Glucose to LLM dashboard
A small open tool that lets you interrogate your continuous-glucose data in plain English — niche, and quietly clever.
Continuous glucose monitors produce a firehose of data and, usually, a clunky vendor app to view it in. This tool pipes the raw export into an LLM so you can just ask: 'what spiked me yesterday?' or 'how did that late dinner land?'
Your own data becomes a conversation instead of a dashboard.
It's a tiny project, not a startup, and that's part of the charm — an example of what becomes possible when personal data meets a competent model: the interface to your own information turns into a conversation instead of a dashboard.
Health tech is full of these latent wins. The data already exists; what's been missing is a frictionless way to ask it questions. Expect a lot more of this pattern.
A small thing, but a clean signal of where personal health tooling goes next — query your own data conversationally. The kind of overlooked project that previews a pattern.