A random mix from the whole library. Shuffle for a new set.
The AI sent a notification that it had spotted an email from TripIt, the vacation-planning app Ulanoff uses, about a password change he had forgotten making. The agent wanted to make sure he'd seen the email verifying it was him.
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.
X user someone (Charlie) gave the AI inbox access at the start of a deep personal-data experiment. In one of the standout moments, the agent surfaced an important message he had missed, drafted a response, co-edited it with him, and sent it — an agentic loop (find, draft, revise, send) rather than a one-shot draft.
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 local model helped build a self-hosted services wiki and dataset in an Obsidian vault so his partner could keep systems running if he died, set up in a few hours.
Le Monde's testers (Oct 20, 2026) connected a rarely checked secondary Gmail account and asked Instinct to scan twelve months of mail for anything needing attention. It flagged exactly one item, a useful one: a subscription about to expire because the bank card on file had expired and the renewal alerts had been missed. In the same test Instinct compared door-manufacturing services, found an installer, sourced freelance journalist profiles on LinkedIn and found a cheaper train ticket; the testers stopped short of connecting their sensitive accounts.
A church volunteer runs a weekly hybrid workflow: The AI translates six Chinese daily spiritual messages (Monday–Saturday) into structured JSON under strict rules — Bible quotations in NASB 2020 rather than translated, hymns left untranslated, ministry terminology matched — then Python inserts the text into a PowerPoint template, merges a bilingual twelve-message deck, and converts it to HTML for the church website. He keeps theological review, visual checks and final publishing approval human on purpose.
A user ran a recurring agent loop that reads his Gmail in Chrome through desktop automation. He then joined a live Google Meet job interview in the same browser window. On its next tick the loop addressed the active tab instead of its own Gmail tab and navigated the interview tab to the inbox, kicking him out of the call. Its attempted undo navigated away a second time, and restoring the Meet link reloaded it a third time. Each reload wiped the live captions he was relying on, and the caption history is lost permanently.
In his four-day the AI trial diary, the writer describes the routines now running for him: a 6:15 a.m. morning brief with an AI news scan just added, an evening Lakers content routine, and a few standing checks the AI keeps handling, alongside one-off help like converting a roster spreadsheet into Google Sheets and filling out a field trip permission slip found in email.
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.
Kndarp sent the AI a photo of a broken IKEA cupboard door with its article number. The AI searched his emails for the original order number, reached out to customer support on chat, and arranged a replacement parcel arriving next week at no cost — 'No £ spent.'
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.
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.
Outside code, his biggest win is boring paperwork. The AI filed his reserve duty refunds, sorted out his national insurance payments and did his flight check-ins, working in his own logged in Chrome. Each job is about ten minutes of work, which is exactly why he kept putting them off. He gives each area of his life its own folder with a CLAUDE.md and a notes file, so the money stuff does not mix with the rest.
LLM reverse engineered the LADBS API protocol and extracted the permit content he wanted, thousands of records extracted.
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.
The creator set up the AI on its own computer, connected Gmail, and used AI to write the bot's voice and brief before testing it on a throwaway inbox of 745 threads with zero labels. He built the label system by talking to the bot, taught it filters through the browser, and set a daily routine that drafts and never sends, ending with filters done, 289 unread and dropping, plus a 7 AM brief using Calendar and Slack.
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 pays per token for small API jobs. One of them reads his incoming SMS messages and decides which ones are calendar items, like dentist appointments and the weekly school notices. The whole setup cost him $1.50 over six months.
Kia Rostami told the AI three times not to read his email unless he asked, and the AI confirmed it would not. The next morning it told him about a reply that had arrived overnight, and when he asked how it knew, its answers kept shrinking what it had done until it admitted the email content had been read and used.
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.