I have been messing around with workouts to see what happens with the new AI FTP prediction but I usually just leave it alone because when ever I change something it usually drops the FTP but this last one I was trying really is not making sense to me.
Below is a screen shot of what its currently showing. You can see that the FTP is predicted to go to 358.
If i change ethe Moose’s Tooth on Feb 8th to something harder, the FTP prediction drops to 350. This does not really make sense to me. Why would doing something harder at the end of 3 weeks of structured training followed by a week of endurance drop the predicted FTP?
“ while yes, it is unlikely that actual fitness would change that much in that time, the method to give the most effective training could.“
Your fitness or FTP isn’t changing based on how your rate a workout or changing a workout. But the TR metric the system uses to determine optimal future workouts does change. People are trying fight or game the system because they don’t understand the what Nate means when he says, “it’s just about the watts.” For example I had to swap out my 90 minute threshold workout on Thursday for a 60 minute threshold. The 90 minute had a WL of 4.2 while the alternate had a 3.0. Lots of people who say that the alternate workout selection wasn’t working but it was dropping the level. But that’s looking at the wrong thing. The 90 minute workout had 30 minutes of over/under time and then added zone 2. The 60 minute workout had 30 minutes! So it found me just the right workout because it was looking at watts! It didn’t care what the WL levels was.
This same principle applies when you move/skip/add workouts. The system is trying to solve for “what are the optimal workouts”.
So I did search the forums but what I found was someone changing there endurance day from 1 hour and 30 min workout to a 2 hour and 30 min work out and it dropped his FTP. That also didn’t make much sense to me because it was an endurance ride.
my point was that its at the end of a structured training block followed by an endurance week which in my view that would give me time to recover(maybe thinking of an endurance week incorrectly).
To me it just does not make sense that making your last structured training ride(picked from their suggested “harder” rides) a little bit more stressful would cause such a huge drop.
its not like I’m adding huge amount of TSS, duration, or even doing a “group ride” on a yellow or red day.
anyhow maybe I’m thinking of all this wrong because I do know that TR “FTP” is not the traditional FTP that most people think of. I know for a Fact that I could not hold 347 ( current TR FTP) or the predicted 358 FTP for 40 min to 1 hour.
I guess for now I’ll just keep following this AI FTP suggestions and see if I get any new PRs.
You have an easier VO2Max workout the day before your detection in your second screenshot. That might very well adapt, bumping your prediction back up again. If not, feel free to manually bump it up if you feel up for it when the day comes.
I’m sort of dreading this today. The ftp jump was 10 watts which is significant. I fuelled relatively highly so feel it’s wasted if I change tac. Starlight -2 suggested. But stressing
My WAG, is that the model is telling you that more is not always more. Notice is also reduces your Vo2 max workout on the 17th when you increase your threshold workout. So it must be sensing that increasing your load now is too much and will require more rest to compensate.
I noticed something similair. Wanted to see how a longer session (1 hour) would effect FTP prediction, and it lowered mine (250-247). So I switched back to the the original planned session (30 mins) and the FTP prediction did not return to its original estimate. Not a complaint really, just thought it was interesting.
Not that I know anything (and to anthropomorphize TR’s AI/ML) the way I figure it is that if the goal was to increase FTP, then it creates what it believes to be the optimal plan. Any deviation from that optimal plan will be less optimal and lead to a lower predicted FTP. In my limited experience that seems to be what happens.
It recalculated and then landed on the same (lower) prediction. Only reason I even mention it, is on the podcast the guys were saying you were free to substitute different workouts to see what effects are. A few measly points losses are a big deal, will just motivate more. Definitely don’t want to be seen as complaining.
