AI Running
Recreational runners training for a 5K to marathon — typically already following an app like Runna, Garmin Coach or a ChatGPT-built plan — who can read their own Strava and watch data but need help judging whether an AI-generated plan is progressing them safely.
- Guides
- 12
- Articles
- 27
- Words
- 73,721
What this site covers
6 sections, 6 supporting pages and 27 articles. Every one is free and complete.
- AI Coaching Apps, Tested Against Each Other
best ai running coach app
2,386 words 1 supporting 5 articles
- Building Your Own Plan With ChatGPT and Claude
chatgpt running training plan prompt
3,088 words 1 supporting 4 articles
- Training Load and Injury Risk
acute chronic workload ratio running
2,876 words 1 supporting 6 articles
- Reading Readiness, HRV and Recovery Scores
garmin training readiness explained
2,725 words 1 supporting 5 articles
- AI Gait and Form Analysis From Phone Video
ai running form analysis app
2,489 words 1 supporting 4 articles
- Return-to-Running After Injury
return to running after injury plan
3,067 words 1 supporting 3 articles
Latest writing
- Garmin Daily Suggested Workouts: Three Weeks of Following Them Exactly 1,464 words A logged test of obeying the watch's daily suggestions, showing where the reactive day-to-day model conflicts with the structure a race build actually needs.
- Rebuilding Chronic Load From Zero Without Overshooting 1,889 words Explains why ratio-based load rules break down at low baselines and proposes absolute weekly increments for the first six weeks back instead, with worked numbers.
- Ground Contact Time and Vertical Oscillation: Useful or Noise? 1,857 words Shows these watch metrics track speed more than technique, so they're only informative when compared against yourself at matched pace — and mostly useless as cross-runner benchmarks.
- Body Battery, Whoop Recovery and the Number That Disagrees With You 1,741 words Compares how different recovery scores are constructed and argues that when the score and your legs disagree, the score is the one that should lose — with the exception cases spelled out.