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.
He used Deno's Jupyter kernel all the time for exploring TypeScript libraries and automations, and was going to miss it. He pointed the AI at the problem and the result is cdp-kernel, Deno's Jupyter kernel extracted to run notebooks on any V8 runtime, now on GitHub.
He said he built his setup with AI and local models. He told the agent to use a GitHub tool to download his Garmin data automatically and store it in a local SQLite database, and the data includes sleep and HRV, not just workouts.
DeepSeek upgraded gnarly, exploitable PHP 7.x code to fully patched PHP 8.3 in about 15 minutes for a few dimes of tokens.
He uploads his own data and points the AI to specific sources and documents, with examples he made before to show the format he wants. The AI then builds the tables and graphics for his Education Rights Project, public pages on education rights and funding in US states, with policy briefs, slide decks and interactive widgets.
He used GPT-6 Astra to model a small weed holder and 3D print it. Talking to the computer and getting a real object back felt to him like a Star Trek replicator.
He is treasurer for a nonprofit food co-op. He gave the AI the co-op's financial statements, some notes on what he wanted to explain, and the logos, and 20 minutes later he had a ten slide deck and separate printouts for the annual meeting.
A Japanese writer let his AI pipeline produce an entire article by itself (scouting the topic, fact-checking it against official documentation, drafting, and generating the header image) and published it untouched as a paid note priced at ¥500. The piece itself discloses that no human wrote or edited it, testing whether readers will pay for fully agent-made work.
He had the AI translate his MaPollution app into Italian, and it took 30 minutes. He can now offer his free service to people who speak other languages.
A statistician had argued that class balancing helps mini batch gradient descent. He had the AI Astra design and run a simulation to test the claim, and the results partly corrected him: oversampling sped convergence but hurt probability accuracy, while importance weighted oversampling kept most of the speed and the accuracy. The code was cross checked with AI, and he posted the corrected conclusion as an answer.
In the same test, he connected Gmail, Google Sheets, and Google Drive; the AI responded to his emails and performed tasks autonomously on its own server even while his laptop was turned off.
A man gave an agent all of his father-in-law’s care records and made it the coordinator across the many doctors involved. It found real problems, including a pain medication given on the wrong schedule and a key error from voice transcription in the records, and fixing them changed the treatment plan and left him feeling a lot better.
Posting in Korean after one week with AI, someone says the AI handled her LinkedIn refund complaint for her through browser automation ('링크드인 환불 항의도 브라우저로 알아서 해줬음'). In the end the refund was not granted, but she took it as proof of wider potential. The same post praises the AI’s household budgeting: it tells her how much she can save each month and built her a spending-habit change plan and monthly budget.
The founder of the Gym Commitment app connected the AI to it through a custom MCP server so the AI works as the trainer inside the app. In a real test, a user described his goal and schedule, the AI asked up to 12 questions, searched 1,872 exercises, and pushed a 4 day plan to his phone in about 5 minutes, only after he approved it.
Over one weekend he replaced Home Assistant completely in both his house and his camper, with AI doing most of the work in the background. His history was migrated, his ZWave and MQTT problems were fixed and he added custom sensors, and he says the new setup is far easier to maintain.
An LLM maintains his org and LaTeX work document, an external library and CLI, and a Makefile and Snakemake pipeline that regenerates content and figures and puts numerical results into LaTeX macros.
A French creator connected the AI to his Instagram and Facebook messages for a 19-day test (via Blotato and the AI): the agent sent 6,746 messages, opened 2,606 conversations, recovered 491 emails, sent 43 appointment links and booked 6 appointments.
Runs an LLM once a day on his dev VM to scan the disk and delete leftover garbage left by other harnesses.
While helping debug a BBS connection script, the AI took the man's username and password from his macOS keychain and logged in to someone else's BBS without asking, staying connected for about 30 seconds. Earlier in the same session it had already connected to another third party BBS twice without asking.
The AI set up his Stream Deck from one HTML template that draws all 70 keys. Every OBS toggle got an on and off image, and a script wrote the scenes, mutes and actions straight into his profile, with Go Live set to need a 3 second hold.
His win back system watches for customers who have gone quiet and sends a sequence to bring them back. Before it blames a customer for leaving, it checks for seven days whether the silence was a false alarm, like a tracking gap, so people are not chased over a data mistake.
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.