Cover illustration for Structuring movement data to isolate training recovery thresholds

What the AI found

“"Clients reporting lower-limb stiffness showed no correlation with total weekly volume, but stiffness spiked 68% when interval work was separated by under 48 hours."”

Before

Subjective fatigue logs buried in 18 client chats

After

A 12-minute Friday review guiding client load

The same system, three states — real screens, not a screenshot

1Starting
Apple Notes
  • M.T. text: 'Right hamstring tight after Tuesday track'
  • S.K. email: 'Felt flat on long run, skipped strides'
  • L.R. voice note: 'Calves aching, is 45km too much this week?'
  • Need to cross-check last 3 weeks of volume manually
2Working
Claude

Prompt

Analyse this 12-week movement ledger (attached as CSV) for 14 runners. Compare subjective stiffness entries against weekly distance, acute-to-chronic workload, and rest intervals. Surface any non-obvious correlations that predict reported soreness.

Here is the anonymised 12-week ledger of 14 runners containing volume, session cadence, and subjective stiffness reports. Audit for non-obvious correlations with recovery.

AI

Clients reporting lower-limb stiffness showed no correlation with total weekly volume (r=0.12). However, stiffness spiked 68% when interval sessions were separated by under 48 hours, regardless of total mileage.
3Implemented
Apple Health

94%

Weekly Spacing Compliance

-58%

Unscheduled Deload Requests

12 min

Friday Review Time

PractitionerCore Course in use

Structuring movement data to isolate training recovery thresholds

How an independent movement specialist turned scattered fatigue notes into a precise recovery rule using the 3-Layer Method.

An independent movement coach and running biomechanist, Northern Europe

Tools used

The real tools used here — swap any for your own equivalent. Each links to how we’d set it up.

4 min readWellness & AI editorial
1

Before anything was set up

Friday evenings were consumed by cross-referencing sixteen athletes across WhatsApp, voice notes, and haphazard training diaries. Clients frequently flagged persistent soreness or requested spontaneous rest days. The coach assumed the culprit was creeping mileage or inadequate warm-ups. Without a consolidated tracking ledger, identifying systemic programming blind spots meant wading through dozens of disjointed messages each weekend.

Apple Notes
  • M.T. text: 'Right hamstring tight after Tuesday track'
  • S.K. email: 'Felt flat on long run, skipped strides'
  • L.R. voice note: 'Calves aching, is 45km too much this week?'
  • Need to cross-check last 3 weeks of volume manually
2

Core Course, doing its job

Following the Core Course protocol, the coach built a standardised Google Sheet ledger and fed twelve weeks of anonymised athlete notes into Claude. Rather than asking vague questions, they applied the structured analysis prompt from Module 2. Within seconds, the system disproved the coach's primary assumption about mileage and isolated the exact operational flaw in their weekly schedule.

Claude

Prompt

Analyse this 12-week movement ledger (attached as CSV) for 14 runners. Compare subjective stiffness entries against weekly distance, acute-to-chronic workload, and rest intervals. Surface any non-obvious correlations that predict reported soreness.

Here is the anonymised 12-week ledger of 14 runners containing volume, session cadence, and subjective stiffness reports. Audit for non-obvious correlations with recovery.

AI

Clients reporting lower-limb stiffness showed no correlation with total weekly volume (r=0.12). However, stiffness spiked 68% when interval sessions were separated by under 48 hours, regardless of total mileage.
3

The finished system, running on its own

A single shared Google Sheet feeds a Claude workspace every Friday afternoon. The practitioner reviews a three-bullet summary rather than dozens of chat fragments. When a runner reports hamstring tightness, the ledger reveals whether recovery spacing slipped below the 48-hour threshold, removing guesswork from programming adjustments. The clients feel heard; the practitioner preserves ten hours a week previously lost to ad-hoc correspondence.

Apple Health

94%

Weekly Spacing Compliance

-58%

Unscheduled Deload Requests

12 min

Friday Review Time

12 min/wk (was 3.5 hrs)

Client audit time

94%

Recovery spacing compliance

Down 58%

Unscheduled session cancellations

ClaudeSynthesis and prompt workspace

Handles large multi-client text exports cleanly without losing nuance in client notes.

Google SheetsCentralised training ledger

Low-friction, lightweight data capture that clients can update from any mobile device.

Apple HealthObjective movement and resting metrics

Collects background cadence, steps, and resting heart rate data without active compliance burden.

These are the tools used in this story. Any can be swapped for an equivalent you already trust.

Explore the Core Course

This story runs on Core Course. The tools and prompts above are the real build — swap any tool for your own equivalent and follow the same steps.

Suggested for you

Based on what you've been reading — always learning.

See all →