App Icon Coach GPT App

About the Coach GPT

The Coach GPT App blends data-driven precision with evidence-based training principles. It integrates objective load metrics (TSS, CTL, ATL, HRV, VO₂max) with subjective markers (RPE, mood, recovery) to generate personalized training analysis.

It uses advanced frameworks like ACWR, Strain, Monotony, Durability Index, and Polarisation Index to deliver clear weekly, seasonal, and wellness reports, ensuring balance between hard and easy days.

🧭 Coach Tips — Get More From Your AI Coach

  1. Confirm your Intervals.icu connection first. Type “Connection active” before running any report.
  2. Let the coach self-audit. If totals or hours look incorrect, say “Audit and validate totals”.
  3. Tell me your age. Enables Friel-based load and recovery adjustments (defaults to 35 if not given).
  4. Log subjective data. Sleep, fatigue, mood, soreness, motivation, and hydration improve accuracy.
  5. Keep FTP and zones current. Retest FTP/LT1 roughly every 6 weeks or after 3–4 microcycles.
  6. Be specific in commands. e.g. “Run a weekly report”, “Show wellness trend”, “Audit season totals”.
  7. Check the audit flag. Reports only render when audit✅. If not, ask to re-audit.
  8. Understand data limits. Some derived metrics (e.g. age or readiness) depend on what Intervals.icu provides.

Core Features

Coach GPT Avatar

Coach Profile

This coach blends data-driven precision with evidence-based endurance frameworks, delivering actionable insights across cycling, running, triathlon, and multisport.

By combining objective metrics — TSS, CTL, ATL, HRV, VO₂max, ACWR, Monotony, Strain, Durability, and Polarisation — with subjective feedback such as RPE, mood, fatigue, and recovery, the coach ensures a precise balance between load, readiness, and adaptation.

Grounded in validated research and long-term performance modeling, this approach follows:

The coach continuously monitors ACWR, Polarisation Index, and Recovery Index to detect maladaptation early and adapt training proactively.

Whether targeting an Ironman, Gran Fondo, or Marathon, this system ensures the athlete peaks on time, achieves maximal aerobic fitness, and avoids non-functional overreaching.

Intervals.icu Dependency

The Coach GPT App is fully dependent on Intervals.icu for data. Training activities, wellness logs, and advanced load calculations are sourced directly from Intervals.icu.

For the best results, athletes should ensure their wellness markers (HRV, resting HR, sleep, mood, stress, soreness) are synchronized to Intervals.icu. This ensures the app can combine objective training load with subjective recovery data for accurate reporting. Also adding custom fields helps coaching accuracy; Garmin users can expose Vo2maxGarmin and PerformanceIndicators, also IF (Intensity Factor) is a useful metric.

Special thanks to David Tinker, the creator of Intervals.icu, for building and maintaining the platform that makes this integration possible.

📊 Sample Reports (Unified Reporting Framework v5.1)

Anonymised examples for a cycling-focused athlete.

Weekly Report 
📊 Weekly Report — Unified Reporting Framework v5.1






Athlete[Anon]


DisciplineCycling


Window2025-10-20 → 2025-10-26


Audit✅ Final







🔹 Key Stats




Volume10 h 46 m


Load (TSS)579


CTL / ATL92 / 81


Form+11


ACWR1.01


Monotony3.6 ⚠


Strain579





🔸 Training Quality




Z1–Z2 Distribution70 % ✅


Z3–Z5 Time30 % ⚠


FatOx Index0.80 ✅


HR–Power Decoupling4.9 % ✅





🔹 Efficiency & Adaptation




Benchmark IndexStable (+0.4 %)


Specificity Index0.74 → 0.77


Durability MarkerHigh





🔸 Recovery & Wellness




HRV46 ms


RestHR44 bpm


Sleep7.6 h avg


Fatigue / Stress / SorenessLow





📈 Performance Insights (Automated)


    

  • ✅ Seiler alignment – Polarisation 0.72 (Optimal 80/20 balance)
    • 

  • ✅ San Millán – FatOx ≥ 0.8 and Dec ≤ 5 %
    • 

  • ✅ Friel – Balanced ACWR (1.01)
    • 

  • ⚠ Foster – Monotony > 3.0 → Slight uniformity risk
    • 




🧭 Actions (Max 5)


    

  1. Maintain ≥ 70 % Z1–Z2 for aerobic durability (Seiler).
    2. 

  2. Keep FatOx ≥ 0.8 and Decoupling ≤ 5 % (San Millán).
    3. 

  3. Schedule recovery microcycle next week (Friel).
    4. 

  4. Retest FTP / LT1 in 6 weeks (benchmark update).
    5. 

  5. Validate FatMax calibration ± 5 % via field data.
    6.
Season Report 
📆 Season Report — Unified Reporting Framework v5.1




Athlete[Anon]


Window2025-09-15 → 2025-10-26


PhasesBuild → Overload → Deload


Audit✅ Final





🔹 Key Stats




Total Volume61.3 h


Total Load (TSS)3330


Average ACWR1.08


CTL Trend+12 ↑


Recovery Index0.63


Monotony2.8 ✅


Strain930 ✅





🔸 Training Quality




Polarisation Index0.74 ✅


FatOx Index (Avg)0.81 ✅


Endurance DurabilityHigh





🔹 Efficiency & Adaptation




Benchmark Index+2.1 %


Specificity Index0.75 → 0.79


Durability MarkerImproved





🧱 Phase Summary




PhaseSpanVolume (h)Load (TSS)Trend


Build2 wks18.4940↑


Overload3 wks31.71770↑↑


Deload1 wk11.2620↓





🔸 Recovery & Wellness




HRV Trend-6 % during Overload ⚠


RestHRStable (44 bpm)


Sleep Average7.4 h


Stress / FatigueNormalised after Deload





📈 Performance Insights


    

  • ✅ ACWR 0.9–1.2 — adaptive zone
    • 

  • ✅ CTL +12 — progressive load gain
    • 

  • ⚠ HRV suppression during Overload phase
    • 

  • ✅ Subjective stress ↓ after Deload
    • 




🧭 Actions


    

  1. Maintain 3 : 1 build/deload cycle (Friel).
    2. 

  2. Extend base endurance before next intensity phase.
    3. 

  3. Ensure ≥ 7.5 h sleep for recovery quality.
    4. 

  4. Retest FTP and VO₂ metrics post-block.
    5. 

  5. Monitor HRV and mood for readiness confirmation.
    6.
Wellness Trend 
💠 Wellness Trend — Unified Reporting Framework v5.1




Athlete[Anon]


Window2025-10-13 → 2025-10-26


Audit✅ Final





🔹 Key Stats




HRV Avg46 ms


RestHR44 bpm


Sleep Duration7.6 h


Sleep Quality84 %


Stress / Fatigue / SorenessLow (2 / 5)


MoodGood ↑





🔸 Recovery Summary




Recovery Index0.68 ✅


Readiness Score0.72 ✅


HydrationAdequate (~2.3 L/day)


Sleep ConsistencyHigh





📈 Performance Insights


    

  • ✅ HRV +2 % vs previous fortnight
    • 

  • ✅ RestHR −1 bpm improvement
    • 

  • ✅ Fatigue consistent ≤ 2/5
    • 

  • ⚠ Stress spike mid-block (Transient)
    • 




🧭 Actions


    

  1. Maintain sleep ≥ 7.5 h /night.
    2. 

  2. Prioritise hydration during load weeks.
    3. 

  3. If HRV ↓ > 10 %, reduce load ≈ 15 %.
    4. 

  4. Retest readiness after Deload.
    5. 

  5. Keep subjective logs daily.
    6.
Executive Summary 
🧩 Executive Summary — Unified Reporting Framework v5.1




Athlete[Anon]


ScopeLoad & Recovery Overview


PeriodLast 42 days


Audit✅ Final





🔹 Key Stats




Volume61.3 h


Load (TSS)3330


CTL / ATL90 / 84


Form+6


ACWR1.08 ✅


Monotony2.8 ✅


Strain930 ✅


Polarisation0.74 ✅





🔸 Recovery & Wellness




HRV46 ms ✅


RestHR44 bpm ✅


Recovery Index0.68 ✅


Readiness0.72 ✅





📈 Performance Insights


    

  • ✅ Balanced ACWR (0.8–1.3)
    • 

  • ✅ Positive HRV stability
    • 

  • ⚠ Monotony 2.8 → uniformity watch
    • 




🧭 Actions


    

  1. Continue 3:1 build/deload rhythm.
    2. 

  2. Keep Z1–Z2 ≥ 70 % volume.
    3. 

  3. Maintain ≥ 2 nights recovery after high load.
    4. 

  4. Monitor HRV daily for fatigue trend.
    5. 

  5. Plan next benchmark retest in week 7.
    6.

Get the App

In the GPT Store, search for: "Intervals icu training coach"

Contact

For integration, customization, or coaching inquiries, connect via GitHub or Intervals.icu

github.com/revo2wheels