How it works
What the AI does, and what it does not
The same page exists inside the app. It is here too, so you can read it before you install rather than after.
What it does
- Reads every value on your report and explains what each one measures
- Compares your value to the range your own laboratory printed beside it
- Tells you how much a value has to change before the change means anything
- Answers your questions about your own results, in your own language
- Keeps your results together across laboratories and years
- Says plainly when it does not know
What it does not do
- Name a condition, or tell you what your results mean about your health
- Recommend treatment, medication, doses or supplements
- Publish reference ranges of its own — we hold none, anywhere
- Connect what you ate to a value on your blood test
- Replace a consultation, a clinician, or an emergency service
- Make decisions about insurance, employment or eligibility
Where the answers come from
Two sources, and nothing else. First, your own report — the values on it and the ranges your laboratory printed. Second, reference content drawn from trusted medical sources, human-reviewed before it is ever shown, and attributed where the source requires it.
The AI is constrained to those two. It cannot introduce a threshold that is not in the sources, because there is nowhere for one to come from. That is an architectural limit, not a policy we hope it follows.