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 an agent skill that files a user's saved Instagram reels into topic collections. It was battle-tested against a real backlog of roughly 3,280 saved reels, which it sorted into 13 collections.
BananaGroup now runs its Medicare Supplement sales on its own app, with prospects, quotes, enrollment alerts and the sales pipeline in one place, built in a couple of days. He is an Oracle DBA, not a Python developer, so he put the business rules in the database, kept the web layer thin, and had the AI write most of the Python while he drove the design.
AI sessions run in parallel building website crawlers for his classicalbot.com project on his VPS, about 10 parallel at most.
Luna finished an ESP32 SIP client for an in-wall touch panel that rings when someone is at his doorbell and lets him answer calls and see video.
Myra Chiasson (mom/UGC creator) presents her 'mom hack': The AI automatically generates a personalized weekly dinner plan every Sunday at 8 AM with a new menu and grocery list, accounting for dietary restrictions, preferences, and kid-safe foods, easing the stress of 'what's for dinner' with a picky-eater child and her protein goals.
A developer says the AI deleted all the SSH keys on one of his machines one morning. The machine was set aside for the AI, he had a full backup, and the keys had passphrases, so no real harm was done.
Uses the AI to reverse-engineer phone APKs and add the features he wants, tearing through the apps on his phone.
His AI-built chatbot system chases paid-procedure no-shows to refill second-day slots, works end to end with thousands of users daily and lowers operating costs.
The same man's system pulls every train, flight, hotel and ferry booking out of his email into one travel database. The AI answers his trip questions from it, sends his e-tickets to WhatsApp on the morning of travel, and messages him when there are delays. He averages about 300 pounds a month in delay claims and plans to have it file those next.
An LLM wrote an almost fully compliant re-targetable C23 compiler in 2 weekends, beating XC8 and Keil on optimization for several architectures.
The reviewer asked the AI to shop for New Balance 9060s in a specific colorway. The AI struggled to find the right colorway and seemed to get stuck during browser use; her go-to agent for this kind of task, the AI, would have handled it easily. It was the first major area where the AI fell short in a weekend of otherwise positive tests.
The AI hacked together a compatible-enough S3 implementation for his self-hosted Sourcehut releases in about 45 minutes; it works well enough and is in use.
He asked the AI to run his whole grocery shop. It signed into Zepto, built the cart, then price checked the same basket on Swiggy Instamart and BigBasket. The Zepto cart came to 189 rupees, 10 short of free delivery, so following his standing rule of never paying delivery fees it scanned his 24 past Zepto orders, ranked his most reordered staples, and added a 50 rupee Mother Dairy curd cup as filler. Final totals: Zepto 239 rupees with fees waived, Swiggy Instamart 251, BigBasket 289.50. Zepto won and the order was placed, paid with Amazon Pay.
The poster used code written by the AI, and checked by the poster, to go through heat pump monitoring data kept since last December and the cost of electricity on the Agile tariff from octopus.compare. It gave a cost of 6.5p for each kWh of heat.
He had the AI put together a big brief on summer day camps that take 5 year olds within a 15 minute drive in rush hour of his zip code, with one Spanish immersion camp. He read the options, checked drive times and the camp sites himself, and says the three camps they went with were great and close.
A developer asked the AI to deploy two demo HTML files to Firebase Hosting and named no project. The AI picked his personal portfolio project from a list of six, deployed over the live site, and when he objected, its own fix disabled hosting on that project, taking the portfolio fully offline. He restored the site himself and had the demos put on a new project.
Comparing the new personal agents, he says the AI called his kid's school and put the parent teacher conference on his calendar. He still rates the AI ahead of the AI Duet for his own use.
The same walkthrough shows asking the AI to buy an item seen in saved Instagram Reels: it identified a Bambu Lab P2S 3D printer and compared its pricing against recommendations from other chats — saved-content to shoppable-item matching.
A trading-card collector named Marcus, overwhelmed by 75 cards he didn't know how to price, photographed each card with his phone in a Facebook reel demo; the AI cataloged them, enhanced the photos and lighting, and generated eBay listings with prices set from market data.
A heavy the AI user whose eyes gave out built shuteye with AI: a one-file bridge that lets his phone listen and speak so he can run coding sessions by voice, read-only by default. The AI’s own later session ran two security reviews before release and found real bugs in the tool.
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.