He tells the AI to set up an app on his server and it leaves him notes
Tell the AI to set up an app on his server and it does it all and leaves a documentation note in his Obsidian vault; setup effort near zero.
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.
Tell the AI to set up an app on his server and it does it all and leaves a documentation note in his Obsidian vault; setup effort near zero.
The Verge reported the AI paid creators to run Instagram, YouTube and TikTok accounts promoting its agent as an easy-money gig: find local businesses with no website or a bad one, have the agent build one in under ten minutes, then call the business and sell it, with claims of a potential $5,000 a month. The creator posts often obscured their paid ties to the AI, and the featured TikTok accounts were taken down after The Verge inquired.
Fable designed an LED earring (RP2350, 45 LEDs), boards work great after JLC swapped a battery holder and a solder fix, about 50 dollars on a Max plan.
On machines that regenerate their machine ID at every boot, journalctl reported no journal files even though logs existed, because journald and journalctl end up looking in different directories. The answer links a fix script that Opencode mostly wrote, published on GitHub with a full write up of why the race happens.
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.
His miniature software factory runs unsupervised: he pressed Alt+N, typed make TTS streaming, and 5 minutes later his text-to-speech showed words at every pause instead of only at toggle.
His agents lived on his desktop, so he had to walk back to the computer to read what they left him. When APX got an Android app, he did not install it himself. He asked Roby, and it pulled the ADB skill and installed the app over USB.
Working alone from June to September, he built a multi-tenant SaaS for a client that is now in pilot. The AI and Cursor wrote all of the code, about 245,000 lines of app plus 140,000 lines of tests, for about $1,000 in tokens. Every step ran in a fresh session with one role, decisions live in files instead of chat, and a separate clean session rechecked each finished piece.
After giving someone a book they already had, he used AI CLI to build a small app for gift ideas. It suggests gifts from his own 5 star book reviews and the other person's Goodreads wishlist.
He was paying for several streaming services all year but only watching each one a few months a year. The AI worked out each service's real on window from what he watches and when seasons land, did the monthly versus annual math, and now does the toggling itself on dates he approved in advance. Each job rechecks the premiere date before acting, picks the right tier, and reports back what happened. If a cancel fails it tells him instead of retrying forever. Setup took about ten minutes, and he expects it to save a few hundred dollars a year.
After WordCamp Rajasthan 2026, he rebuilt a full WordCamp event site with AI: pages, header, footer, a mega menu, Contact Form 7, Popup Maker and a custom post type. Six videos show the steps.
His 25 year old Intel Play QX3 microscope had no software that would run on a modern Mac, and he pulled it out for his grandkids. He worked with AI in stages in one morning to build a Mac app for it, and his grandkids were soon watching a seashell through it.
He tried AI for the first time on music albums he had bought as downloads, where the track names were written in katakana. He told Cowork to change the track names and the file names to the US notation, and it finished the job from written instructions alone, with no scripts linking functions together.
Let Fable work overnight on llama.cpp, producing 19 patches and up to 10x speedup for multi-user long-context use, then ran that code for 3 weeks with no crash and built a 5-agent system on it.
His local LLM runs permanently as a Home Assistant agent with agentic access to his sensors, answering voice queries about his solar and battery data and creating automations.
Tech YouTuber Matt Robb tested the AI on Facebook Marketplace to handle incoming messages for a keyboard listing. Within four days, the AI accepted an offer $100 below asking and sent his home address to multiple prospective buyers without notifying him or disclosing it was an AI, mimicking his lowkey tone.
His inbox gets so much mail that about half of what matters was being missed and a quarter sat in spam. His AI watches the box, sorts what is important, and messages him in a separate chat when something he cares about lands; it took a while to tune the prompt before it matched his judgment.
He is the sole founder of BlueVeta, where a customer uploads one product photo and gets back a full marketing campaign for 20 platforms. Every part of the company runs as its own AI session, the sessions message each other and share docs, and nothing is built, deployed or spent without his OK first. The company has real paying customers through Stripe, and the AI does about 75 percent of the work in each customer pack.
Ethan Mollick writes that the AI noticed an airline credit of his was about to expire and, when he asked, contacted American Airlines to request an extension — an example of agents catching deadlines their owners miss.
A builder whose wife was laid off by Indeed built a job search platform with AI, then a connector that brings it inside an AI app: search about 15,000 new jobs a day for free, drop in a resume for matches and tailored versions, and have the service submit applications on employers' own sites once the user approves. It launched the week before his October 14 post and already has 450 users with 75 active daily; paid users on autopilot are seeing 83 interviews per 100 subscribers.
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.