A random mix from the whole library. Shuffle for a new set.
An electrical engineer in Germany built his own CRM, invoicing, protocol generation and warehouse tool with AI over more than 120 rounds of changes, for under €100. He says the same build would have cost six figures a decade ago, plus €5,000 to €8,000 a year to use, and the tool now runs the way he wants on his own computer.
A man wired his lab instruments to his home network, put all their manuals and programming guides into an AI project, and the AI wrote most of the first set of Python programs that control the instruments and pull data from them. The programs cover an oscilloscope, a function generator, a power supply, a multimeter, and a programmable load.
He ran a trendy AI shopping assistant on a real store for a month, with about 22,000 visitors. Revenue per visitor was $1.118 with it on and $1.112 with it off, for a net effect of about minus $120.
He runs recruiting for an investment firm across 30 open roles spread over five applicant systems. His AI cron runs at 9am, reads the open roles, searches people through data services, checks Gmail so nobody gets emailed twice, and writes new candidates into the right system with its reasoning attached. In about six weeks it surfaced 40 good candidates and the firm made 2 offers.
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.
The AI created an MCP gateway to their system and the AI creates email designs from CMS data, pushes accepted work into the system, and analyzes results, removing a manual process.
Ekaterina Li reports that during her week with AI she connected it to the external tools Kling and Higgsfield and had it edit photos and videos for her. It was one of eight tasks she delegated end-to-end, from idea to execution.
A developer threw a significant codebase at the AI. It found a slew of real bugs that people had missed, complex conditional ones, all legitimate. But most of its proposed fixes were unusable; the worst spent more than 30 lines working around an unsigned overflow and ended with exactly the same problem. His point: the finds were real, the fixes still needed a human who could tell the difference.
A university worker used AI to build a web version of a transcription program that used to need a special Windows machine reached by remote desktop. The new tool pairs a speech model with speaker detection on the university's own systems. Twenty minutes of interview audio now transcribes in 40 seconds with the speaker changes right, and students and staff can use it from a browser.
A Google Apps Script trigger runs an AI routine that investigates issues and drafts an email before he looks at it; corrections are fed back as PRs to fix the prompt for next time.
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.