so if we are doing a plan or block of training, say 6 weeks. we carry out the work but as we progress, the fatigue builds and perhaps the effort feels harder and the PL changes are small.
does AI FTP only look at the increase work done as evidence of FTP change, or does it factor in the added fatigue and predict that with a rest week and adaptation period your ftp should go up, given the previous weeks work.
for example on week one, doing threshold work may feel hard, but the same PL effort on week 6 may feel very hard, or all out, especially on a high volume plan. would the AI build in expected adaptation or take a view that your ftp has went down?
fitness change = training + rest + adaptation. does AI only focus on training?
In your hypothetical 6-week block, AI FTP Detection will look at your personal biometrics and the unique details of your recent and past cycling data to detect your FTP without the need for maximal efforts or specific workouts.
Because AI FTP Detection considers so much of your training data, it’s very unlikely a single type of effort or workout would substantially sway the model. For example, the model “knows” when you’re doing an easy ride and won’t confuse that for decreased fitness. You also don’t have to do capacitive or all-out efforts for the feature to work. In fact, it works if you only do sweet spot or aerobic riding and never do any high-intensity intervals!
Additionally, with Adaptive Training, your PLs should probably increase over those 6 weeks. It would be unlikely that you would be doing the same PL Threshold workout on week 6 as you would have been doing on week 1. The workout you did on week 1 would probably feel easier compared to the workout on week 6 due to changes in interval structure, total time in zone, and %FTP you’re targeting.
Regarding how you rate your workouts (Hard vs Very Hard vs All Out), those survey responses will be used by Adaptive Training to propose adaptations to your plan, but they won’t impact AI FTP Detection at this time. AI FTP Detection will just look at the raw power data from your workouts combined with your personal biometrics.
Hope this helps! Feel free to let me know if you have any other questions.