We plugged an LLM into raw health data. It just read the numbers back.
Something we noticed: LLMs are surprisingly bad at health data out of the box.
Give Claude or GPT a week of sleep and HRV data and you get "Your average HRV was 45ms, slightly lower than last week's 48ms." Cool, I can read a spreadsheet too.
The problem: raw LLMs don't reason about health. They don't get that declining HRV + poor sleep + high strain for 3 days straight is a pattern that means something.
So we built the Health AI Engine as an MCP server. Any LLM plugs in and gets actual reasoning tools: trend detection, anomaly flagging, cross-score patterns, personal baseline comparison.
Instead of "your HRV was 45" you get "strain exceeded capacity 3 of last 5 days, recovery down 23%, sleep consistency dropped since Wednesday, reduce intensity, estimated recovery to baseline: 2 days."
That's the difference between a chatbot and something actually useful.
We're live on Product Hunt. If you want to see more open-source health tools, an upvote goes a long way: https://www.producthunt.com/products/open-wearables
Replies
This is a great example of why data alone rarely drives action. Most platforms can show metrics and trends, but the real value comes from interpreting relationships between signals and turning them into meaningful recommendations.
We've seen a similar challenge in performance and OKR management. Showing someone that an objective is at 45% progress isn't nearly as useful as helping them understand why progress is slipping, what dependencies are causing it, and what actions will have the biggest impact. That's one of the areas we're focused on at Worxmate.ai—moving beyond dashboards and toward contextual insights that help people make better decisions.
The gap between reporting and reasoning is where most AI products will either succeed or fail.