baseline
Own your baseline.
Find out what is actually working for you. Your sleep, your labs, your workouts, the things you have been trying — in one place, with a straight answer about which of them changed anything.
Most of the time the honest answer is that it did nothing, and a system worth trusting has to be willing to say so.
How Baseline works
Baseline merges six streams of personal health data — wearable and watch metrics, blood panels, gut and continuous glucose monitoring, meals, symptoms, and supplements — into a single record aligned on one nightly time axis. It then fits a hierarchical Bayesian time series to that record, pooling across a population to estimate the causal effect of an intervention on an outcome for one individual.
Worked result
Magnesium glycinate 400 mg increased deep sleep by 18(95% credible interval +6 to +31 minutes) across 62with a 97% posterior probability of benefit. Estimated with a hierarchical Bayesian model, n=1 pooled across the cohort, holding travel, alcohol, and late meals as confounders.
N1Bench
We built an open benchmark so the claim above can be checked rather than taken on trust. It asks the hard version of the question: on data where the answer is known, does a system find the real effects, and does it decline to invent one when there is nothing there?
Our engine scores highest on it, ahead of the best published method from the academic literature. Four of the six kinds of question have no real effect to find, which is where most approaches come apart.