Inside the Engine

The read.
Where the engine stops.

The homepage shows the engine as a diagram. This is the version with the working parts showing. Structured answers go in, a single cautious interpretation comes out as the CFFS, and it is re-read every week as the CFWS. It prescribes nothing at any point. Where it stops is set out at the bottom of this page, and it is the most important thing on it.
One interpretive core8 signal domains5 pillars3 body statesIt ends at the read
By the Numbers

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

271

intake questions

the read instrument · 8 domains

5

interpretive pillars

FMM primary + PTS/HABNS/RRS/BIRS

4 + 14

Fat Map

patterns + extended sub-zones

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 on its own. Whatever gets built on top of a read is a much larger piece of software than the read itself, and that is the point: the hard, slow, defensible part is small.

The Pipeline

Four stages, then it hands over.

The questions feed the CFFS. The CFFS is re-read every week as the CFWS. A monitor with no model in it watches for drift and says when the read has gone stale. That is the entire engine. It hands the read to whoever is going to act on it and takes no part in what they do next.
00The Read InstrumentInputs
01CFFS, the core interpretationwhere it ends up
02CFWS, the weekly re-readkept current
03Signal monitoringself-governance
00

What goes in

Four inputs. Almost all of it is plain capture with no model involved; the only model at this stage transcribes blood panels. The forms belong to whoever is collecting the data. The question set and what each answer means belong to the engine.

Foundational Intake

deterministic

8 domains · 271 questions

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

Height, bodyweight, waist, hips, chest, and three photos (front / side / back). The photos feed the engine’s vision read; bodyweight floors the nutrition protein anchor, and height is what makes an energy estimate possible at all.

→ 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 Sonnet 5

optional · multimodal

Client uploads a lab PDF or photo. The engine transcribes every marker against the range the lab itself printed. Transcription, not diagnosis. Only a panel the coach has approved reaches the interpretation.

→ blood_panels.*

The read is triggered by hand, and only once both the questions and the baseline photos are in, because the Fat Map needs the photos. The engine starts at the intake. Anything earlier, including any short quiz used to bring people in, sits outside it and never feeds it.
01

The CFFS

Coach-Facing Foundational Synthesis, which is the written read. This is the heart of it, and it is where the interpreting stops.

Body Recode™ Interpretation Engine

Claude Sonnet 5 · multimodal

Reads

  • Eight intake domains (pre-summarised: average, elevated ≥3/4, low ≤1/4)
  • Baseline measurements → derived ratios (BMI, waist-to-height) with a plausibility check
  • Baseline photos → vision read (Spatial Patterning)
  • Any prior pattern read carried in from the funnel (not binding)
  • clients.medications (free text)
  • Dietary context (hard constraints)
  • Approved blood markers (the coach gate)

Does

Condenses the scored sections, reads the photos as one more signal rather than as evidence on their own, and resolves the whole picture through the Fat Map's four location-plus-signal patterns. Where two reads are possible, the cautious one wins every time. It names the body state, rates four readiness signals, and prescribes nothing.

Produces

  • body_state_classification
  • pattern_classification (one of four, or no clear pattern) + confidence
  • pattern_rationale + competing read
  • 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 by the server, never by the model, because it is a fact about time rather than a judgement.

02

The CFWS

Coach-Facing Weekly Synthesis, the weekly re-read. Still interpretation, still written for whoever acts on it, still prescribes nothing.

Reads

The week's check-in, measured against the original read rather than against nothing. The form that collects it sits outside the engine. The engine reads the answers the same way it reads the intake.

Rule

Readiness moves one notch at a time from where the original read put it. Red is the floor. It only jumps two notches on a named safety event, and no single answer on one form can drag it down by itself.

Produces

A weekly write-up plus the four readiness colours, stored in cfws.*. Weeks of those in sequence are what the end-of-block review reads.

Claude Sonnet 5
03

Signal monitoring

How the engine polices itself. It decides when a read has drifted far enough to need doing again. No model involved, and it 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.

Effort creep

Logged effort running a full point above what was prescribed counts as creep. Two points, or any set at 9.5 or above, counts as severe. The logging happens outside the engine. The monitor reads it as one more sign of drift.

This is the last thing the engine does. The monitor's recommendation loops back round to a fresh read. It never reaches forward into what anyone does about it.
The Handoff

Where the engine stops, and what happens next.

The engine finishes at the read and hands it over. What gets built on top of it, the training, the food, the workload, the clinical decisions, is not the engine's business and is not part of what it does. That is deliberate, and it is the reason the read can be handed to anyone.
The traffic runs one way. A plan that wants more load, or a person who wants a faster result, never changes the read. If the read says the body cannot take what somebody wants to do with it, the read stands and the plan moves. That asymmetry is the whole agreement between what the engine says and what anyone does about it.
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 patterns, fourteen 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, and location alone does not separate the four, because three of the four drivers push storage centrally, so the pattern says where to look and the accompanying signal decides. The extended sub-zone then says how. Fat-storage conclusions are valid only on the long arc, which means 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.

Cortisol · Stress-Stored

Front of the midsection

The middle fills while the limbs stay lean

Extended zones

  • ·Lower Abdominal Compression
  • ·Peripheral Sparing

Insulin · Insulin-Drift

Mid-back, lower back, flanks

Afternoon crash, evening cravings. Front spared

Extended zones

  • ·Subscapular Fullness
  • ·Flank Carriage
  • ·Deep Abdominal Fullness

Oestrogen · Estrogen-Shift

Hips and thighs, then central

Two phases. Direction of travel is the read

Extended zones

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

Testosterone · Androgen-Decline

Not one location

Central fat rising while muscle and drive fall

Extended zones

  • ·Central Accumulation
  • ·Peripheral Softening
  • ·Chest Fullness
The Machinery

What holds it together.

The same 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

Tiered by consequence, never chosen at the call site. Claude Sonnet 5 for anything whose output reaches a client's body, which is the read and the lab extraction. Claude Haiku 4.5 for drafting, routing and extraction that is cheap to retry. One multimodal call: photos and lab files run alongside 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, never silent. The read is watched across the whole block.

The Line

What the engine will not do.

It reads, it never prescribes

The engine finishes at the read. Whatever gets prescribed is decided by a person afterwards, built from the read and 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 read 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.

Independent Review

Built to be reviewed.

The Body Recode™ doctrine is being submitted for independent review by a small advisory group of practising clinicians and high-performance specialists. The full doctrine is written down, it names the claims it has withdrawn, and it is being put in front of people qualified to challenge it.

Sports medicine physician

European-trained

Reviewing

how the system reads hormonal and regulatory state, and where it should defer to clinical care.

Elite-sport physiotherapist

Works with professional athletes

Reviewing

how the system reads load, recovery and readiness.

High-performance coach

Competitive physique athlete

Reviewing

the training, nutrition and supplementation logic.

Reviews are being sought now. Names and credentials will be published only where an advisor has completed a review and agreed to be named.