Inside the Engine · Layer 1

The read.
Where the engine stops.

The homepage shows the engine as a schematic. This is the deep version of the engine itself — Layer 1. Structured data goes in; a single conservative interpretation comes out as the CFFS, refreshed weekly as the CFWS. It prescribes nothing. Everything downstream — programs, nutrition, the client readings, the coaching loop — is the Performance Coaching application (Layer 2), powered by this read and documented separately.
One interpretive core8 signal domains5 pillars3 body statesInterpretation terminates at the CFFS
By the Numbers

The interpretation core is small and dense. Every figure is counted directly from the codebase.

221

intake signals

the read instrument · 8 domains

5

interpretive pillars

FMM primary + PTS/HABNS/RRS/BIRS

4 + 11

Fat Map zones

macro + extended

3

body states

the classification

CFFS

one read

refreshed weekly as the CFWS

39k

lines of canon

the doctrine behind it

This is the engine alone. The application built on it — the Performance Coaching environment, ~126k lines across 192 routes and 65 tables — is the far larger codebase, documented separately. The interpretation is small; the system that makes it usable is large.

The Pipeline

Four engine stages, then the handoff.

The read instrument feeds the CFFS. The CFFS is re-read weekly as the CFWS, and a deterministic monitor watches it for drift. That is the whole engine — it terminates here. Everything past it is the Performance Coaching application (Layer 2), powered by the read.
00The Read InstrumentInputs
01CFFS — Core InterpretationLayer 1 · the terminus
02CFWS — Weekly Re-ReadLayer 1
03Signal MonitoringLayer 1 · governance
00

The Read Instrument

What the engine reads. Mostly deterministic capture; the only model here transcribes blood panels. The capture surfaces are delivered by the application — the signal schema is the engine's.

Foundational Intake

deterministic

8 domains · ~200 scale signals

The deep input. Eight scored signal domains map one-to-one onto eight JSONB buckets the engine reads: Fat Map, Injury, Training, Nutrition, Schedule, Sleep, Stress, Medications/Supplements.

intakes.*

Baseline

deterministic

measurements + photos

Bodyweight, waist, hips, chest, and three photos (front / side / back). The photos feed the engine’s vision read; bodyweight floors the nutrition protein anchor.

baselines.*

Medications

deterministic

free text · longitudinal

A single free-text field soliciting hormonal and non-hormonal pharmacology. Read by the engine for signal class, never moralised, never propagated as a compound name to client prose.

clients.medications

Blood Panel

Claude Haiku 4.5

optional · multimodal

Client uploads a lab PDF/photo. The engine transcribes every marker against the lab’s own printed range — transcription, not diagnosis. Only a coach-approved panel reaches the interpretation.

blood_panels.*

The CFFS is coach-triggered only after both the intake and the baseline photos are in, so the Fat Map can read spatial patterning from the photos. The engine's entry point is the Foundational Intake — the public scorecard is a Performance Coaching lead-gen tool, upstream of and separate from the engine.
01

The CFFS

Coach-Facing Foundational Synthesis. The heart of the engine. Interpretation terminates here.

Body Recode™ Interpretation Engine

Claude Haiku 4.5 · multimodal

Reads

  • Eight intake domains (pre-summarised: average, elevated ≥3/4, low ≤1/4)
  • Baseline measurements
  • Baseline photos → vision read (Spatial Patterning)
  • clients.medications (free text)
  • Dietary context (hard constraints)
  • Approved blood markers (the coach gate)

Does

Pre-summarises the scale domains, reads the photos as one signal stream feeding Spatial Patterning, and resolves the whole picture through the Fat Map’s four macro zones. Conservative resolution always overrides the optimistic read. It classifies the body state and rates four exposure-readiness signals — and prescribes nothing.

Produces

  • body_state_classification
  • resolution_state
  • client_context_summary
  • primary_patterns_and_signals
  • capacity_constraints_and_guardrails
  • risk_flags_and_watch_items
  • tensions_and_tradeoffs
  • explicit_non_directives
  • closing_interpretive_notes
  • visual_signal_summary
  • exposure_readiness ×4 (Capacity / Schedule / Regulation / Behaviour)

Vision

Front / side / back photos are base64-encoded and passed to the same Haiku call. Eight rules govern the read: photos are one signal, never the conclusion, and never an aesthetic verdict.

Blood markers

Only a coach-approved panel is read, against the lab’s own ranges. A single out-of-range marker is short-arc evidence, never a diagnosis.

One live read

Generating archives the previous CFFS. reassessment_flagged is always set server-side, never by the model — it is a temporal construct.

02

The CFWS

Coach-Facing Weekly Synthesis — the weekly re-read. Still interpretation, still coach-facing, still prescribes nothing.

Reads

The week’s check-in signal, anchored to the CFFS baseline. The capture itself is a Layer 2 surface; the engine consumes it the way it consumes the intake.

Rule

Readiness moves one notch at a time from the CFFS anchor. Red is the floor. Two-notch jumps only on a named safety event. Single-form answers can’t downgrade alone.

Produces

A weekly synthesis + the four readiness colours → cfws.*. The accumulated sequence becomes the input to the block-end arc.

Claude Haiku 4.5
03

Signal Monitoring

The engine’s self-governance: it decides when the read has drifted enough to need refreshing. Deterministic. Prescribes nothing.

Drift

Any Red in the latest CFWS = high. The same signal Amber/Red across two consecutive weeks = sustained instability. A two-notch drop = high.

Reassessment routing

Drift routes to a lightweight, delta, or full re-read. Signal-based triggers are suppressed until the CFFS is ≥21 days old; a 12-week cap forces a full re-intake.

RPE creep as signal

Avg logged RPE ≥ prescribed +1.0 = creep; +2.0 or any set ≥9.5 = severe. The logging is a Layer 2 surface; the monitor consumes it as one more drift input.

This is where Layer 1 ends. The monitor’s recommendation loops back to a fresh CFFS. Everything past this point is the application.
Layer 2 · Powered by the engine

What’s built on the read.

The engine terminates at the CFFS. Everything below is the Performance Coaching application — the first of five environments — powered by the read. It consumes the CFFS and never bends it. It is documented separately; the other environments (Executive, Tactical, Clinical, Developmental) build their own Layer 2 on the same engine.

Client readings

  • ·Foundational
  • ·Program
  • ·Nutrition
  • ·Medications
  • ·Trajectory

Generators

  • ·Program (training)
  • ·Nutrition (+ validator)
  • ·Medications Analysis
  • ·Blood Panel Analysis
  • ·Coach Guidance
  • ·Recovery Clamp

The weekly loop

  • ·Weekly check-ins (A / B)
  • ·Coach feedback
  • ·Workout logging
  • ·Block-end review
Execution is bounded by interpretation, never the reverse. A program that wants more load or a client who wants a faster result never changes the read. That asymmetry is the whole contract between the two layers.
The Lens

Five pillars. One synthesised read.

The engine reads the body across five pillars at once. No single pillar drives the output alone; the interpretation is always a synthesis of the full picture.
FMM

Fat Map Method™PRIMARY

Primary pillar. Fat accumulation read as hormonal and metabolic signalling, not energy surplus. Where the body stores fat reflects its adaptive response to the current environment.

PTS

Performance Training System

Physical stress exposure, training load, fatigue and adaptation. Defines what training the body can tolerate now.

HABNS

Hybrid Animal-Based Nutrition

Nutritional sufficiency and biological threat signalling. Is intake supporting regulation or reinforcing scarcity.

RRS

Recovery & Regulation System

Capacity to restore and return to baseline. Distinguishes genuine recovery from suppression. RRS always overrides training.

BIRS

Behaviour, Identity & Rhythm

Emotional load and identity constraints as structural biological stressors. Compliance and identity threat are inputs, not psychology.

The Classification

Three body states. Four zones, eleven sub-zones.

The deep state (named below) is the engine’s own classification, with a public-facing label for client language. The Fat Map reads at two resolutions: the macro zone says where load is expressed, the extended sub-zone says how. Fat-storage conclusions are valid only on the long arc — months, not weeks.

Remediation

public: Depleted

Under load it cannot resolve. Performance-level intervention here is counterproductive. Most who present believing they are elsewhere are actually here.

Optimisation

public: Transitioning

Stabilised. Capacity exists to pursue body composition and performance. Where most coaching begins, but few arrive here.

Post-Optimisation

public: Ready

Performing. The goal shifts to identity-level performance and long-term maintenance. Built over time, never forced.

MZ1 · Stress Belt

Stomach / Waist

Cortisol and adrenaline dominance

Extended zones

  • ·Lower Abdominal Compression
  • ·Lower Back Shelf
  • ·Solar Plexus Compression

MZ2 · Gut & Bloat

Digestive region

Insulin timing disruption

Extended zones

  • ·Lower Abdominal Distension
  • ·Ribcage Bloat

MZ3 · Hip & Thigh

Hips / Thighs

Reproductive hormone and metabolic conservation

Extended zones

  • ·Glute Shelf Retention
  • ·Lower Quad Crest Retention
  • ·Hamstring Tie-In Retention

MZ4 · Upper Body Stress

Upper body

Nervous system load, adrenaline, sleep retention

Extended zones

  • ·Upper Back Puffiness
  • ·Shoulder Bracing
  • ·Neck Holding
The Machinery

What holds it together.

Shared discipline runs under every stage — the same model strategy, the same JSON handling, the same language guards, the same refusal to do anything silently.

Model

Claude Haiku 4.5 for the read — one model, multimodal. Photos and lab files run in the same call as the text.

JSON

A brace-counting extractor, never a greedy regex. Every parse survives prose, code fences and stray commentary.

Em dashes

Recursively stripped from every generated string. A banned AI-writing signal across the whole platform.

One live read

Generating a CFFS or CFWS archives the prior one. reassessment_flagged is always server-set, never by the model.

Non-diagnostic

No interpretive surface names a disease, alters a lab range, or gives medical advice. A marker is a hypothesis, not a finding.

Governed, not assumed

Drift and reassessment are surfaced, not silent — the integrity of the read is monitored across the block.

The Line

What the engine will not do.

It interprets, never prescribes

Layer 1 terminates at the CFFS. Prescription is Layer 2 and is always derived from the interpretation, never the other way round.

Non-diagnostic, absolutely

No stage names a disease, alters a lab range, or gives medical advice. Markedly abnormal values are referred to a GP in neutral language.

Pattern, not event

Interpretation is pattern-based and conservative resolution always wins. One reading is a hypothesis; the arc is the evidence.

No aesthetic verdict

Photos are signal, not judgment. Words like overweight, lean, soft or athletic are banned from the read.

The machinery stays hidden

No CFFS, RPE or cortisol language ever reaches the client. The reading family translates everything into one voice.

Brand boundary held

Structured compound tracking is Arete’s lane. Body Recode captures it only as free text and never propagates compound names to client prose.