Use AI To Draft Your Next Training Block

Spend less time on data entry and more on coaching. Use a simple AI workflow to parse athlete data from any source, identify trends, and generate the first draft of your next training block. Your thinking, just faster.

Start the free 10-day challenge →See the method

What we’re actually working with

As an endurance coach, you work with athlete-generated data from wearables, power meters, and heart rate monitors. This includes workout files (TSS, IF, power/pace curves), subjective feedback (RPE, soreness), and health markers (HRV, sleep duration). This isn't about replacing your hard-won coaching intuition; it's about using AI as a tireless assistant to structure and pre-analyze this data before you apply your expertise.

Why doing this without a method fails

Without a system, you drown in data. You toggle between platforms, manually copy-paste ride notes, and eyeball charts, trying to connect a client's subjective feelings to their power data. This manual pattern-matching is slow, error-prone, and doesn't scale. It caps your client roster and burns you out on administrative work, leaving less time for the high-touch relational coaching that sets you apart and delivers real results for your athletes.

The 3-Layer treatment

How the method handles endurance coaching clients

Layer 01

Research

The Research layer is for understanding the evidence base for a specific intervention *before* you program it. For example, before programming a high-volume block, you might ask an LLM to summarize the latest meta-analyses on polarized versus pyramidal training intensity distribution for a 50+ masters cyclist. Or, you could have it pull the protocols from specific studies, like Støren et al. (2008) on maximal strength training for runners, to check your session design against the source material.

Layer 02

Ledger

The Ledger is your structured record of the athlete's data. Instead of disorganized notes and multiple data silos, you'll teach an LLM to parse it all into one clean format. You feed it everything: exported .fit file summaries, RPE scores from a spreadsheet, sleep data, and the athlete's own text messages. The AI's job is to create a simple, day-by-day table with every metric in its own column. Now you can scan for correlations between sleep, stress, and performance at a glance.

Layer 03

Protocol

The Protocol is your plan of action. With a clean Ledger, you can now use the AI for efficient analysis and drafting. Ask it to "Graph the relationship between weekly TSS and morning HRV," or "Identify all sessions where RPE was more than 2 points higher than the session goal." Based on the output, you can then prompt it to generate a draft training block: "Draft a 3-week base block for this athlete, decreasing volume by 10% from the last cycle and adding one day of mobility work. Keep weekend long rides under 3 hours."

Read the full 3-Layer method →

Three prompts you can use today

Paste any of these into the AI chat tool you already use. No setup.

Draft a Training Block from Athlete Data

Act as an expert endurance coach. I will provide you with a summary of my athlete's recent training data, performance metrics, and subjective feedback. Your task is to analyze this information and draft a 4-week training block for their upcoming goal.

Here is the athlete's context and data:
- Goal: 100-mile gravel race in 12 weeks.
- Experience Level: Intermediate, 3 years structured training.
- Recent Weekly Volume: 8-10 hours.
- Key Observation: Athlete reports high fatigue after weekend back-to-back long rides.

Data:
[PASTE YOUR DATA HERE. Include weekly summaries of TSS, hours, key workouts with power/HR/RPE, and any notes on sleep, stress, or recovery.]

Based on this, draft a 4-week training block. Structure it as a 3-week build and a 1-week recovery. For each week, provide a day-by-day plan including workout type (e.g., Z2, Tempo, VO2), duration, and intensity target (e.g., TSS, %FTP, or RPE). Reduce the load of the second weekend ride to improve recovery.

Synthesize Subjective and Objective Data

Act as a data analyst for an endurance coach. I will give you a multi-week log containing both objective training data (TSS, duration, power) and subjective athlete feedback (RPE, sleep quality, life stress, soreness). Your job is to merge these sources and identify potential correlations or mismatches that I should investigate.

Data Log:
[PASTE YOUR DATA HERE. A simple text format is fine, e.g., 'Date: YYYY-MM-DD, Workout: 2hr Z2, TSS: 100, RPE: 6/10, Sleep: 7hrs, Stress: High'].

Analyze the provided data and answer the following:
1.  Are there any days where RPE is unusually high for the given TSS or workout intensity? List the dates.
2.  Is there a visible trend between reported life stress or poor sleep and next-day performance or RPE?
3.  Based on the data, what is one question I should ask my athlete to better understand their recovery?

Research the Evidence for an Intervention

Act as a research assistant for a sports scientist. I need a concise summary of the current scientific literature on a specific training intervention for endurance athletes. Please cite key studies (Author, Year) and provide specific protocols where possible.

My athlete is a 45-year-old male marathon runner with a history of calf strains. I am considering adding heavy-resisted strength training to his program to improve running economy and injury resilience.

Based on a search of PubMed and Google Scholar, please summarize:
1. The evidence for heavy strength training improving running economy in masters athletes.
2. The evidence for its role in lower-leg injury prevention.
3. A sample weekly protocol, including specific exercises, set/rep schemes (e.g., 4x5 reps @ 85% 1RM), and how to periodize it alongside a running plan. Focus on studies like Beattie et al. or Rønnestad et al.

Tools that help

How AI tools make endurance coaching clients easier to live with — and understand.

You don’t need another app. These are the tools most people already have or can use for free, and the specific job each one does when you point it at endurance coaching clients.

Research the literature

A sourced-search AI (e.g. Perplexity, ChatGPT search, Gemini)

Replaces an afternoon of tab-juggling on endurance coaching clients with a cited summary in minutes. Ask it to mark every claim as primary study, review, or opinion — that one habit removes most of the noise.

Read your own data

A long-memory chat AI (e.g. Claude, ChatGPT, Gemini)

Paste weeks of notes, exports, or symptom logs about endurance coaching clients in a single window. The AI spots patterns your seven separate apps hide from you, and remembers them next week.

Capture without friction

Apple Health + Notes (or Google Fit + Keep)

Already on your phone. Pulls endurance coaching clients-relevant signals into one export and lets you jot context in seconds — no new subscription, no new dashboard to maintain.

Stream the raw signal

Your wearable (Oura, Whoop, Garmin, Apple Watch)

Stop reading the marketing score. Export the raw stream behind your endurance coaching clients number and feed it to a chat AI — that's where the actual insight lives.

Build your own reference

NotebookLM (or any source-grounded notebook)

Drop in your lab PDFs, saved articles, and personal notes on endurance coaching clients. Ask questions; the answers cite back into your own sources. Becomes a second brain you actually trust.

Turn data into a plan

A weekly review prompt

One scheduled prompt every Sunday: "Given this week's endurance coaching clients data and notes, what changed, what's noise, what's the smallest experiment for next week?" Replaces three productivity apps and an anxiety spiral.

Browse the AI Tools Atlas →See how the method uses them

Common questions

Will this replace my coaching software?+

No. This method complements your existing tools. You still need platforms like TrainingPeaks or WKO5 to collect and organize raw data. The AI layer sits on top, helping you analyze and synthesize that data more efficiently once you export it.

Is it safe to put my client's data into an LLM?+

Use caution and prioritize client privacy. Use anonymized data whenever possible, removing names and personal identifiers. Check the privacy policies of the AI tool you use; many offer business-grade versions that do not train on user inputs.

Can the AI make a mistake in the analysis?+

Yes. An LLM can misinterpret data or 'hallucinate' patterns that aren't there. Always treat the AI's output as a first draft or a hypothesis. Your expertise is required to verify the insights and make the final coaching decision. Never trust, always verify.

How is this better than just using my platform's built-in analytics?+

Platform analytics are great for 'what' happened (e.g., power curve, TSS). This AI method helps you understand the 'why' by blending quantitative data with the athlete's qualitative feedback (notes, stress, RPE) to create a more complete picture of their progress and limiters.

Deeper research

The evidence — and where it breaks down

Six short briefs on what the literature, the devices, and the AI tools actually do when you point them at endurance coaching clients. Read them before you change anything.

What the current research actually says about endurance coaching clients+

As an endurance coach, you work with athlete-generated data from wearables, power meters, and heart rate monitors. This includes workout files (TSS, IF, power/pace curves), subjective feedback (RPE, soreness), and health markers (HRV, sleep duration). This isn't about replacing your hard-won coaching intuition; it's about using AI as a tireless assistant to structure and pre-analyze this data before you apply your expertise. Most peer-reviewed work on endurance coaching clients sits in three buckets: mechanistic studies (small samples, tightly controlled), observational cohorts (large samples, noisy variables), and consumer-device validation papers (mixed quality, often vendor-funded). When you read AI-generated summaries on ai for endurance coaching, treat the first two as signal and the third as buyer-beware. The 3-Layer method makes you triage these before they enter your personal ledger.

What your wearable or app is really measuring (and what it isn't)+

Consumer devices that surface a "Endurance coaching clients" score almost always combine a small set of raw signals — accelerometry, optical heart rate, skin temperature, sometimes ECG — into a proprietary index. The score is opinionated, the raw stream is not. The Ledger layer of the method exports the raw stream so AI can analyze the underlying variables instead of the marketing score. That is where most insight lives.

Where consumer-grade endurance coaching clients data is reliable vs noisy+

Cross-validation studies (Stanford, ETH Zürich, and several EU centres in 2023–2025) consistently show that wearables are most reliable for trend direction and least reliable for absolute values — especially night-to-night endurance coaching clients. Use the data the way it is actually accurate: deltas over weeks, not single-night verdicts. AI is well-suited to this kind of rolling-window analysis; humans staring at one number are not.

Common confounders that distort endurance coaching clients signals+

Without a system, you drown in data. You toggle between platforms, manually copy-paste ride notes, and eyeball charts, trying to connect a client's subjective feelings to their power data. This manual pattern-matching is slow, error-prone, and doesn't scale. It caps your client roster and burns you out on administrative work, leaving less time for the high-touch relational coaching that sets you apart and delivers real results for your athletes. The most under-discussed confounders are time-of-month variation, recent travel, alcohol with a 48–72 hour tail, ambient temperature, and any acute infection — all of which shift baseline values by more than most behaviour changes do. A good AI ledger tags these as covariates before drawing conclusions; a bad one quietly attributes the swing to whatever supplement you started that week.

What "good evidence" looks like — and what's hype+

Good evidence on endurance coaching clients: pre-registered protocols, declared funding, raw data available, effect sizes reported with confidence intervals, replication in an independent cohort. Hype: single n-of-1 anecdotes generalised on social media, supplement-funded reviews, AI summaries that cite nothing. The Research layer is for understanding the evidence base for a specific intervention *before* you program it. For example, before programming a high-volume block, you might ask an LLM to summarize the latest meta-analyses on polarized versus pyramidal training intensity distribution for a 50+ masters cyclist. Or, you could have it pull the protocols from specific studies, like Støren et al. (2008) on maximal strength training for runners, to check your session design against the source material. Asking AI to mark every claim with "primary study", "review", or "opinion" before you act on it is one of the most useful prompts you can run.

How AI changes the picture for endurance coaching clients in 2026+

Three shifts matter. First, long-context models can now read 60–90 days of your raw export in a single pass and find correlations no app dashboard surfaces. Second, sourced-search models (with citations) collapse the literature-review step from days to minutes — provided you verify the citations. Third, agentic workflows can run the same daily check-in you would otherwise skip. The Protocol is your plan of action. With a clean Ledger, you can now use the AI for efficient analysis and drafting. Ask it to "Graph the relationship between weekly TSS and morning HRV," or "Identify all sessions where RPE was more than 2 points higher than the session goal." Based on the output, you can then prompt it to generate a draft training block: "Draft a 3-week base block for this athlete, decreasing volume by 10% from the last cycle and adding one day of mobility work. Keep weekend long rides under 3 hours." The judgement layer — what to test, what to ignore, when to stop — is the part that stays with you.

Educational summaries — not medical advice. Cross-check claims against primary sources before changing anything material.