Loading page…
A content creator vibe-coded an app for himself while ill: continuous glucose monitor and Apple Health data all stored locally, with a single API letting AI analyze his vertigo triggers and give advice in the moment
no monetization yet
The killer feature is "local-first + multi-source health data + AI giving actionable advice in the moment" — glucose, Apple Health, expenses, and notes all feed the AI without the data ever leaving the device, and when vertigo hits it tells you right then whether to stand, lie down, or eat.
Fewer bars = easier, cheaper, or faster for an AI-assisted solo builder. Editorial judgments based on the case details.
This project didn't start as a business, it started as self-rescue. The protagonist runs Topbook, a knowledge-content channel with over a million followers, and describes himself as a humanities major who doesn't write code. He developed Ménière's disease, suffering sudden spells of vertigo and fainting with no warning, which upended his life and stopped his content output for six months. In that situation he vibe-coded an app for himself — called Thinking Space — that stores data from a continuous glucose monitor, Apple Health, expense tracking, and notes entirely on his own phone, with a single API letting AI analyze the triggers of his vertigo and give actionable advice the moment an episode hits. The framing has to be clear: **this is not a ready-made business**. There's no monetization, no pricing, and it's purely for personal use — the creator himself only says he can share it if people are interested. Treating it as a "copy this and make money" template would miss the point entirely. The video itself pulled 187K views, but that's traffic from the founder's existing personal brand, not something the product earned. So why include it? Because a deeply real self-rescue story points at a product form with genuine market potential: "local-first + multi-source health data + AI actionable advice in real time." And it incidentally proves something else — a humanities major built a moderately complex health app with vibe coding, which means the development barrier for this kind of product has been flattened by AI. What we're capturing is that **direction** and that **signal that the barrier is broken**, not its business model.
Nothing was sold here, so the real question is what distribution actually happened. Two things shipped.
The quick-reference card — acquisition channels, replication playbook, and risk map — is members-only.
Join the Unicorn Club — $5/moCancel anytime, in one clickPaste into Claude Code / Codex and get a working version of this product end-to-end.
Two production-grade prompts per idea — a full build spec and an SEO growth plan — plus 10 tailored build specs a week. Members only.
Join the Unicorn Club — $5/moCancel anytime, in one clickEvery claim traces back to a listed source — open any of them and check the number yourself.
Data credibility: The creator states plainly that he built it to help himself, that all data stays local, and that it hasn't been publicly released or sold (Seven Timers is on the HarmonyOS store but free). No revenue figures at all — included as a directional reference. All revenue figures are founder-reported or estimated by the video creator — unaudited.
No money has come in. Seven Timers is a free download and Thinking Space has never been released, so what matters is what the architecture makes the first sale look like.
Two loops turned here, and only one of them is about software. The health loop is the one that mattered.
The stretch ran for months with no upside in it. One ear went nearly deaf, vertigo and fainting arrived without warning, and arranging a single normal day became impossible; the bookstore stayed open because partners carried it, and the channel simply stopped.
The rest of this breakdown — 10 more sections — is in the Unicorn Club, with every section of all 1,335 ideas: first customers, first dollar, the flywheel, and the silent stretch.
Join the Unicorn Club — $5/moCancel anytime, in one click