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.
Amar Ghose, the non-technical CEO of ZenMaid, had the AI interview him with about 20 questions, draft product, technical and design documents, then build 'Fran's Peak' — a live app where his wife logs her 100-day painting challenge, watches her streak climb a visual mountain and shares progress with followers. It took roughly 7–8 hours on a Saturday, went live Sunday morning, and she uses it every day.
The AI wrote a PowerShell script that turned a 3 hour manual task into a 10 minute task he can repeat any time.
Made an ESP32 flight radar for his desk showing planes over his house, two of them including one for his wife, running around the clock.
The Zilliz team linked the AI to their Slack community in about 20 minutes of setup. The agent now answers user questions around the clock.
Engadget reporter Karissa Bell tested the AI for a few days starting with her Meta-app activity, since she was initially cautious about granting access. Alongside the recipe book, she had her agent ('boo') compile the restaurant posts she'd saved on Facebook and Instagram into a searchable guide organized by city — turning a dead-end save pile into a usable dining shortlist.
A nightly coding agent works his backlog and never merges.
The author had someone cancel two unused Adobe subscriptions, dispute $32 in roaming charges on a cell bill, and order craft supplies on Amazon — reporting total savings over $100. Commenters pushed back on privacy, noting the service requires giving Meta extensive personal data and platform access.
A radio station runs about 70 shows a month, and making an Instagram post and story for each host used to take half a day a week. Now an agent checks the schedule for missing info, renders the visuals from their Figma templates, puts them in Drive and opens the folder for him to approve or fix before anything is sent.
Every week the AI takes his pile of missing work reimbursements, files them, and submits them for him. He says it is the real time saver for anyone who travels for work.
A maker had an LLM design a circuit board by running KiCad headlessly from a terminal, checking the design in a loop until it passed every rule check. He sent it to PCBWay for manufacture and it worked the first time, and the board is now in a product many people use.
He gave an AI one job: earn a first real payment from an open source bounty. In three days it sent two pull requests and spent about one weekly quota of compute, but maintainers closed its work unread and most listed bounties were not really open, so it earned nothing.
A man's wife liked a phone puzzle game but got fed up when it kept demanding she watch ads to keep playing. The AI rebuilt the game as one web page with a daily challenge, all time stats and as many puzzles as she wants, with no ads and a cat theme, for about $25 in token costs.
One of several tools he built with AI: a program that listens for the neighbor's dog, detects the barking and logs it to a spreadsheet, so he has a record before he complains.
The AI interfaced with FPGA boards over USB, set up UART, created an on-chip logic analyzer, and troubleshot a synthesis problem to a workaround.
He built a Homebridge plugin with AI that lets him turn his server on and off from Apple HomeKit for free. He says he does not know the first thing about coding.
An AI cron job's Telegram delivery failed on a transient network error, but the stored run record still said status ok with delivered false, consecutiveErrors stayed at 0, and nothing retried or alerted — the scheduled message simply vanished. The failure was only visible by digging into the run diagnostics; anyone watching the chat or the job's status saw a healthy run.
In February he told the AI what road he was taking and when he was setting off. The AI picked lunch places within a 20 minute detour that he would reach at lunchtime, 10 of them spread over 50 miles, with an import into Google Maps.
The AI took care of an Epiphan VGA2USB driver problem he had been sitting on, driver posted on GitHub.
A man patched almost 10 devices the day before posting by prompting his local the AI or AI agent through a small connector that gives it access to the whole fleet only when he asks. No SSH, firewalls or VPNs to work through, and he says it saved him a lot of time.
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.