Real things everyday people got it to do, and how to try them yourself.
A random mix from the whole library. Shuffle for a new set.
Nate B. Jones (11K followers) joined what he called a 'viral challenge for the AI': connecting bank accounts through Plaid, the AI identified more than $5,000 in subscriptions he was paying and canceled nearly $1,300 worth for the coming year.
Creator Elona Karafin documented the AI running her Mexico City trip live: confirming her flight and lounge access, sending proactive reminders, and adapting plans as conditions changed. It built a walking-tour route, read a menu photo to recommend dishes, and offered to move lunch indoors when rain threatened.
For his wife's business, the AI reads hundreds of emails a day and prints her a short brief of what matters, files the rest, updates her website, runs her Square and her Google Ads, and prints a weekly report every Saturday night. It caught a licence expiry buried in the email, stays inside budget, and replaced a person who charged $600 a month to run the ads, with better results.
His dad, a Vietnam veteran, needed help to keep his VA benefits. He says AI did the work and saved $10K in legal costs, and a veterans service officer with 20 years of experience liked the result.
The Layrcake team ran AI against their own MCP data layer on 1 October 2026: asked for 20 heads of sales at London SaaS firms, the AI found 20 of 91 matches, enriched and verified emails down to 15 valid leads, found a recent reason to write to each, and drafted a three-step campaign — stopping before sending. The logged run took under ten minutes and 145 credits, about $1.45.
Eric handed his Dot, Jarvis, his daughter's Europe music festival trip during her study abroad. Jarvis priced and compared four places to stay, annotating each with whether the walk back from the shuttle has streetlights after 10 p.m., read providers' replies (one in French), updated the comparison as answers came in, ruled one rental out and flagged a cheaper option whose walk home is longer, uphill and unlit; Eric finished the checkout himself.
Frontier model reviewed his KiCad project, queried the AI vision for datasheet data, ran ngspice sims; $1-2 tokens saved $70-80 of bugged PCBs.
The AI used rtl-sdr tools, wrote Python scripts to analyze signals, and built a SQLite database from FCC licensor data to identify and decode trunked voice channels.
Each week he drops three files into a folder: an Apple Health export, his Peloton data, and a spreadsheet of extras. The AI runs the numbers through 19 metrics, flags shifts like cycling power dipping after a hard hike, and updates a dashboard he checks to adjust his training.
Spent an hour with AI migrating a Home Assistant setup to Tailscale, updating sensors and Pi-hole, and putting it all in one documented git compose file.
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.