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 user's notes MCP was down - his own mistake - when his agent decided finishing the request mattered more: it researched the Joplin API, wrote, refactored, and debugged a 400-plus-line Python tool across five files, then used it to read his notes and write its weekly update markdown into Joplin as planned.
His AI Fred collects recipes from his Instagram Saves into the Kyle app and keeps the collection up to date; the reel shows the organized collection with named recipes.
Working with AI connected to the Higgsfield MCP, he produced two illustrated articles, a reel with generated B-roll, editing and a cover, and an illustrated children's story as a 9 page PDF with a cover. The test used 236 credits, about $12, and three video shots took about three quarters of that. He also shows the connection mistake he made at the start.
A father's the AI logs into his kids' school account daily. It tells him if any classes were missed, any discipline notes, assignments not handed in, and whether grades moved up or down since the last check.
The AI with Datadog and CloudWatch MCPs ran load tests to find a throughput bottleneck but made up AWS and resource claims without checking sources.
With five days' notice, her AI Romy reviewed 51 saved 'Costa rica' reels, built a 5-day itinerary (Bajos del Toro, La Fortuna, Monteverde), found and held Miami-San Jose flights without purchasing, and searched for a dry bag pending her approval; the reel ends with footage from the trip itself.
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.
A couple filed their own taxes - his simple, hers split between employment and freelancing. The AI made sense of the Excel spreadsheet their accountant sent and translated it into exactly what the tax portal expected, beating the tax advisor they hired two years earlier, who had made a significant mistake.
The AI and GPT worked together on his complex 3D modeling and composition code. In the morning a run took 769 seconds on average. By the afternoon it took 58.6 seconds, 92 percent faster.
Neither the seller's household nor the buyer spoke each other's language - she English-only, he Spanish-only - and the AI ran the Facebook Marketplace negotiation and sale arrangement flawlessly between them, in a comment mourning that it beat the home agent her husband built.
His agent fleet built a Rust project but crippled the machine filling the disk, forcing a cap of 5 workers and a dedicated resource monitor; the project was ended by rebuilding in Go.
The AI rebooked the same hotel, room type, and dates at a lower rate as prices moved, saving $179. The author verified the new reservations directly with the hotel and confirms everything held.
A solo litigator had about 15,000 pages of discovery to dig through for a summary judgment motion. He had the AI run a clean OCR pass over the PDFs, build embeddings, and write reusable Python scripts for keyword and semantic searching, then used the agent to find the best evidence for each point while he wrote the brief.
Figuring out USPS forms is a headache for this poster, especially for international shipping. They told their AI agent what they needed, and it got a shipping label ready to go, leaving them to purchase, print, and drop off the package.
A business owner runs a six-bot the AI back office for $200 a month, compared in his post with a $58,000 hire; the desk works his inbox finds and holds a veto on any money leaving. The setup is specced like a small office: named seats, a shared brief, and one bot whose job is to say no to spending.
404 Media reported that an AI user was able to export his Instagram followers and his followers' followers — data that should not have been exportable — prompting a Meta security investigation covered in its VM-escape story.
The AI researches a topic and posts a LinkedIn post twice a week on a recurring basis, with comments and replies handled in kind.
The AI, given a Home Assistant API key, watched for the new Bluetooth aquarium thermometer he installed, replaced the broken one's entities with it, and verified graphs and automations worked.
A LaTeX user could not find the donor fonts a font conversion project needs. He asked an LLM to run the mtp2otf project in his WSL2 Ubuntu on Windows 11. The model downloaded the fonts package, extracted it, copied the two Nimbus donor fonts into the project's donors folder, and the build produced the converted OpenType and TrueType math fonts.
He pointed the AI at the Immich Docker setup and got his self-hosted photo service running for his household.
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.