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.
He got the AI to build out a structured dataset of all 4,925 vacancies, with job titles, organisation, salary and location. He shared it in a spreadsheet for other people to play with.
Jack created a recurring daily website-check goal by chat in about a minute, then deleted it by chat. The Goals tab itself was slow to load (once 25 seconds, once stuck on placeholders).
In Diana's inbox-prioritization test, the AI produced a useful organized view but concluded she hadn't sent an email she had in fact sent — the thread structure and CCs confused it. If she'd trusted the first answer, she'd have sent a duplicate email.
This one went wrong. See what happened before you try it.
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.
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.
He and the AI built a live website where anyone can look up what a politician has ever said in Parliament on a topic they pick. He calls it a moral manoeuvrability monitor.
A man was spending 90 minutes a day on email. An AI agent was set up to read, sort and draft replies to every routine message. He now approves the drafts in 8 minutes, saving 82 minutes a day.
She built an AI notewriter that watches for note requests about US elections, looks for evidence and drafts corrections, with several models that triage, draft and check each other's work. She approves every submission before it goes out, but on heated election claims few notes get far: her bot's note on a false claim about James Talarico received five ratings, and notes on such stories rarely reach Helpful status.
This only partly worked. Worth knowing before you try it.
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.
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.
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.
This one went wrong. See what happened before you try it.
In two weeks of real inbox-and-calendar work, The AI Crux had the AI book three conference rooms. Calendar work was functional but conservative: it refused anything outside 9-to-5 local without an explicit override, which the reviewer framed as a guardrail more than intelligence.
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.
Every month the family benefits system asks him for a fresh proof of domicile, and a forgotten upload stops the payments. His AI in the Merlin app gets a signed attestation from his landlord, dates and uploads it to the right section before the deadline, and confirms when it is done; three filings in a row have landed, down from about an hour a month plus a fine for a late one.
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.
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.
This one went wrong. See what happened before you try it.