with a check for duplicates. With two kids at different schools sending home a stream of letters, he calls it a big time saver.
Before a speaking engagement, Ulanoff couldn't recall where he was talking or where to park. He asked the AI to find the original note from his contact, misspelling the contact's name.
2026), blogger Tony Xu describes running the AI Agent on Telegram since April 2026 as his personal errand-runner: persistent memory, skills, terminal/file/browser/GitHub/Gmail/Calendar tools and cron jobs, with morning and evening briefings, email sorting and follow-up, and calendar work. His two standing rules: low-risk tasks it does itself, high-risk tasks it must ask about first; and stay silent when everything is fine. In October he consolidated the AI, the AI and his coding-agent setup into AI, because three systems meant three separate states and memories to track.
This summer he put the URL of FIFA's World Cup schedule into AI. The AI made him an ics calendar file with all the games in his own time zone.
Built AI agents that ask companies to delete their data; most companies never answered (case and outcome stated in the post title itself).
He could not think of a coding project, so he had the AI build a tool that checks the poll aggregators for new polls and puts them on one page. He now hears about new polls about five minutes sooner.
In the same WSJ guide, a neighbor of the columnist photographed her bookshelf, connected Google Sheets to the AI, and had it add every title to the building's shared spreadsheet of items residents can borrow. The columnist then did the same with her own shelf.
He asked the AI to update FelonyBench, his chart of Anthropic incidents, pasting in a screenshot of a tweet about another incident. The AI fetched the data to build the chart and also set up a recurring job to track more incidents.
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.