A random mix from the whole library. Shuffle for a new set.
In a Vox feature on personal agents, entrepreneur Matt Van Horn said his wife sent Instinct a photo of a parking ticket with no instructions at all. The agent, which already had her credit card on file, simply paid it.
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.
He gets 215 GitHub notifications a day, so he built a bot to triage them.
TechMitra founder Ayush Singhal asked the AI to triage his Gmail thread by thread. It proposed archiving ten promotional emails, correctly found nothing to do on other categories, and unprompted flagged a spam comment on his second website. After his approval it archived nine FYI threads and left two genuine action items.
Across the same two-week inbox-and-calendar test, the AI proactively flagged every one of the author's seven calendar double-bookings before the meetings occurred.
She was using AI to archive legislative material when it flagged a serious vulnerability in a state legislature's website. She had to stop and report it.
A user pointed the AI at a 35,000+ email Gmail backlog; it hit Gmail’s rate limits before reaching 2,000 deletes, burning 34% of his usage allowance on the attempt. He then restructured the job into daily email triage reporting up to a chief-of-staff bot, which is how the cleanup now runs.
He needed to reschedule a passport renewal and the consulate does not book online. Instinct emailed the consulate from his account, the consulate called him the next day to arrange the appointment, and Instinct put the emailed confirmation on his calendar and checked it for clashes.
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.
Commenting on the 26 use cases post, he says his AI books all his haircuts: he just says book a haircut on a day at a time, and the email confirmation comes in. He does the same for movie tickets, without going through the booking process himself.
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.
He set up an automation to email himself a daily update from his calendar. Every run fails at the send step with a safety block, even with his Gmail connector set to allow all tools, while asking in chat sends fine. He rebuilt it several ways and every version stops at the same point.
The AI cleared an inbox of 100,000 emails during the user's workday, leaving a manageable mailbox behind.
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.
The same setup reads his incoming email and texts, builds his weekly to do list, sends him a digest every morning with the list and any scheduling clashes he might miss, and adds events to the family calendar on its own. A spreadsheet of every house appliance and its service schedule feeds the list, and it drafts the messages to repair firms for him to send.
He updated an old email triage workflow for a client this weekend. Jev now runs alongside GPT-4o mini, which still controls which emails get forwarded to her customers.
Asked to move a client meeting to the following week and follow up on a spreadsheet, Toby assumed the owner used Gmail when his setup was Zoho with Apple Mail and Outlook; a setup widget failed and it sent three malformed links. Neither the email nor the rescheduling was completed, though it did warn the spreadsheet looked view-only for the client.
He had the AI work out how the When2Meet scheduling site works and turn it into a skill. Now the AI can read his calendar and fill in the When2Meet availability grid by itself.
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.
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.
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.