A random mix from the whole library. Shuffle for a new set.
An IT provider managing multiple Microsoft 365 client tenants asks the AI to take a new-user request straight from email, create the user in the right tenant, and email the client back with the details - work his technicians previously did by hand across many tenants.
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.
A user gave a farm of Opus agents on three AI accounts one job: make money. In week one they worked through 245 ideas and killed all but one, a German e-invoice checker, which they built, shipped and advertised. It drew 68 visitors and 6 real invoice checks and earned nothing. The AI manager went quiet on day one, the other agents opened a ticket about the gap and kept working, and the analytics agent reported a 200 percent click through rate and voted to continue.
Alongside his homemade TMS, Wes Oberman built a settlement payroll program that calculates every driver's pay automatically. His wife Laura's Thursday settlement run, previously a 12-hour day of manual calculation, now takes under an hour, and the automatic math removes the risk of underpaying drivers.
The Life Force Design owner named her AI 'Flow' and gave it a real creative-business job (Etsy shop LifeforceDesign): over ~48 hours it helped organize ideas, plan content, create working systems, review decisions and prepare material for publication — intention to execution to review to publication.
The AI wrote Zig tools in real use, including a wasm utility integrated into a site and reverse engineering a USB wire protocol for an industrial camera driver.
Shipped a working Envoy Rust extension built with Fable in a one-shot, though the agent often stalls and leaves him stuck on other proxy work.
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.
Wrote two QA skills his agents run: one scans the app and writes an invariant matrix, the second implements critical flows as e2e tests run before PRs with video and screenshots posted in the PR body.
Every release of his app used to cost him a weekend taking store screenshots in 16 languages, cropping them and pasting them into store cards. He and the AI built a small tool that drives headless Chrome through the real app, grabs the screens in each language and composes the finished cards with captions and backgrounds. A release is now one command.
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.