MIntelligence — competitive & technical brief
The science and the logic behind the suite — how each score is computed, why it's built the way it is, and the one thing it sees that no wearable can: your nutrition and body composition.
What MIntelligence is
MIntelligence is Metapace's wellness intelligence suite — three features that turn an Apple Health connection and the nutrition data Metapace already holds into coaching-grade insight. It rests on a single premise:
Nutrition, body composition, sleep, training and recovery — all in one place, on a device you already own.
No proprietary band. No subscription ring. No extra hardware. Because the suite reads from Apple Health, it works with any watch or band that writes to it — and every score is transparent, computed privately on your device, and explained in one tap.
The M-family has two pillars: MIntelligence, the umbrella brand for the suite — what the app does for you; and MTribe, the Pro membership layer. Going Pro means joining the MTribe.
Nightly stages, hypnogram, overnight vitals (HRV, respiratory rate, wrist temperature, SpO₂), trends and a transparent sleep score built from five weighted components — publishing exactly how every point is earned.
Training load (Acute:Chronic), true time-in-zone from per-second heart rate, aerobic efficiency, personal bests, and body-composition-aware training that frames effort against your weight and energy balance.
Six signals — sleep, HRV, training load, nutrition and energy, resting heart rate and consistency — fused into one 0–100 readiness score. Two of the six are unique to Metapace.
The landscape in 2026
Every recovery and sleep product on the market shares the same limitations. MIntelligence is built to close them.
The dedicated recovery players lock their best science behind a proprietary band or ring — a recurring membership, a device to charge, one more thing to buy and wear. MIntelligence runs on a watch or band you already own.
Why it mattersHardware lock-in is a business model, not a scientific requirement. The sensors on a modern watch are equivalent or superior.
A single number appears each morning and you're asked to trust it. The score built into your watch is a timing measure — it doesn't use HRV, resting heart rate, respiratory rate or stage quality. Most readiness scores are notoriously opaque. MIntelligence shows its work.
Why it mattersA number you can't interrogate is a verdict. A number you can explain is a conversation.
Physiology without nutrition is half the picture. A deep caloric deficit measurably impairs recovery and deep sleep — yet no wearable knows you're in one. Metapace holds both sides, because nutrition and body composition are its home turf.
Why it mattersA sustained −500 kcal/day deficit is the single most actionable lever on recovery that pure sensor data can't detect.
Four structural advantages
These come from what Metapace already knows and how it's built. A competitor can't match them without rebuilding into a full nutrition and body-composition platform first.
Metapace already knows your energy expenditure (Mifflin-St Jeor / Katch-McArdle), deficit-or-surplus trend, body-fat percentage, fasting windows and weight trajectory. Recovery is read against whether you're actually fuelled — a signal pure wearables don't have.
Why it mattersA recovery score without nutrition context is like a weather forecast without wind: technically correct, practically incomplete.
Someone at 35% body fat in a 500-kcal deficit recovers very differently from someone at 15% at maintenance. MPace frames training energy as kcal per kilogram — relative output — so progress reads correctly regardless of size.
Why it mattersA 60 kg runner and a 100 kg lifter burning “400 kcal” are doing very different things.
Competing scores are black boxes. MInsights publishes the exact five-component formula (25 duration, 25 stage quality, 20 efficiency, 20 HRV, 10 consistency); MRecover shows all six contributors with weights.
Why it mattersThe single biggest UX difference is trust. An explained score you believe beats a precise score you don't.
Everything runs on a device you own. Reading from Apple Health, it works with a wide range of watches and bands — and honest empty states make clear when richer sensors would add more. The split-sleep bug that breaks the closest App Store rival is solved here.
Why it mattersAdding hardware is a tax on the user. The sensors already on their wrist are more than sufficient when the math is right.
The science & the logic
Every score rests on a deliberate engineering choice. Here is the reasoning behind each one, in the open.
01 — Correct sleep first
Wake at 3 a.m. for an hour and the watch writes two or more sleep records. Naïve code keeps only the largest block and throws away the rest — corrupting total sleep time and every score built on it. This is the exact failure that breaks the closest app-only alternatives.
MInsights runs a 90-minute gap-merge: sessions less than 90 minutes apart are treated as one continuous night; a true daytime nap is kept distinct and never pollutes the nightly score.
Total sleep time sums only real asleep stages — core, deep, REM — never time merely in bed. Missing stages are marked unavailable, never invented.
The merge, step by step
Why 90 minutesIt spans one full sleep cycle — the longest gap a normal bathroom break could produce without being a deliberate wake-up.
02 — HRV done correctly
The watch exposes SDNN — the standard deviation of beat-to-beat intervals — not the RMSSD some dedicated devices use internally. These are different values; converting between them without the raw interval series (which Apple doesn't expose) would be a fabrication.
So MIntelligence never invents a conversion. It builds a baseline from your own history and reports deviation — “8% above your 14-day average” — with the methodology explained.
How HRV is shown
Last night vs your 14-day baseline
+8%above average
Shown as deviation from your own history — never a raw millisecond figure dressed up as a universal “good” or “bad.”
03 — Dual rolling-window baseline
Every “vs baseline” comparison weighs a 7-day exponentially-weighted average against a 28-day mean. Only a drop beyond roughly one standard deviation reads as a genuine negative signal — far more robust than day-over-day noise.
Why two windowsOne fast (7d), one slow (28d) — capturing acute shifts while anchoring to your long-term norm.
04 — Training load (Acute:Chronic)
MPace weighs a 7-day acute load against a 28-day chronic baseline, each session weighted by heart-rate zone (a Banister-TRIMP approach). Where per-second HR exists, zones use true time-in-zone; when estimated, the card says so.
GuardrailWithheld until 28 days of history exist — never fabricated early.
05 — Missing-contributor re-weighting
The wellness domains are independent — you might have workouts but no tracked sleep. When an input is missing, MRecover doesn't punish you: it drops that contributor and re-normalises the rest to still sum to 100%. Scoring a missing signal as 0 would falsely crater readiness; scoring it 100 would falsely inflate it.
score = Σ(presentᵢ · weightᵢ) ÷ Σ(present weightᵢ)
One exceptionTraining load defaults to a neutral 100 when absent — no workouts means no fatigue, not a penalty.
06 — Baseline gates
A readiness score appears only after at least 7 nights of sleep and 14 of HRV; a sleep score waits for 3 nights; the ACR ratio needs 28 days; wrist-temperature deviation needs 5 or more baseline nights. Below those, the app says “building your baseline” — never a number it can't stand behind.
Why gate at allEarly scores with thin baselines look precise but swing wildly. A shaky first number is worse than no number.
07 — The nutrition–recovery bridge
Metapace derives expenditure from established equations and tracks real intake and weight. So MRecover can say what no wearable can: a sustained deficit is likely suppressing recovery. An extended aggressive deficit (beyond −700 kcal/day) hard-caps the nutrition contributor at 40/100 and suggests a diet break.
EvidenceResearch shows deficits above roughly 700 kcal/day measurably impair recovery — capping prevents the score reading “fine” when nutrition is undermining it.
08 — Honest time boundaries
Before noon, the freshest completed night is still yesterday's. Open the app at 1:45 a.m. and it shouldn't flag “no sleep tracked” — the night is still happening. Sleep is filed under the morning it ends, workouts bucketed by start time, with a noon cutoff that prevents premature banners.
StakesA false “no sleep tracked” alarm at 2 a.m. destroys trust. This logic is invisible when it works — and catastrophic when it doesn't.
09 — Gaps stay blank, never zero
If a night wasn't tracked, that day appears as a blank gap — the line connects across it. Never a zero bar, never interpolated, never borrowed from the prior week. An “X of Y nights tracked” label keeps coverage honest.
The differenceA zero bar reads as “something terrible happened.” A gap reads as “we don't know.”
Honest time boundaries, gaps left blank instead of zero-filled, trustworthy units filtered first, and any value withheld until its baseline pool is deep enough. The biggest risk in health features is an impressive number that's quietly incorrect. Every metric here degrades to a clear, explained empty state instead.
The sleep score, in the open
The score that ships on your watch is a timing-and-duration measure. It doesn't factor in HRV, resting heart rate, respiratory rate, or how much deep and REM sleep you actually got — and it isn't exposed for apps to read. MInsights computes its own, physiologically-grounded score from raw stage data, and publishes exactly how.
100
total pointsAnd it degrades honestly: if an older watch can't report stages, those 25 points redistribute to duration and efficiency; if HRV is missing, its 20 move too; below three nights you see “building your baseline.” Tap any score in the app to see this exact breakdown for your night.
The readiness layer
MRecover fuses six signals into one 0–100 score. Four the dedicated devices also use — but the nutrition and consistency reads are Metapace's alone. It's a read-only consumer: biometric inputs arrive through already-authorised scopes; nutrition inputs come from your own logged data.
Last night's MInsights score — the entire physiological assessment as one input. Sleep is the foundation of recovery, so it carries the most weight.
Missing → dropped & re-weighted.
SDNN deviation from your dual-window baseline (7d EWMA vs 28d mean). The strongest single biomarker of autonomic recovery.
Requires ≥14 nights. Missing → dropped & re-weighted.
Acute:Chronic proximity to optimal (0.8–1.3 = 100, degrading symmetrically). Are you training harder than your body has adapted to?
Missing → defaults to neutral 100 (no load = no fatigue).
Caloric-balance trend vs your expenditure. Deep deficits (beyond −700 kcal/day) hard-cap this at 40/100 and suggest a diet break.
Only Metapace
Sleeping RHR vs baseline. A low weight — it rarely says something HRV hasn't already, but it validates the story.
Missing → dropped & re-weighted.
Sleep-timing regularity plus training frequency. Social jet lag is one of the most underrated recovery suppressors — measured and penalised.
Only Metapace
Across the whole suite
When recovery dips, the suite can point to a multi-day deficit as the likely cause — a read no pure wearable can make.
Every score is explainable in one tap — never a verdict, but the start of a conversation. Component weights are published, not hidden.
The 90-minute gap-merge stitches a mid-night wake-up back into one night — the edge case app-only rivals get wrong. Naps stay separate.
An automatic Monday review across sleep, training and nutrition — best and worst recovery day, plus a correlation insight nobody had to write.
When data is thin you get an honest empty state — never an impressive number that's quietly wrong.
Every score is computed on your phone and cached locally, file-protected. Raw data stays on your device; privacy is the architecture.
Respiratory rate, wrist-temperature deviation, SpO₂ and a full-night hypnogram — each framed against your own baseline, never absolute.
Calm, personal language — “often an early sign your body is fighting something” — never “you may be sick.” Awareness, not fear.
The master comparison
Compared by product category, not by name. ✓ present and strong · ~ partial · ✕ absent.
| Capability | MIntelligence | Built-in watch score | Subscription wearable | Premium smart ring | Watch readiness | Other watch apps |
|---|---|---|---|---|---|---|
| Runs on hardware you already own | ✓ | ✓ | ✕ | ✕ | ✕ | ✓ |
| No proprietary device or membership hardware | ✓ | ✓ | ✕ | ✕ | ~ | ✓ |
| Transparent, tap-to-explain scores | ✓ | ~ | ✕ | ✕ | ✕ | ~ |
| Sleep stages & physiological depth | ✓ | ~ | ✓ | ✓ | ✓ | ~ |
| Full-night hypnogram & overnight vitals | ✓ | ✕ | ✓ | ✓ | ~ | ~ |
| Reads your nutrition / energy balance | ✓ | ✕ | ✕ | ✕ | ✕ | ✕ |
| Body-composition-aware training | ✓ | ✕ | ✕ | ✕ | ✕ | ✕ |
| Aerobic efficiency trending | ✓ | ✕ | ~ | ✕ | ~ | ✕ |
| True time-in-zone (per-second HR) | ✓ | ✕ | ✓ | ✕ | ~ | ~ |
| Training load (Acute:Chronic) | ✓ | ✕ | ✓ | ~ | ✓ | ~ |
| Daily readiness score | ✓ | ✕ | ✓ | ✓ | ✓ | ✓ |
| Missing-contributor re-weighting | ✓ | ✕ | ~ | ~ | ✕ | ✕ |
| Dual-window baseline (7d vs 28d) | ✓ | ✕ | ✓ | ✓ | ~ | ✕ |
| Cross-domain weekly review | ✓ | ✕ | ~ | ~ | ✕ | ✕ |
| Raw data stays on your device | ✓ | ✓ | ✕ | ✕ | ~ | ~ |
| Honest empty states (no fabricated numbers) | ✓ | ~ | ~ | ~ | ~ | ✕ |
Capabilities reflect each category's typical offering as of June 2026. “No extra hardware” credits products that run on a device you already own.
The bottom line
The dedicated devices have physiology but no idea what you eat. The watch-native scores won't explain themselves. The built-in score is free but timing-only and locked away. The nutrition apps have your food but no recovery science. MIntelligence brings them together — with every score explained in a single tap.
