How the coach decides
The honest version, for people who want to know what is actually computed before they connect their data.
The numbers are math. The words are AI. Every verdict Milewise gives you starts in a deterministic decision core: plain, testable arithmetic over your own data, computed fresh each time you talk to the coach. The AI model's job is to present those results in your language and to coach within them. It does not invent your readiness, your load, or your limits.
Your baselines, not population norms
Overnight HRV and resting heart rate are judged against your own rolling baselines, not against tables of what is normal for other people; sleep is judged by what last night actually delivered. A resting heart rate of 52 is an alarm for one athlete and a Tuesday for another; the only meaningful question is how today compares with your recent trend, and trends beat single readings: one noisy HRV night does not flip a verdict on its own.
What gets computed
- Readiness: an HRV-trend ladder over your baseline, combined with resting heart rate and sleep, resolving to green, amber or red.
- Training load: acute vs. chronic workload plus a sanctioned weekly ramp, so volume growth is judged against what your history supports, with the worst jumps blocked outright.
- Plan compliance: what you actually ran against what was planned, by sport, so a stroll never silently completes a planned run.
- Goal feasibility: your current performance level against the goal and its date, including gates for debut distances.
These results reach the model as a fixed block of labels and numbers. When the coach cites a figure, that is where it comes from.
Missing data is not caution
If there is not enough data for a call, the verdict is no verdict, stated as such. It is deliberately distinct from amber: an athlete without wellness data would otherwise live in permanent artificial caution, which teaches you to ignore the coach. When Milewise does not know, it says so.
Hard rules live where plans are written, not in the prompt
The hardest limits are enforced at the moment a plan is created or changed: a plan that jumps weekly running volume by more than 30 percent, schedules more consecutive running days than your own history supports, or ignores the days you said you can train does not get written, no matter how the conversation went. The finer ramp targets are computed on every write and put in front of the coach, which has to fix the plan or tell you plainly why it stands. This split is a deliberate design choice: safety rules that live only in an AI model's instructions can be argued with; rules in the write path cannot.
What the AI model actually does
Language, context and coaching judgment inside those bounds: which session fits the week, how to adjust around your race, what your splits say about pacing. Milewise runs on EU-resident AI infrastructure; the providers, their regions and the contractual training-use restrictions are listed in section 9 of the privacy policy.
Limits, stated plainly
Milewise is an AI coach and can make mistakes. It gives training and fitness guidance only, never medical advice. If something feels wrong in your body, that signal outranks every number on this page.
More on the data itself: what the coach reads and the one thing it writes.