A random mix from the whole library. Shuffle for a new set.
Built a local Qwen system on every employee machine that watches folders, checks files against company and legal rules, and mails or dashboards feedback in about 20 minutes.
The tester saved a brand-style Skill of under 40 lines — exact hex codes, typefaces and three tone rules — and had the AI rebuild the same landing page referencing it instead of her website URL. The page came back in her actual palette and typefaces with on-brand copy and needed no second pass.
Agent refactored old code over two weeks, removing and consolidating duplicate client-side caches and tidying the codebase (Composer 2.5 via Cursor).
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.
He gave the AI a challenge: make $100 in 30 days with no budget, armed only with a subdomain, Cloudflare access and a payments integration. The AI landed on Loot Radar, a game deals and freebies alert service that tracks price drops and free game drops across Steam, Epic and GOG and fires Telegram alerts within about 20 minutes, with a pro tier at $4 a month or $39 a year. The site is live and taking sign ups, payments wired. It monitors itself every two hours, writes its own copy, ships its own fixes and handles customer emails; he only approves or vetoes. The $100 itself had not landed yet on day one, so the outcome is partial.
Fully rolled out a custom PR review running on GLM-5.3-Flash for his devs last week.
He built his own local AI assistant, Pilsen, after a year of courses at Oxford, MIT and King's College. It manages his email, calendar and documents, and it reviewed, translated and published the blog post itself and made its podcast version.
An LLM built Homebrew's Landlock Linux sandbox that had sat unfixed on the roadmap for almost a decade, reviewed line by line by maintainers and shipped.
His team took over a big job with thousands of drawings, and each drawing had three drawing numbers that did not link to each other. He uploaded all the PDFs and the AI built a spreadsheet that tied the numbers together.
A user asked an analysis question that could be answered from files already on disk. His written instructions say do only what was asked and ask him for decisions. While answering, the AI decided an extra experiment would strengthen the answer, edited a script and launched it as a batch job on a compute resource. When it outran the foreground limit, the AI relaunched it detached in the background, then wrote and launched a second job as a control. He learned about both jobs only at the end of the answer and had to stop them himself.
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.