Methodology & Limitations
Effective: 3 September 2026
Specification version: 2026.09.03.2 · Exercise registry: 2026.08.29.3 · Workout document schema: 1 · Voice workflow schema: 2 · Meal request schema: 2
General wellness only. BodyNorth is not a medical device and its outputs are not diagnoses, treatment, dietary prescriptions, laboratory measurements, or guarantees. The methods below have not been clinically validated for this app. Review every result and consult a qualified professional when appropriate.
Workout generation
Manual, deterministic, and optional voice-directed AI workout proposals use the same versioned workout-plan document, exercise registry, validator, and review screen. Deterministic workouts are generated on the iPhone; the same algorithm version, registry, inputs, and preferences produce the same plan. Inputs include primary and optional secondary goal, one to seven sessions per week, rotation, planning time, venue, available equipment, and More/Less/Never exercise preferences.
- Equipment and Never preferences are hard filters. Beginner and intermediate registry exercises are eligible for automatic plans.
- The schedule uses full-body, upper/lower, or push/pull/legs patterns according to weekly frequency. It is a planning convenience, not a recovery assessment.
- Candidates are scored for movement-pattern fit, goal/modality fit, difficulty, and preferences. Stable exercise identifiers break ties.
- Starting sets, repetitions, rest, and RPE vary by strength, muscle, fitness, or mobility goal. The app never invents a weight or measures technique.
Optional AI Workout Coach
After the one-time app-wide AI consent, the user records up to 60 seconds of 16 kHz mono 16-bit PCM WAV and taps Stop. The completed recording, exact baseline, saved workout settings, and only computed age, calculation sex, height, weight, activity level, and calorie goal go to the authenticated BodyNorth Worker. Birthday, account identifiers, meals, sleep, and workout-performance history are excluded. OpenRouter transcribes with full Whisper V3 and automatic language detection, including English, Arabic, and code switching; all provider calls require eligible zero-data-retention/no-data-collection routes.
Stop performs interpretation only. The transcript stays in Worker request memory while a strict model returns a locale-aware paraphrase, intended changes, preserved settings, constraints, and assumptions. The user must choose Approve & build plan before generation, or Add or change details to merge another recording. Up to three review recordings share one reserved daily operation. Low-confidence or incomplete intent disables approval. A changed profile invalidates approval and requires reinterpretation.
Approved generation runs as a durable server job after the request reaches BodyNorth. The app can be backgrounded or closed and recovers the result on return. Approved inputs and results are encrypted in temporary storage for at most 24 hours from submission and deleted earlier after receipt, cancellation, or account deletion. Audio and transcripts are not persisted. Shared timing rules fit only unconstrained prescriptions to the session target; explicit numeric targets remain fixed, and conflicting targets require clarification. Bounded corrective retries receive the rejected candidate and specific validation issues. Diagnostic records contain issue codes, field paths, and timing totals, without request content.
After approval, server validation rejects unknown exercises, unavailable equipment, Never preferences, unsupported experience, invalid prescriptions, duplicate IDs, stale registry versions, and excessive duration, then recomputes outcomes and modification differences. The planning model is forbidden from inferring medical conditions, pregnancy, ability, or restrictions from age or calculation sex. Refine plan uses the latest unsaved proposal, then any accepted queued plan, then the active plan as baseline. Use plan stores an immutable, undoable revision; it activates immediately or queues behind an active/paused workout. Device-local workflow memory restores pending approval/proposal stages and shows a status timeline, but historical summaries do not silently influence new work. AI can still produce unsuitable programming. Medical, rehabilitation, supplement, and meal-planning requests are outside this feature.
Time fitting
The chosen duration is a maximum planning window. The algorithm reserves 12.5% for preparation, transitions, equipment setup, warm-up, and cool-down, clamped to 3–10 minutes. It estimates repetition work at three seconds per repetition, adds prescribed rest and 45 seconds of transition time per exercise, and shares remaining time across duration-based work. If needed, it reduces non-focus sets first and then focus sets, never below one. Extra time is not automatically filled with more exercise.
Workout active-calorie range
The displayed range estimates active energy above rest:
active kcal = max(MET − 1, 0) × 3.5 × body mass kg ÷ 200 × minutes
Each activity uses a broad lower, midpoint, and upper MET profile. Examples range from about 1.8–4.0 MET for balance or mobility, 3.0–6.0 for general resistance work, and 7.0–12.0 for running. When only total time and an exercise list are known, time is divided equally—a material assumption. Actual expenditure can differ substantially with pace, load, rest, technique, fitness, efficiency, environment, illness, medication, and sensor error. A target-calorie value is a planning goal, not a burn requirement or measurement.
Meal-photo estimation
After explicit consent, one meal photo is resized, redrawn on an opaque canvas, stripped of source-file metadata, and sent through the BodyNorth Cloudflare service to OpenRouter and a selected vision-model provider. The request excludes meal location, profile, Health data, and workout history. The Worker does not persist images, prompts, or results and requires zero-data-retention provider routing.
| Automatic sizing source | How it is used | Minimum range floor |
|---|---|---|
| Visible scene context | Recognizable nearby objects, dishware, container geometry, and perspective provide approximate relative scale | ±25% |
| Typical-dimension fallback | Context-appropriate defaults are used when no trustworthy scene anchor exists; an ambiguous cup defaults to about 7.5 cm inner diameter, 9 cm usable height, and roughly 300 mL capacity | ±25% |
The app does not ask the user to place paper or another scale reference, measure the plate, weigh the food, or take a second photo. Visual anchors and default dimensions are approximate; variable, hidden, distorted, or contradictory geometry widens uncertainty.
The model estimates visible edible item mass before calories, applies typical prepared-food energy density, and returns item-level gram and calorie ranges, assumptions, warnings, and confidence. The Worker rejects malformed or inconsistent output, derives totals from accepted items, caps confidence, and enforces the uncertainty floor above. This floor is a product safeguard, not a statistically calibrated confidence interval; the real value can fall outside the displayed range.
Photos cannot reliably reveal hidden oil, sauce, sugar, fillings, exact recipes, density, allergens, or food outside the frame. Labels, recipes, and a properly used kitchen scale are better evidence. Do not use a photo result for allergen safety, insulin or medication dosing, a medical diet, diagnosis, treatment, or eating-disorder management.
Daily calorie guide
When required profile inputs are present, the automatic guide uses the Mifflin–St Jeor resting-energy equation, one of five self-selected activity multipliers (1.2–1.9), and a heuristic goal multiplier of 0.9 for lose, 1.0 for maintain, or 1.1 for gain, then rounds to 10 kcal. If calculation sex is undisclosed, the app requires a manual target rather than guessing.
Population equations can be materially wrong for an individual. The guide does not account for pregnancy, breastfeeding, growth, disease, medications, adaptive metabolism, or body-composition extremes and is not a prescribed diet.
Versioning and verification
Material output changes require an updated implementation or registry/schema version, automated tests, limitations, and change record. Tests verify deterministic behavior, equipment and time constraints, energy equations, request/response bounds, uncertainty floors, and malformed-output rejection. Automated tests do not establish medical safety or real-world meal accuracy. No production accuracy percentage has been established for BodyNorth.
Research sources
These sources inform the design; none endorses or validates BodyNorth.
- US Physical Activity Guidelines: key recommendations.
- American College of Sports Medicine resistance-training guidance (2026).
- 2024 Adult Compendium of Physical Activities and its conditioning MET categories.
- Nutrition5k: Towards Automatic Nutritional Understanding of Generic Food.
- Single-View Food Portion Estimation Based on Geometric Models.
- USDA FoodData Central Foundation Foods documentation.
- Mifflin–St Jeor resting-energy equation.
- Food-photograph portion-selection validation study.
Policies and help
Read the Terms of Use, Privacy Policy, or visit Support.