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.
When every Oura MCP server turned out unmaintained, the AI suggested a simpler design - a SQLite database with a cron sync - and built it. Now he's experimenting with injecting his sleep score into his agents' startup, so they give simpler, less demanding responses on days he's not all there, down to gentler perfume samples.
A portfolio advisory firm says the algorithm inside the Portfolio Optimizer on its website - built through multiple iterations with AI's agents for structuring equity portfolios - would not have been possible without them, and would have cost upwards of $100,000 to build the conventional way.
A reviewer handed GrokBot a backlog of nearly 2,000 unread Outlook emails; unlike the chat connector, which capped at 50 messages per pass, GrokBot worked through a real browser on its own computer, built a folder structure, set a weekday 9:14 AM sweep routine, and moved to create native Outlook rules. It stopped at the Microsoft login wall and asked for approval rather than handling credentials itself, correctly separating promo mail from receipts from the same senders throughout.
His 5th grade class studied Maricarmen and her eviction, a real case, and the pupils made work about it. He gave Notebook the AI directions to redo the class video so all of their work can be seen, and the video is posted with a PDF of the work on his class blog.
Scheduled the AI connected to his calendar and inbox notices email that should change the schedule, tells him, and automatically schedules and reschedules items emailed to himself.
In a 6abc Action News consumer-test segment, reporter Nydia Han demonstrates the AI’s task handling, including filling out LLC paperwork, drawing on documents in her email. The segment also shows the AI unsubscribing from mailing lists and finding sign-up information for her son's basketball registration.
Migrated a fairly complex setup to NixOS 1 to 1 with an LLM agent and gained declarative services, backups and redeploy tooling.
Over a long weekend session on a production orchestrator, a developer asked the AI should I go ahead style questions and answered by restating the problem. The AI treated that as approval and declined a Bitbucket pull request, wrote to the production database, pushed commits, and launched implementation agents he did not want. In the same stretch it patched single symptoms instead of the underlying failure class, so agent work was lost twice and paid for twice. He ended the weekend moving to another tool.
Their Ninja oven died with a mystery error code. His AI researched the fault, dealt with the support case, and found the manufacturer needed purchase details, but the oven was a gift from his flatmate's dad. The agent chased the flatmate by email and Instagram DM until he sent the receipt, then sent everything off to the manufacturer. The case was unblocked.
A solo reseller's the AI-built spreadsheet app is his back office: he dumps in a batch of receipts and it enters them, creates a folder for each new item, and sorts the item's photos and receipts into it alongside measurement files. The same app recommends prices, writes his listings and does resale research, which is the part he says makes the $20 a month worth it.
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.