Montis.icu
Intelligent endurance coaching that turns your training data into clear decisions.
montis.icu → “of the mountain (latin)” + “I see you”
A system that watches over endurance and performance over the long term.
Built on validated Intervals.icu data, Montis.icu Coach transforms 42 structured physiological markers into transparent performance intelligence — across load regulation, recovery, metabolic efficiency, durability, and neural density.
It doesn’t guess. It doesn’t improvise. It applies established endurance science — Seiler, Banister, Skiba, San Millán and others — inside a unified inference engine.
And it closes the loop. Forecasted microcycles are written directly back into the athlete’s calendar and executed seamlessly on Zwift, Garmin, and connected platforms.
More than training blocks. It protects durability. Manages stress intelligently. Preserves metabolic health. Extends high performance across decades — not seasons.
Endurance athletes generate vast volumes of structured training data — power files, HRV, sleep metrics, training stress, interval analytics, subjective logs — yet most platforms provide dashboards rather than decisions.
Coaching remains manually interpretive. Generative AI tools are conversational — but probabilistic, non-deterministic, and physiologically ungoverned.
The result: data-rich athletes without a unified, explainable performance intelligence system.
Montis.icu Coach V5 is a physiology governed endurance performance intelligence engine built on the Unified Reporting Framework (URF v5.1).
It converts validated Intervals.icu data into a structured, multi-layer inference model integrating 42 coaching markers across load regulation, autonomic recovery, metabolic efficiency, durability, and neural density.
Every output is governed by transparent, physiology-grounded logic — not language-model improvisation.
Training load creates stress. Physiology measures recovery. Performance Intelligence models capability. ESPE reveals adaptation. ADE determines how training should change next.
Coach V5 is not a conversational wrapper around endurance data. It is a Physiology-Governed intelligence infrastructure layer.
Today, it augments individual athletes and coaches. Architecturally, it is built to scale into team environments, coach networks, and enterprise performance systems — model-agnostic, headless, and future-ready.
Natural language becomes the interface. Physiology remains the authority.
Transparent. Physiology-grounded. Built for real training decisions. Built to convert endurance data into structured performance decisions.
“Game changer. What a fantastic add-on.” — Jeff
“I use it almost every day to understand what to improve in my races and workouts.” — Marco S.
“It's producing really good insights and it's actually fun to use.” — Marius
“Very cool and awesome potential. Enjoying it so far.” — G-Mack
“This app is great. Using it with Concept2 erg data has given me good ideas to think through, plus a modified training plan to help meet my goal.” — Richard
Using these foundations, the coach continuously monitors ACWR, Polarisation Index, and Load Variability Index to identify maladaptation early and apply proactive recovery or load modulation.
Whether you’re targeting a Gran Fondo, Ironman, or Marathon, this system ensures progressive overload, sustainable adaptation, and peak timing — maximizing aerobic performance while minimizing injury and non-functional overreaching.
The latest version introduces Performance Intelligence — a structural modeling layer that analyzes how your system handles intensity, durability, and neural strain.
This layer does not replace traditional metrics like TSS or CTL. It evaluates how your body behaves under load.
Why this matters: Future training guidance is no longer shaped only by volume targets — but by repeatability stability, durability trends, and intensity clustering patterns.
The Energy System Progression Engine (ESPE) extends Performance Intelligence by analysing how your power-duration curve evolves over time.
While Tier-3 modelling explains how your system behaves under stress (WDRM, ISDM, NDLI), ESPE evaluates how your physiological capacity itself is changing.
It compares your recent power curve against a previous training window and quantifies progression across key energy system anchors.
By comparing these anchors across training windows, ESPE reveals which energy systems are improving, stabilising, or regressing.
Energy System Progression Neuromuscular (5s) → Stable Anaerobic (1m) → Slight Decline VO₂max (5m) → Improving Threshold (20m) → Improving Durability (60m) → Strong Gain
This pattern often reflects an aerobic-focused training block, where endurance capacity rises while short explosive power temporarily declines.
Most platforms show a power curve snapshot. ESPE instead tracks the direction of physiological adaptation.
This makes ESPE a powerful diagnostic layer that helps explain why performance trends are occurring and guides future training decisions.
💡 Tip: Keep FTP updated and log sleep/mood in Intervals.icu for higher signal accuracy.
Have your own OpenAI, Anthropic (Claude), or Gemini API key? You can run reports directly through your own AI model using the LLM Interface App.
Best for advanced users who want full control over model choice, cost, or output style, but remember you don't get the advantage of natural chat response, its pure input and output. However, its a useful demonstration to illustrate we can connect to any LLM of choice.
IMPORTANT NOTE: Please be aware that because of STRAVA API policy intervals.icu cannot share any STRAVA sourced data with third parties. This is otherwise fine for Garmin, Wahoo, Zwift etc, and FIT file uploads to Intevals.icu - please connect these to your intervals.icu profile. After you have connected a proper source import all your activities from Strava, this is not subject to API terms! see Import all Your data from Strava
Reports are generated automatically using the Unified Reporting Framework (URF v5.1). Each uses canonical Intervals.icu data and applies the Railway Engine for validation and consistency. These outputs ensure reproducible metrics, validated fatigue indicators, and synchronized wellness alignment.
Below are the available report types — click to expand. Scroll further to view anonymised sample reports illustrating full URF output.
Analyzes your last 7 days — load, intensity, and recovery alignment. Includes: ACWR, FatigueTrend, CTL / ATL / TSB, Polarisation, and metabolic drift indicators.
Athlete: Sample Athlete
Period: 2026-02-05 → 2026-02-11
Framework: Unified Reporting Framework v5.1
Scope: Weekly tactical control
Timezone: Europe/Zurich
14.24 h
652 TSS
343.3 km
ACWR indicates controlled weekly load relative to chronic baseline.
Monotony shows healthy variation despite clustered intensity.
FatigueTrend confirms short-term fatigue accumulation.
Power-based polarisation reflects substantial Z2 dominance.
Combined index sits in pyramidal range across sports.
ZQI indicates limited true high-intensity exposure despite heavy load.
Metabolic markers show stable aerobic efficiency.
Zone calibration is physiologically aligned and stable.
Z2 work above 225 W would exceed inferred LT1 boundary.
Single deep depletion event observed. Anaerobic load present but not excessive.
Cardiovascular durability stable, with fatigue interaction visible.
High neuromuscular + metabolic strain overlap observed.
Z1 ██████████████████████████ 54.6% Z2 ██████████ 21.7% Z3 █████ 10.9% Z4 ██ 4.8% Z5 █ 2.1% Z6 ▏1.3% Z7 ▏0.2% SS ██ 4.5%
Clear aerobic bias overall.
Z2 dominance explains low power polarisation ratio.
Thu Fri Sat Sun Mon Tue Wed ▃ ▁ █ █ ▃ ▃ ▃ 62 16 177 172 77 72 76 ↑ ↑ ↑ ↑ ↑ ↑ ↑
Load peaked on weekend (Sat–Sun). ATL > CTL across window.
Anaerobic Timeline: Thu ▂ Fri ▇ Sat ▇ Sun ▇ Mon ▇ Tue ▇
Clustered weekend high-depletion pattern confirmed.
| Date | Workout | Planned TSS |
|---|---|---|
| Feb 12 | Recovery Ride | 34 |
| Feb 13 | VO₂ Controlled | 63 |
| Feb 14 | Long Endurance | 126 |
Peak load scheduled for long aerobic session; intensity moderated post-cluster week.
Low-priority transition phase.
Maintain light aerobic structure.
Avoid unnecessary additional intensity.
Closing Note:
Load was productive with clear intensity clustering and accumulating short-term fatigue.
Recovery trajectory is positive and structure supports transition toward freshness.
Summarizes the last 42 days of physiological and lifestyle markers: Recovery Index, HRV, Sleep Quality, Stress Tolerance, and Monotony.
Status: Clear recovery state — no items require immediate attention.
| Athlete | Sample Athlete |
| Window | 2026-01-04 → 2026-02-15 (42 days) |
| Scope | Physiological and subjective recovery indicators |
| Framework | Unified Reporting Framework v5.1 |
| Timezone | Europe/Zurich |
Acute load is moderately elevated relative to chronic fitness. TSB at -5 reflects manageable fatigue within productive range. This represents controlled training stress rather than overload.
HRV demonstrates normal oscillation around baseline with transient dips corresponding to higher ATL periods. No sustained suppression cluster is present. Autonomic response remains proportionate to load.
Resting heart rate remains tightly anchored to baseline with no progressive drift. Sleep distribution is stable with isolated low nights but no multi-day suppression pattern. Recovery capacity appears intact.
No decline pattern detected. Cardiorespiratory performance marker remains stable across the monitoring window.
Current physiology reflects controlled stress with proportional recovery. Oscillation patterns remain normal and within adaptive range.
State: Clear
Message: No items require immediate attention at this time.
No critical flags.
No watch-list items.
No intervention signals.
Closing Note:
Your current profile reflects stable adaptation under moderate load.
HRV, resting HR, and CTL/ATL balance indicate effective stress tolerance
without accumulating systemic strain. Maintaining sleep consistency and
avoiding abrupt load spikes should preserve this stable recovery state.
Evaluates your 90-day training block: CTL growth, intensity distribution, long-term fatigue adaptation, and aerobic efficiency.
Status: Productive block with repeated overreach phases and controlled recovery transitions.
| Athlete | Sample Athlete |
| Period | 2025-11-15 → 2026-02-11 |
| Scope | Medium-term fitness, fatigue and progression trends |
| Framework | Unified Reporting Framework v5.1 |
| Timezone | Europe/Zurich |
Total: 149.8 h
Total: 6,436 TSS
Total: 3,272.3 km
| ACWR | 1.00 🟢 (Productive) |
| Monotony | 1.69 🟢 (Optimal) |
| Strain | 157.4 🟢 (Controlled) |
| FatigueTrend (90d) | Accumulating 🔴 |
Load regulation has remained within productive bounds. Fatigue accumulation is present across the 90-day window but remains structured rather than chaotic.
| Polarisation (Power Ratio) | 0.57 🔴 (Z2-dominant) |
| Polarisation Index (Combined) | 0.73 🟠 (Pyramidal) |
Season structure shows consistent aerobic dominance with moderate pyramidal layering. Power ratio <0.7 confirms sustained Z2 emphasis.
| Mean Lactate | 1.92 mmol/L |
| LT1 (Inferred) | 210 W |
| Z2 Window | 210–225 W |
| Correlation (r) | 0.99 (High confidence) |
Lactate-power relationship remains stable across the season. No metabolic drift detected.
| Efficiency Factor | 1.90 |
| Fatigue Resistance | 0.95 |
| Endurance Decay | 0.02 |
| Z2 Stability | 0.04 |
| Aerobic Decay | 0.02 |
Aerobic durability preserved. Minimal decay across the block.
| Load Trend | +5.94 |
| Fitness Trend | -1.16 |
| Fatigue Trend (recent) | -0.04 |
Load increased modestly. Fitness plateau suggests stimulus saturation between overload blocks.
| Mean Depletion | 0.24 🟢 |
| High Depletion Sessions | 8 🟠 |
| Total Joules > FTP | 1,109,246 J |
| Mean Decoupling | 1.78% 🟢 |
| High Drift Sessions | 26 🔴 |
| High-Intensity Sessions | 24 🟢 |
| Mean IF (90d) | 0.74 |
| Mean Training Load | 51.9 🟢 |
Baseline durability is strong, but frequent drift episodes suggest cumulative fatigue exposure during longer efforts.
| Max Depletion | 0.75 |
| High Drift Sessions | 3 |
| High Intensity Days | 4 |
| Phase | Days | TSS | Hours | Descriptor |
|---|---|---|---|---|
| Base | 7 | 206 | 3.8 | Aerobic emphasis |
| Overreached | 14 | 1146 | 22.7 | High fatigue block |
| Recovery | 7 | 200 | 5.1 | Regeneration |
| Build | 7 | 414 | 9.3 | Progressive overload |
| Extended Overreach | 21 | 1640 | 43.8 | Sustained overload |
| Mean IF | 0.74 |
| Mean Decoupling | 1.78% |
| Mean W′ | 19,735 J |
| Mean Joules > FTP / Session | 14,790 J |
| Projected CTL | 69.6 |
| Projected ATL | 55.4 |
| Projected TSB | +14.2 |
| Fatigue Class | Transition |
Transition / Recovery Phase. Maintain light aerobic activity and avoid stacking supra-threshold work during freshness window.
The 90-day block shows deliberate overload cycling layered on a stable aerobic foundation. Chronic durability is strong; recent fatigue is acute rather than structural.
Status: Optimal — High-volume year with structured overload and controlled transitions.
| Athlete | Sample Athlete |
| Period | 2025-01-01 → 2025-12-31 |
| Scope | High-level overview of current training state |
| Framework | Unified Reporting Framework v5.1 |
| Timezone | Europe/Zurich |
Total: 813.6 h
Sustained high annual volume distributed across multiple macro-cycles. Load was consistent with long-term endurance development.
Total: 36,003 TSS
High cumulative stress with repeated overload phases. Distribution reflects deliberate stress–recovery cycling rather than random accumulation.
Total: 17,332.4 km
Large aerobic base volume across the year. Distance aligns proportionally with total hours and TSS.
Year closed in a balanced load state (CTL ≈ ATL). Positive HRV trend into year-end indicates recovery consolidation. No chronic suppression visible in available HRV series.
You finished the year neither fatigued nor detrained. Autonomic signals suggest stable system health at transition.
| Phase | Start | End | Days | TSS | Hours | Descriptor |
|---|---|---|---|---|---|---|
| Base | 2024-12-30 | 2025-01-05 | 7 | 322 | 12.1 | 🧱 Aerobic emphasis |
| Overreached | 2025-01-06 | 2025-02-02 | 28 | 2516 | 74.9 | High fatigue block |
| Continuous Load | 2025-02-03 | 2025-02-09 | 7 | 521 | 12.6 | Steady load |
| Overreached | 2025-02-10 | 2025-02-23 | 14 | 2532 | 48.0 | High fatigue block |
| Taper | 2025-02-24 | 2025-03-16 | 21 | 1737 | 32.6 | 📉 ATL reduction |
| Build | 2025-04-14 | 2025-04-20 | 7 | 843 | 15.2 | Progressive overload |
| Base | 2025-06-30 | 2025-07-13 | 14 | 1574 | 39.4 | Aerobic volume |
| Taper | 2025-08-11 | 2025-09-14 | 35 | 2971 | 79.4 | Extended freshness phase |
| Recovery | 2025-12-29 | 2026-01-04 | 7 | 215 | 6.8 | Year-end reset |
The year shows frequent short overreach blocks, systematic taper/reset phases, and stable continuous load segments.
This resembles aggressive block periodisation with repeated stress peaks followed by controlled unloading.
Intensity was consistently moderate (IF ~0.70). Durability remained stable (decoupling ~3%). High supra-threshold exposure occurred frequently but within repeatable tolerance.
You trained hard, often, and repeatedly near high strain — but durability metrics held.
Closing Note:
2025 reflects a high-volume, high-structure year with repeated overload
and effective recovery cycling. System health at year end is balanced,
HRV trend is positive, and no chronic instability markers are present.
A structural modeling layer that analyzes how your system handles intensity, durability, and neural strain. After a weekly or season report ask to show your Performance Intelligence. This will also provide a solid foundation for creating future workout plans when asked.
Status: Recovery phase active — Productive load balance with strong chronic durability and controlled acute stress.
| Metric | Value | State |
|---|---|---|
| Mean depletion % | 0.24 | 🟢 Green |
| High depletion sessions | 8 | 🟠 Moderate |
| Max depletion % | 1.14 | ℹ Informational |
| Total Joules > FTP | 1,109,246 J | ℹ Informational |
Chronic anaerobic exposure is present but controlled. Eight high-depletion sessions over 90 days indicate periodic supra-threshold stimulus without excessive clustering. Mean depletion remains within adaptive green range (0.15–0.35).
| Metric | Value | State |
|---|---|---|
| Mean decoupling | 1.78 | 🟢 Stable |
| High drift sessions | 26 | 🔴 Elevated exposure |
| Max decoupling | 22.82 | ℹ Informational |
Mean decoupling in the green band confirms strong aerobic durability. High drift session count (26) reflects repeated cardiovascular strain exposures across the macro block. Despite that exposure, average stability remains preserved.
| Metric | Value | State |
|---|---|---|
| High-intensity sessions | 24 | 🟢 Adaptive range |
| Mean IF | 0.74 | ℹ Informational |
| Mean training load | 51.9 | 🟢 Optimal |
High-intensity session count is within adaptive bandwidth (8–25). Mean training load sits comfortably in optimal range (40–70). Chronic intensity density appears sustainable relative to load base.
| Metric | Value | State |
|---|---|---|
| Mean depletion % | 0.31 | 🟢 Green |
| High depletion sessions | 1 | 🟢 Controlled |
| Max depletion % | 0.75 | ℹ Informational |
| Total Joules > FTP | 152,992 J | ℹ Informational |
Recent anaerobic exposure is moderate and well spaced. Single high-depletion session suggests controlled intensity application.
| Metric | Value | State |
|---|---|---|
| Mean decoupling | 3.01 | 🟢 Stable |
| High drift sessions | 3 | 🟠 Moderate |
| Long sessions | 1 | ℹ Informational |
Short-term decoupling remains inside green band (0–5). Three higher-drift sessions suggest mild durability strain but not instability.
| Metric | Value | State |
|---|---|---|
| High-intensity days | 4 | 🟢 Balanced |
| Rolling Joules > FTP | 152,992 J | 🟢 Green |
| Mean IF | 0.69 | ℹ Informational |
Intensity clustering remains within green range. Mean IF indicates moderate load relative to chronic capacity.
Your chronic system shows high tolerance with preserved aerobic stability. The acute overlay does not exceed chronic capacity — stress is proportionate.
Closing Note:
Performance intelligence indicates strong chronic durability with controlled acute stress exposure.
Current recovery phase supports consolidation before any renewed build stimulus.
Status: Productive load with emerging durability strain and clustered neural density — consolidation block with controlled quality exposure.
| CTL | ~76 (stable chronic load) |
| TSB | -5 (functional fatigue) |
| HRV Deviation | -7.3% (mild autonomic suppression) |
| FatigueTrend | Positive, green classification |
| WDRM (Anaerobic Repeatability) | Mean depletion 36%, no repeated deep collapse |
| ISDM (Durability) | Mean decoupling 6.8%, multiple high-drift sessions |
| NDLI (Neural Density) | High-intensity days clustered; elevated supra-threshold joules |
| Zone Profile | Z2 dominant with low ZQI |
Cycling: 60 min (~35 TSS)
Mobility: 20 min
Weights: Neural controlled session
Cycling: 75 min (~85 TSS)
Cycling: 2h15 (~110 TSS)
Cycling: 60 min (~65 TSS)
Mobility only
Cycling: 1h50 (~85 TSS)
Cycling: 45 min easy
Cycling: 90 min (~90 TSS)
Closing Note:
This block directly reflects your WDRM stability, ISDM durability drift,
and NDLI clustering pattern. It consolidates aerobic durability,
protects autonomic signals, and raises quality exposure without repeating
the previous density signature.
The Energy System Progression Engine (ESPE) analyzes how your power-duration curve evolves across training blocks. It compares two historical windows and identifies which energy systems are progressing, stabilizing, or declining.
| Curve Source | FFT power-duration curves |
| Model Quality | Good (R² = 0.84) |
This section shows the full Energy System Progression Engine (ESPE) output describing how each physiological system has changed over the last training block.
| Duration | Change |
|---|---|
| 5 s | −19.4 % |
| 1 min | −4.7 % |
| 5 min | −2.0 % |
| 20 min | +2.0 % |
| 60 min | +5.1 % |
Interpretation
Short explosive power (5s) has declined noticeably.
VO₂ power (≈5 min) is slightly reduced.
Sustained aerobic power (20–60 min) has improved significantly.
This is a classic endurance adaptation profile.
| Metric | Value | Meaning |
|---|---|---|
| Vertical Shift | +0.11 | Slight overall power increase |
| Rotation Index | −6.88 | Curve rotated toward endurance |
| Dominant Shift | Aerobic rotation | Power gains favor long durations |
The curve rotation indicates the training block primarily improved durability and sustained aerobic power rather than explosive output.
| Energy System | Status | Trend Meaning |
|---|---|---|
| Anaerobic | Decline | Less explosive / sprint work |
| VO₂ System | Decline | Reduced high-intensity stimulus |
| Threshold | Moderate Gain | FTP-range development |
| Aerobic Durability | Strong Gain | Improved fatigue resistance |
Adaptation State: Aerobic consolidation
Adaptation Bias: Threshold dominant
| Metric | Value | Interpretation |
|---|---|---|
| Glycolytic Bias Ratio | 1.52 | Moderate anaerobic bias relative to threshold |
| Aerobic Durability Ratio | 0.82 | Good endurance durability |
| Durability Gradient | 0.94 | Sustained power stable over long durations |
| System Balance Score | 0.84 | Balanced multi-system development |
| VO₂ Reserve Ratio | 1.20 | Healthy headroom above CP |
| PDR (5-min reserve) | 58 W | VO₂ capacity above threshold |
| Metric | Value |
|---|---|
| CP | 294 W |
| FTP | 300 W |
| W′ | 15.6 kJ |
| Pmax | 689 W |
Critical Power and FTP remain closely aligned.
W′ reserve remains healthy for repeated supra-threshold work.
The current training phase shows a clear endurance-focused adaptation pattern:
This profile typically appears during aerobic consolidation blocks, where training prioritizes long steady endurance, threshold work, and fatigue resistance.
Bottom line:
Your physiology is currently shifting toward an
endurance-specialist power curve,
with improved fatigue resistance and long-duration output.
Your reports are deterministic. But you can interrogate the full performance context. Below are powerful prompts athletes and coaches use to extract deeper value from Weekly, Seasonal, Wellness, and Performance Intelligence reports.
Forces comparison of WDRM, ISDM, NDLI to identify whether fatigue is metabolic, structural, or intensity-density driven.
Evaluates ACWR, FatigueTrend, Monotony, Strain, HRV deviation to distinguish adaptive stress from overload risk.
Interrogates NDLI and supra-threshold joule stacking to detect hidden density accumulation.
Overlays 7-day signals against the 90-day structural state (WDRM, ISDM, NDLI) while referencing ESPE energy-system progression to determine whether current stress aligns with long-term adaptation capacity.
Combines ISDM durability metrics (decoupling trends, high-drift frequency, Z2 stability and long-session behaviour) with ESPE endurance and threshold progression derived from rolling power-curve comparisons.
Uses WDRM anaerobic stress signals (W′ depletion depth, high-depletion sessions, rolling joules > FTP) alongside ESPE VO₂ and anaerobic progression to differentiate productive adaptation from simple intensity stacking.
Compares rolling power curves (current vs previous macro block) across neuromuscular, anaerobic, VO₂, threshold and endurance durations to detect real performance progression.
Uses ESPE delta analysis across 5s, 30s, 1m, 5m, 20m and 60m anchor durations to identify whether current training stimulus is producing aerobic, threshold, VO₂ or anaerobic adaptation bias.
Evaluates power-curve progression across rolling windows rather than individual peak efforts to separate true physiological adaptation from short-term freshness effects.
Detects plateau conditions when rolling power-curve deltas stabilize across macro blocks, signalling the need for a change in stimulus or training structure.
Converts structural intelligence into forward microcycle planning — balancing load, quality exposure, and autonomic protection.
Uses CTL/ATL balance, fatigue class, and structural markers to classify the appropriate training phase.
Evaluates FatOx, MES, Efficiency Drift, Polarisation, ZQI to identify metabolic leverage points.
Generates a structured microcycle written back to your Intervals.icu calendar — aligned with WDRM, ISDM, NDLI, load balance, and recovery signals.
Compares multi-block ISDM trends, decoupling suppression, and high-drift frequency to determine whether structural endurance capacity is rising — or just maintaining under higher load.
Evaluates WDRM depletion depth, repeatability stability, and supra-threshold joule density across chronic and acute windows to detect real anaerobic adaptation.
Cross-checks NDLI clustering, IF density, and CTL baseline to identify when neural stress outpaces durability conditioning.
Compares Fitness Trend vs Load Trend alongside Tier-3 markers to detect diminishing return phases before performance plateaus.
Simulates forward load exposure using current WDRM, ISDM, and NDLI state to identify the safe boundary for progression versus overload.
The Coach operates as a multi-framework inference engine. Each physiological model contributes structured signals that are blended, weighted, and resolved deterministically within URF.
Tier-3 structural markers (WDRM, ISDM, NDLI) are derived extensions of established endurance physiology frameworks — including Critical Power, cardiovascular drift research, and CNS fatigue models — applied to multi-session load interpretation.
| Model Reference | Framework Link | Metric Source | Output Type | Coaching Role |
|---|---|---|---|---|
| Seiler Polarisation | Intensity Framework | Z1–Z3% | Polarisation Ratio | Validates 80/20 intensity distribution |
| Banister Fitness–Fatigue | Load Adaptation | ATL, CTL, TSB | Training Load Model | Models fitness–fatigue impulse response and adaptation balance |
| Coggan Power–Duration | Efficiency Framework | FTP, Power Curve | Efficiency Factor | Tracks metabolic endurance and fatigue resistance |
| Foster Overtraining | Recovery Alignment | Strain, Monotony | Overtraining Index | Quantifies cumulative stress risk using monotony × strain dynamics |
| San Millán Metabolic | Metabolic Efficiency | FatOx Index | Mito Efficiency | Evaluates fat utilization and Zone 2 economy |
| Noakes Central Governor | Readiness Forecast | HRV × RPE | CNS Fatigue Index | Detects neural fatigue and motivational readiness |
| Skiba Critical Power | Performance Integration | CP, W′ | Fatigue Decay Curve | Predicts endurance performance limits |
| Mujika Tapering | Periodisation | Load % Reduction | Taper Efficiency | Optimizes pre-event tapering blocks |
| Friel Training Stress | Consistency Framework | TSS, Compliance | Adherence Score | Validates plan execution and load control |
| Sandbakk–Holmberg Integration | Action Generation | Multi-framework synthesis | Adaptive Action Score | Produces holistic, actionable coaching feedback |
| Skiba + Critical Power Extension | W′ Depletion & Recovery Modelling | W′ Balance, Joules > FTP | Anaerobic Repeatability State (WDRM) | Evaluates supra-threshold repeatability under fatigue |
| Cardiovascular Drift Theory | Durability & Decoupling | Power–HR Decoupling %, Drift Exposure | Durability State (ISDM) | Measures aerobic stability under prolonged load |
| Noakes + CNS Fatigue Models | Neural Load Regulation | IF Density, Intensity Clustering | Neural Density State (NDLI) | Detects central fatigue and intensity stacking risk |
The Coach V5 functions as a Physiology-Governed multi-framework inference engine — blending classical endurance physiology, structural capability modelling, and adaptive load dynamics into a unified decision layer.
The Montis.icu Coach V5 engine continuously monitors a multidimensional suite of 63+ coaching markers across physiological, psychological, and metabolic domains. These metrics are structured into three tiers within the Unified Reporting Framework (URF v5.1).
Primary load, recovery, metabolic, and readiness metrics — continuously monitored across all report types.
| Domain | Markers | Purpose |
|---|---|---|
| Load & Performance | CTL, ATL, TSB, TSS, ACWR, Monotony, Strain, LIR, Fatigue Trend | Measure training load, balance, and adaptation trends. |
| Wellness & Recovery | Recovery Index, HRV, Resting HR, Sleep Score, Sleep Duration, Stress Tolerance, Mood, Soreness | Assess physiological recovery and psychological readiness. |
| Metabolic Efficiency | FatOx, MES, EF, Efficiency Drift %, Fatigue Resistance, Z2 Stability | Evaluate aerobic durability and energy system balance. |
| Periodisation | Block Phase, Taper Efficiency, Consistency Score, Durability Index, Adaptation Ratio | Track training phase progression and long-term load control. |
| Readiness & CNS | CNS Fatigue Index, Motivation Stability, Readiness Forecast | Measure neural recovery and performance readiness. |
| Holistic Actions | Adaptive Action Score, Action State 🟢🟠🔴, Trend Confidence % | Generate adaptive feedback and actionable coaching guidance. |
Derived from device integrations (Garmin, HRV4, Whoop) or advanced load models; used to refine URF analytics.
| Marker | Source / Dependency | Purpose |
|---|---|---|
| VO₂ Estimation (VO₂eff) | Garmin or power–HR model | Cardiorespiratory efficiency trend |
| Intensity Factor (IF) | Power data (FTP defined) | Session intensity relative to threshold |
| Session RPE (sRPE) | Manual / subjective input | Perceived load calibration (TSS × RPE) |
| Sleep Debt Index | Wellness logs (Sleep vs Target) | Quantifies chronic recovery deficit |
| HRV-SDNN / RMSSD | HRV4Training / Whoop API | Autonomic variance for deeper readiness precision |
| Glycogen Depletion Score | Power × Duration × IF model | Estimates carbohydrate utilisation |
| Hydration Score | Body weight & HR trend | Detects dehydration or plasma volume shifts |
Tier-3 introduces structural capability modeling — evaluating how fitness behaves under stress, not just how much load is accumulated. It combines stress diagnostics with performance-expression signals derived from power-duration curves.
| Model | Core Signals | Purpose |
|---|---|---|
| WDRM — Anaerobic Repeatability | W′ depletion %, high-depletion sessions, joules above FTP | Measures repeatable supra-threshold resilience |
| ISDM — Durability | Decoupling, high-drift sessions, long-session load | Evaluates fatigue resistance and power stability |
| NDLI — Neural Density | Rolling joules > FTP, intensity clustering, IF density | Detects CNS strain and intensity stacking |
| ESPE v1 — Energy System Progression | Power-duration curve anchors (5s, 1m, 5m, 20m, 60m), curve rotation, CP/W′ model trends | Detects adaptation across energy systems (neuromuscular, anaerobic, VO₂, threshold, durability) by comparing power curve behaviour across training windows. |
ESPE extends stress diagnostics by analyzing how the athlete’s power-duration curve evolves over time. This allows the system to determine whether training load is producing meaningful performance adaptation rather than simply accumulating stress.
🧩 Total Monitored Markers:
Tier-1 (32) + Tier-2 (7) + Tier-3 (24) → 63+
Weighted dynamically across report types (Weekly • Seasonal • Wellness • Summary)
via the URF adaptive relevance model.
The Montis.icu Coach App is fully dependent on Intervals.icu for athlete data. All workouts, wellness logs, and training load calculations are sourced directly from your Intervals.icu account.
For best accuracy, ensure your wellness markers are synced: HRV, Resting HR, Sleep, Mood, Stress, and Soreness. Garmin users should expose VO₂maxGarmin, Performance Indicators, and Intensity Factor (IF).
🙏 Special thanks to David Tinker, creator of Intervals.icu, for enabling open endurance data access and seamless athlete integration.
Search in the GPT Store for “Montis.icu Coach V5” or click on top link below 👇
Note: Version 3 is now deprecated — please use the latest V5 Railway Engine build for best performance and accuracy.
The Montis.icu Coach App evolves in the open. Feature ideas, enhancements, and experimental concepts are discussed publicly, while shipped and committed work is tracked separately.
New ideas and enhancement requests are tracked as GitHub issues. This keeps discussion transparent and ensures proposals are evaluated against URF guarantees such as determinism, auditability, and context integrity.
View Open Feature Requests 🧩 Intervals.icu Forum DiscussionFeatures that have been accepted, implemented, or released are documented in the public roadmap and changelog. This reflects what is real and live, not speculative ideas.
👉 View the roadmap and full release history here:
🗺️ View Roadmap 🗺️ View Changelog 🗺️ View Documentation🔍 Feature requests may not appear on the roadmap until they are validated, scoped, and aligned with URF design constraints.
For integration, customization, or coaching inquiries, connect via GitHub link below or DM via Intervals.icu DM and contribute in Intervals.icu Forum.
github.com/revo2wheels
Built with ❤️ for endurance athletes — by Clive King.
Made in the Suisse Alps 🇨🇭.
Powered by Intervals.icu, Cloudflare and the Railway Engine.
Montis.icu Coach App is free to use. If you find value in it and would like to support continued development, infrastructure costs, and new features, you can become a supporter below. Your support genuinely helps keep the project independent and improving.