AI Cycling
Self-coached intermediate-to-advanced UK road, gravel and time-trial cyclists who already train with a power meter and Strava, intervals.icu or Zwift, and want to know which AI coaching tools, models and prompts actually hold up against their own ride files.
- Guides
- 12
- Articles
- 29
- Words
- 78,666
What this site covers
6 sections, 6 supporting pages and 29 articles. Every one is free and complete.
- AI Coaching Platforms, Tested
ai cycling coach app
3,167 words 1 supporting 5 articles
- Analysing Ride Data With LLMs
analyse strava data with ai
2,358 words 1 supporting 6 articles
- FTP Estimation And Fitness Models
ai ftp detection accuracy
2,939 words 1 supporting 6 articles
- Recovery, HRV And Readiness Scores
hrv guided cycling training
2,701 words 1 supporting 4 articles
- AI Route Planning And Race Pacing
ai cycling route planner
3,206 words 1 supporting 4 articles
- Build Your Own Training Tools
strava api python training analysis
2,643 words 1 supporting 4 articles
Latest writing
- Fitting A Fitness-Fatigue Model To Yourself (And Why It's Harder Than It Looks) 1,197 words Implements the Banister model against real performance tests and argues the fitted parameters are unstable enough that the chart's shape, not its values, is the usable output.
- Athletica.ai Under The Bonnet: Science-Led Or Marketing-Led? 1,337 words Traces Athletica's published methodology to its source literature and tests whether the delivered sessions actually reflect the polarised model it claims to implement.
- Reviewing A Whole Season With A Long-Context Model 1,740 words Demonstrates a summarise-then-reason pipeline over 300 rides, arguing the useful output is pattern detection across blocks, not commentary on individual sessions.
- Build A Personal Training Dashboard With Streamlit In An Evening 1,693 words Argues a 200-line local dashboard answers your three recurring questions better than any subscription, with the full code for load, power curve and decoupling views.