AI health coach for your wearable data

Your Oura readiness has read 71 most mornings since February. Your Apple Watch puts your VO2 max at 44, and it’s been 44 for four months. The rings close green, the readiness band says “good,” and nothing in either app suggests anything is wrong. Nothing is wrong. Nothing is moving either, and no screen you own will tell you why.

That’s the gap. The dashboard reports each number in its own panel: HRV on one screen, sleep stages on another, glucose in a third app that doesn’t know the first two exist. Five apps, five charts, zero instructions on what to do next.

The thing worth paying for isn’t more data. You already collect more than you read. It’s an AI health coach for your wearable data: something that reasons across the streams you’ve already got.

What an AI health coach for wearable data does that a dashboard does not

A dashboard plots a stream. A coach reads streams together, assigns a cause, and names one thing to do about it. That’s the whole difference, and it’s a difference in behavior, not branding.

Three jobs a dashboard structurally can’t do. It can’t connect two systems you’d never think to line up, like the glucose swings on a stressful day and the HRV you lost the next morning. It can’t credit the right cause and drop the wrong one, telling you the zone 2 work is carrying your fitness while the HIIT you’re proud of barely registers. And it can’t put a deadline on the fix, the recheck date that turns a suggestion into a plan.

A chart shows the line. A coach tells you why it bent, and what bends it back.

There’s a second source the coach almost always has, and it’s free: time. A single reading is noise. The meaning is in the slope across weeks, and a coach reads the slope where a snapshot reads the dot.

Reading across Oura, Apple Watch and CGM at once

Here is the move a dashboard can’t make. A flat number becomes a finding the moment a second stream explains it.

Take that VO2 max stuck at 44. On its own it’s a plateau, and the usual advice is “train harder,” which is exactly wrong here. Line the training log up against your HRV and the cause is obvious: every logged session ran in zone 4 to 5, and your HRV never recovered between them. You’re training hard enough to fatigue the system and not easy enough to build it. The fix isn’t more work. Cap two sessions a week in zone 2, keep the hard days hard, and recheck VO2 max next month.

Now cross your CGM with your HRV, two systems most people read on separate screens. Your glucose swings widest, a 50 mg/dL range across the day, on the days your HRV reads lowest the next morning. The volatile-glucose days aren’t random; they’re the high-stress, low-sleep days, and your nervous system is paying for them overnight. The fix isn’t a stricter diet. Flatten the biggest swings, the post-lunch crash and the late carbs, and watch whether the next-morning HRV lifts over the following two weeks.

One more, shorter. Your resting heart rate is up 6 bpm over six weeks and you blamed the training block. It tracks the training poorly and the calendar well: the climb lines up with two or three weeknight drinks that crept in, not the workouts. Pull the weeknight alcohol and the resting heart rate should settle inside two weeks.

In each case the second stream, not the first, named the fix.

How the coach assigns cause, not another chart

The mechanism is simple to describe. The coach holds your streams on one timeline and looks for one signal that moves when another moves, then right-sizes the claim to what the data can carry.

The right-sizing is where trust is won or lost. When the data is too thin to call a cause, the honest answer is “not yet, here’s what I’m watching,” not an invented reason. Two late dinners and one short night isn’t a pattern; it’s a coincidence you note and wait on. A coach that says “associated with” when it means a correlation, and waits for the pattern to repeat before it tells you to act, is a coach you can act on. The n-of-one signal is noisy by nature. Caution in the verb is the credibility.

And the reference that matters is yours, not the population’s. A 55 ms HRV night means nothing in the abstract. Read against your own 70 ms floor, it’s a real dip worth a question; read against someone else’s average, it’s a number from a stranger’s body. Your baseline is the only yardstick that fits you.

Why this isn’t a generic chatbot

The fair objection: “I can paste my Oura export into ChatGPT and ask.” You can, and it’ll summarize the file you pasted. That’s genuinely useful for one afternoon. It also stops there.

A general chatbot sees one snapshot, with no memory of last month and no second stream sitting beside it. It pattern-matches the text you handed it. It doesn’t watch your line, because it has no line to watch. Ask it again in March and you’re re-explaining yourself to something that has already forgotten you.

A coach is wired to your live streams, carries your history, and reasons across your blood and your wearables together. That’s why the instrument has to be continuous rather than a one-off prompt: the value is in the months it’s been watching, not the cleverness of a single reply. And a system acting on your body needs your real, sourced numbers, the actual 110 mg/dL from your sensor, not a plausible-sounding average it filled in. Acting on a hallucinated number is worse than acting on none.

How Depth turns your streams into one read

This is what Depth is built to do. It pulls your Oura, Apple Watch, Whoop and CGM continuously, lines them up against your bloodwork, and reasons across all of it on one timeline.

On the wearable side it watches HRV, resting heart rate, VO2 max, sleep stages, and continuous glucose. On the blood side it ties those to ApoB, hs-CRP, HbA1c, fasting insulin, ferritin, and Lp(a), so a rising resting heart rate or a stalled VO2 max gets read next to the markers underneath it, not in isolation. The wearables see the day to day; the blood sees the substrate; Depth reads them together and hands you the one thing to change.

The next step is small. Early access and the Founders Edition let you connect your wearables and put the coach to work on the streams you’re already collecting.

Which brings us back to that VO2 max of 44, flat for four months. It was never a plateau. It was a question no single app could answer, sitting in plain sight across two of them. Read together, it’s a number you now know exactly how to move.