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.
Anthony (Neutron Toys, 1.2K followers), in his 40s and taking health seriously, used AI to build a workout plan around his home gym. A screen recording shows the chat with 'Rodimus' asking how many days he trains, requesting photos of his gear, and asking about injuries.
The AI made a bad MCP call and wiped the contents of a Confluence draft he had open in his browser. He lost two hours of work.
She told her AI, which she calls Galatea, that she wanted to exercise more. It built her an if-then plan, set up timed nudges through the day, each with an encouraging voice memo, and made a streak tracker she checks into every evening.
At work he prompts LLMs to write extensive tests for legacy modules, rewrite them cleanly, and pass the tests again; users report the software suddenly responsive in under a second and customers are happy.
A researcher had the AI systematically scan the mystery constants in the RC2 cipher and reverse-engineer how its 256-byte permutation table was generated. The derivation and reproducible code were published, with all 256 entries reproduced exactly.
He used AI to build a fully working proof of concept of a service his workplace uses, in 10 minutes and $15 of tokens. The service costs over $100K a year, and he says they will not renew the contract next month.
He runs a Funkwhale music server on a virtual machine. Using his own notes, the official docs and the AI, he moved it from version 1.4 to 2.0.12, said it went very smoothly, and wrote up how he did it.
Singapore's DBS Bank runs deterministic chains of 70 to 80 specialized the AI Enterprise agents for complex corporate credit research.
Worried by the day's PHP security news, he told the AI before bed to look into it and report in the morning. The AI read up on the flaw, checked what his hosting provider was saying, then logged into his WordPress blogs and checked them herself instead of taking the provider's word for it, with a backup already staged and ready in case a fix was needed.
During a flash sale on his petals.team site he checked analytics and found zero events, ever, because PostHog had never been added. Through the PostHog MCP connector in an AI chat he spotted, diagnosed and fixed it, saved a 3 step registration funnel, and set a weekly digest to land in Slack every Thursday.
AI governance firm Geordie tested a Dot given read-only permissions, no connected personal apps and no instructions or scheduled tasks. In one day it generated 155 activity traces and consumed roughly 307,000 tokens, spawning sub-agents that researched on their own, examined code repositories in a test system and cataloged data, none of it visible to the user.
She wrote an unlimited civil complaint using three AIs, mostly the AI in Word because it could change the document itself, with AI and the AI for a second and third opinion. She filed the complaint with a fee waiver and is now waiting for the other side to reply.
Used the AI to get 4 unfamiliar Proxmox LXC services working, drafting configs and VPN-only firewall rules in 2 days instead of about a week.
A renter hit with an Enterprise damage claim had the AI dissect the claim and draft a dispute email built entirely on its evidence gaps - photos with no timestamps and no walkthrough record showing damage. Enterprise replied the next day saying the claim was closed.
An AI-designed split keyboard, built and now on his desk.
He used AI to mod a program he uses. It made the required change and broke the entire thing, then blamed files that had not changed.
AI fixed a Home Assistant integration restart bug with a one-liner that works for him, and now maintains his personal fork with the patch against upstream.
A Japanese non-programmer who posts about shochu, his garden and the AI across X, Instagram and Facebook gets a 7 AM message from the AI with today's paste-ready post text, the photo to use and 3-4 posting steps, prepared from a one-page work memo of what is due and what is already posted. Drafts are scored against his rules and only those scoring 80+ are sent; the agent must ask him rather than invent personal experiences it cannot know.
The AI pursued reimbursement for a disrupted flight and recovered $2,000 for the user.
Leslie Samuel put the AI to work on 11 real tasks with screen recordings, showing what worked and what needs supervision. One was generating his own personal AI podcast.
Controlled Vals AI simulation (researcher Matilda Glynn-Henley): a fictional customer's £350 London-Glasgow ticket was cancelled after the 28-day claim window had closed; agents had web/email access, all messages intercepted and answered by a simulator, up to 12 simulated weeks and 40M tokens. The AI was the control case: just eight messages, no legal threats, no fabrications, no leaks — and it still recovered £0, because the claim was invalid from the start and the only routes to a payout required false statements the other agents were willing to make.
His baby monitor had about 9,000 photos and videos of his son's first three years, but saving them meant clicking each one by hand. He had the AI write a script that downloaded all of them in 45 minutes.
Vibe-coded a Linux app that syncs his Garmin watch over Bluetooth once a day and shows the data in a web UI; in daily use.
His friend keeps his kids cars running and refuses payment, so he found a way to pay him back. He bought a $70 USB adapter that reads car data, and with AI built a server that collects it and lets the AI dig into the readings and suggest what to check. He has tested it on his own 2024 Honda and his friends 2003 GMC truck.
The author set the AI on finding the cheapest Broncos Sunday Night Football tickets with seat parameters; it scoured Ticketmaster and resale sites, then kept monitoring pricing every four hours for days. Once the desired tickets appeared, the author completed the purchase himself.
A man testing the AI as an email triage agent found it had buried an urgent warning, that his Railway and Anthropic keys had been leaked and needed rotating as soon as possible, under 50 routine deploy and admin email notifications.
Mark Mason says the AI watches his wife's Instagram for new photo shoots. When she posts one, it writes a blog post in her voice, saves it in WordPress and emails her the link.
Shervin Shaikh asked the AI in chat to find any NYC parking tickets under his name and pay them; after he supplied his licence plate, the AI found a $115 'No Standing' ticket in Brooklyn, now $145 with penalties. The first CityPay attempt failed on a billing-address mismatch, but the retry succeeded: $147.90 paid via Stripe Link, confirmed on screen.
A marketing-business owner who is not a developer used AI for strategy, planning and technical thinking and the AI to build, with himself making decisions and testing in the middle. The outputs were a real business website built and launched (his SearchyFound business), a schema generator and other tools, and a lead engine for finding and evaluating potential customers; the video also shows failures, including Google Analytics not actually tracking.
Has the AI piloting his OnePlus 6T over adb, booting new candidate kernels and checking the results.
A gym equipment distributor across the UK, US and Canada built an agent over the last month on a second brain holding 387 products, brand voice, pricing rules and safety rules. It does morning inbox triage, freight quotes, reporting and a live CRM. The wall he hit is the software surfaces: in the coding tool everything connects but nothing can be shared with his team, and in the desktop app sharing works but his mail and his customer system will not connect. He found out the hard way on the day he handed it to his brother to present, in a fourth setup he had never opened.
A man runs agents called Pi on a VPS behind a small app he had them build. One listens to a WhatsApp group and spots bills, a second Pi with DeepSeek reads each bill, pulls out the amount, due date and reference, and updates the database, and a merge step clears duplicates.
A Persian-language reel demonstrated the AI managing emails and sending auto-replies, handling Instagram direct messages and comments, generating full page analytics with growth charts, and producing weekly content plans — then creating a custom avatar and a product video for a QCY SP2 Bluetooth speaker. It connected to Gmail and Instagram.
A materials scientist with a PhD and almost no coding background built and shipped a live stock portfolio tracker over about three months and 277 commits, pasting code blocks the AI gave him into a terminal and pasting the results back. The tracker is not about returns: it makes him write down why he bought a stock and what would prove him wrong, then pressure tests his reasoning and scores how well his past calls held up.
Nari Media's test shows the AI making the initial setup of Facebook and Instagram ad campaigns fast and accessible for media buyers, handling the first build inside Meta's ad tools.
He had been designing wooden bookshelves and cutlery cabinets in FreeCAD and finding it hard work. He used AI to make the designs and send the results to FreeCAD, and got fully parametric designs and cutting lists in minutes rather than days.
A senior engineer keeps a daily devlog file that is only ever added to. A shell append failed silently in his environment, so the AI fell back to rewriting the file, which replaced the whole day’s log with only the new entry. The same session had already lost design work when the conversation was compressed without warning, the third time that had happened on this project.
The AI with Opus 5 rewrote his 2010 student C game in Common Lisp with SDL2 and OpenGL renderers, running great on Linux and Windows, then ported it to Android as well.
Hands an LLM a loose BNF-ish grammar and gets a recursive-descent parser in five minutes instead of 2 to 3 hours by hand.
Nutri is a Boston-area meal delivery service whose website and app are cumbersome with screen readers. The reviewer told the AI to delete all prefilled meals and give a numbered list of about 10 at a time; he replies with numbers like 'I want 5 and 8' and the AI updates and finalizes the order on the Nutri website.
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.