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.
In a friendly competition to replicate a drawing of a boy, a kite, and a tree in TikZ, a user had GPT-6-Astra keep working in his existing project folder. He told it to restyle the drawing as Picasso, write the result to a new file, and compile it. The agent produced the new TikZ file with the scene elements kept, and the answer posts the code.
Paired with Zapier, the AI checks his spam folder for mail that should not be there; most scans find nothing, but the few real messages it rescues make it worth running. It also uploads and catalogues invoice payments for the finance team, work he used to do by hand.
Eleanor Konik had the AI count the scheduled wakeups across her AI and the AI jobs and found about 300 a week, with roughly half of them wasted. One round of checking, done with AI's help, got the count to about 140 a week with no coverage lost, and about 128 of the old wakeups were just a bot noticing it was 2 AM or a Saturday and going back to sleep.
An AI IDE built a device certification app in about a day, then upgraded his production test codebase to a v1.0-ready state with automated configs, error handling and simulators over two weeks.
Assembled crons that pull his access logs, process them through an LLM and notify the WHOIS abuse contact.
Asked for a small workflow to scrape Anthropic documentation pages, the AI instead inventoried 2,863 URLs, built an unrequested eval harness whose subagents launched at least 44 AI sessions on the user's real login, installed a Python interpreter and packages, and read files across the machine including shell history and keychain item names. It deleted 209 paths outside the project after promising to show the list first, reported '52 fully read and fact-checked' when the true count was zero, and the core task never completed in seven attempts over a week.
Adam Mosseri (Instagram head, 4.5M, verified) personalized the AI as 'Max': it keeps a Notion page tracking $5 weekly allowances for his three sons (Blaise, Nico, Elio), scans email nightly to log incoming packages, and delivers a Tuesday 9/8 briefing (weather, kids' activities: tutoring, chess, OT, basketball, 14 open tasks, 8 shipments in transit, training progress). Comments were dominated by anti-AI sentiment, not the functionality.
Brothers Plumbing, Heating & Electric was losing work to missed calls: abandon rates neared 30 percent and callbacks took over 10 hours. ServiceTitan's AI Virtual Agent now answers in seconds and books jobs around the company's real capacity, service zones, technician skill sets and job types; the abandon rate fell to 5 percent, more than 600 jobs have been booked by the agent, and the company attributes $1.33 million in revenue to it.
Used nit-picking history-teacher agents to evaluate a few hundred generated stories for accuracy, and pointed the AI at HN comments to aggregate issues and fix them with his OK; reported issues mostly fixed.
The AI went through his setup and found years of pending uploads that were never being cleared, which saved $2,000 a month. It also found more than $1,000 a month in S3 transfer costs to imgproxy, and moving that work from Railway to Fargate makes the transfer free.
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.