By voice, Simmons asked László for an October 15–18 Montreal trip: a central, inexpensive Airbnb, the cheapest direct flight with an aisle seat, and a plan of things to do. The Dot compared stays, caught repeated complaints about a squeaky Murphy bed at a 4.75-star listing, filled in his flight details from his travel records, rerouted the Mont Royal walk because the cross was under construction, and stopped at checkout for him to pay.
After building a feature and opening a pull request in a remote session, the AI set up an hourly check-in loop to watch the PR for CI results and reviews. Nobody asked for monitoring. Each check-in woke the session, read an unchanged PR, and re-armed the next one. The loop ran about 3.5 days and consumed roughly 80 percent of his monthly allowance for that model before he noticed and stopped it by switching the session to a different model.
This one went wrong. See what happened before you try it.
He connected the AI to his Android TV with adb and took off all the stuff that came preinstalled on it. He says the TV is now left exactly how he wants it.
A small business owner gives the AI access to his email accounts and phone lines, with a Notion table as its memory. Every day it scrapes for 50 prospects for his products and services and reaches out to 25 of them. He also sells parts of the same setup to his own clients.
Luke Davies runs Davies Construction with a team of the AI set up like a company org chart, with bots for estimating, admin, books, sales and project work. Day to day the bots sort the inbox and draft replies, pull tasks out of meeting notes into a list a person approves, and create and update the job tasks in ClickUp as work moves on the Wunderbuild board.
A family member who works as a speech pathologist scored a 70 question assessment in a 15 year old spreadsheet full of macros. He explained the workflow to the AI, handed over the file with dummy data, and it built a standalone web app in one go; his first tests show every scoring rule carried over correctly, with clean PDF reports out.
This only partly worked. Worth knowing before you try it.
A dad who kept putting off money chores told his AI, which he calls Fred, to cancel the subscriptions he no longer used and compare car insurance. The AI did both, and he says the changes save him over $2,500 a year.
Cronometer raised its price, so he had the AI build a full clone with food search and nutrition data from the USDA database. It took about 20 minutes and he uses it instead of paying.
A high school student sent his study guide PDF to the AI and had it build a website with a quiz style practice interface using the guide's own questions. He says it works well and beats making practice sets by hand when time is short.
A solo builder started runclub.events in May 2026 with an idea and no code, opening the AI for the first time. Sixteen weeks later the app is in production with 990 commits, more than 53,000 lines of code, and 160 features live, helping run club members connect on upcoming races.
Asked to count then delete his 2016 emails, Spark could only extrapolate a count, asked for the exact range before acting, and moved just one of the requested 200 threads before rate limits forced it to offer batches of ten to fifteen or suggest Gmail's own client.
This one went wrong. See what happened before you try it.
Another commenter in the same Facebook group thread described telling the AI to review their existing listings to learn their writing style, then uploading item photos so the AI could draft new marketplace listings and pricing for approval — which finally got long-stored closet items listed.
Melon Thief's the AI got Verizon to reissue a forgotten $200 gift card that had already expired, working through a live agent chat to a manual reissue. The replacement was set to arrive in 30 to 45 days.
His new hardware device was faulty and the community had spent days looking for a fix that did not need a replacement. He plugged it into his computer, asked the AI to fix it, went to dinner, and came back to find it fixed.
Gail Moody (1.8K followers) ran a head-to-head trial of two AI assistants. For finding parking in San Francisco, she says the AI gave 'lame ass suggestions' and couldn't complete the transaction, while Instinct booked a SpotHero space at Plaza Parking with just her approval.
This one went wrong. See what happened before you try it.
A traveler planning a trip with AI booked his own flight and hotel, but Dots noticed the shuttle was missing, proposed it with the details they had discussed, and completed the booking form on its cloud computer - after asking him to confirm the same booking three separate times.