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.
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.