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.
A builder created a skill that converts a user's Instagram saved collection into a private, searchable personal library. Every saved post is deep-read by vision AI, and everything runs on the user's own machine.
Someone had the AI buy a domain on Namecheap through the secure vault. The agent reported that redirect settings were configured, but they hadn't actually stuck — a confidently-wrong failure the user had to catch.
A buyer ran an eight-bot the AI crew for his car purchase: over nine days a SCOUT bot watched 1,412 listings, a VALUER bot built a price curve, and a HAGGLE bot sent 11 messages to the dealer. The dealer came down $4,200.
He had the AI answer a Slack notification from a Datadog monitor. The AI checked the issue through Datadog MCP, found the right Slack group to ping, and sent a summary of what needed fixing.
Someone in the house heard a beep a little before 12:13 AM. He handed the question to an agent with access to the camera recorder. It came back with the sound, the source and a short list of reasons: a smoke alarm that sounded once, at 3417 Hz for 0.87 seconds, about two metres from one camera. It was not a fire, not carbon monoxide and not a dying battery.
He spent hours trying to set up a phone for a man with Alzheimer's and could not get it right. Then the AI wrote the app he needed.
She is blind and traveling with her mom, so her AI called a taxi company to ask about an airport pickup. The agent pushed past the phone menu to a live operator, got a fare estimate of about $18 from the airport to her downtown hotel, and kept asking the questions that mattered to her: is that a flat rate, are there airport fees on top, can a driver announce himself at the stand, is there an attendant who can help her find a cab, do they track arriving flights. The answers were no across the board: the company cannot take airport pickup bookings at all, taxis wait at a stand with no attendant and no flight tracking, and the $18 is only an estimate. She shared the full transcript.
In the same roundup, Jason Zhang listed a bonus feature: sending messages to friends via connected Messenger and Instagram accounts.
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.
The AI fixed a long-running Tailscale problem by lowering the MTU.
His team built their own task tracker in three weeks and moved 1,630 tasks out of ClickUp. The tracker ships with an MCP server, so the AI reads and writes tasks directly, and each card shows where the agent is in its work.
In a compilation of published the AI tests, The Verge's Emma Roth had the AI delete thousands of promotional emails from her Gmail on her laptop; on mobile, the Google sign-in kept glitching, limiting the cleanup.
He set up a chain from his phone to the AI to his Windows PC and a background browser. The PC published a post to Bluesky and checked it had gone up, while his other screen work kept running separately.
Grupo Marista uses AI Enterprise agents to analyze hospital claims. Analysis that took 72 hours now takes 4 hours.
A man who self hosts an XMPP chat server had audio and video calls that worked only sometimes. He gave an agent access to his phone over ADB and to the server logs, and within 30 minutes the problem was clear: a setting for STUN and TURN discovery had been missed in an earlier move, so clients behind home routers could not connect. The fix was deployed.
'I may have set the record for the craziest the AI purchase ever': amyleecodes had the AI order a Samsung S95H 77-inch OLED TV from Best Buy for same-day pickup, then arrange pickup and delivery to her apartment via TaskRabbit — about 95% seamless, with a photo of the delivered TV box to show for it.
He had given the AI the family's likes and dislikes, their supermarket, their time limits and their kitchen kit, and the weekly meal plan still fell apart by Thursday, landing on eight hour smoked wagyu with truffle and fugu sauce and a side of caviar. It hit the macro targets and missed everything that mattered. He does the plan himself again.
The AI built a Mumble replacement in Rust from a rough spec in 2 hours; it worked flawlessly on Mac and Windows, he uses it on his LAN, and the AI built a network simulator to fix a latency issue it spotted in logs.
X poster someone set up an AI morning digest that links blood-glucose data from Apple Health to food spending pulled from Plaid and DoorDash emails.
A business owner's lead profile runs every Monday on its own. It formats his warm leads, finds cold leads that match his criteria across a rotating list of cities and niches, then digs into each business to find what he is missing, owner names and exact contacts, checked against business registries. He gets one standard weekly report: best fit clients, outreach details and the facts to judge each lead.
Holdy logged the AI into his medical provider's portal and had it pull his itemized bills and question every line. It found several cases of double billing, asked for discounts, and has saved him over $4,000 so far.
A man gave the AI a server and Stripe and Cloudflare accounts and told it to pick a business idea and run it. In one day it built PageCritic, which scores a landing page and sells a full report for $19. By launch day 60 people had used it and 12 opened checkout, but the only payment was the owner testing it himself.
He gave the AI 10MB of architectural plans. 35 minutes later it gave back a good interactive 3D walkthrough of the house, while the AI did the same job with several layout mistakes.
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.
An agent fixed his Unraid server issue, regaining access by hopping in via a syslog-ng server using a leftover SSH key when direct SSH failed.
A woman opening a small shop uses paid the AI to track her stock. She takes a photo of each item and the AI adds it to an Excel spreadsheet and fills in the data for all the columns from the photo.
His AI Fred collects recipes from his Instagram Saves into the Kyle app and keeps the collection up to date; the reel shows the organized collection with named recipes.
12 hours with AI Fable 5.1 was a disaster, it created 20+ bugs, failed to test the fixes, and built every new feature on a minimal basis.
The AI hacked a headless runner for a 30 year old game and ran parallel instances in the background to playtest it.
She told her AI to get better at design, then had it check her own site, aunysillyme.com. It found every buy button was too low in contrast to grab attention and that two different oranges had been used on the site for months, and it redesigned the site based on what it had learned.
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.