And don’t account for the PM r through changing FTP, instead configure the PM with an appropriate scaling factor/etc.
When’s the last time you calibrated your Kickr?
I assume you can, and should regularly, do it for the Kickr as for other trainers…
1 Like
There’s another thread on my power discrepancies. It’s been handled to death. Nothing has worked thus far. Everything you imagine has been considered
Re-subbed to the platform for the first time in 8 months.
Made a plan, skipped the ramp test and ai ftp analysed all my recent zwift and outdoor rides and came up with exactly the right ftp number (which is currently 30 odd watts under my previous trainerroad recording).
Very, very impressive.
10 Likes
Welcome back! Stoked you’re digging the new features. Let us know if you have any questions and keep up the solid work!
I’ve only adjusted outdoor rides posthumously
Sorry to hear about your sad demise.
10 Likes
Apart from buying a new trainer?
I haven’t been doing any structure this summer since the weather has been good and group rides abundant. I’ve been giving the AI FTP Detection a shot and have found that it overestimates my FTP by quite a bit. I’m wondering if this has to do with the quality of data I’m feeding it through mostly hard group rides which tend towards short V02 max efforts rather than sustained work around threshold? I recently did a TTE/Baseline test which verified that my actual FTP is sitting around 15-20 watts below what AI FTP is estimating. However, I’ve set a number of power PRs on the steeper end of the power curve including from 3 to 5 minutes recently so perhaps if that’s what AI FTP is using to calculate FTP that would explain the discrepancy.
Is anyone having a similar experience with a lot of unstructured riding? I’m curious to see if my results will be closer in the winter once I return to more structured training and my progression levels are tracked accurately.
I’m sure this has been asked, but what’s the harm in making AIFTP available at any time? If it works, and I click it too often, then…?
For starters, changing FTP via ANY method (not just AIFTP) typically applies a downward adjustment to your Progression Levels. Overly frequent FTP changes would potentially nullify the progression in things like interval duration, intensity and shorter recoveries that are common with moving up in PL’s.
Sure, TR could look to refine the changes that get applied to PL’s via FTP changes. Might take a closer look to the timing and amount of changes to determine if/when to alter PL’s.
Outside of that, what is your reason for wanting FTP changes more often than the current 14-day limit applied to AIFTPD?
1 Like
I’ve had similar experiences with the Ai ftp detection, I don’t do many group rides, i follow a plan.
I find it about 5-10 watts higher than expected, sure I could keep it where it puts me and “ raise my levels”. My main focus lately has been building TTE at ftp for a few months so a lower ftp gives me longer intervals. I’ve always been a more anaerobic athlete from years and years of bmx, so riding at threshold for a long time has been a struggle for me.
I thought about writing my experience to support about my issue but haven’t.
2 Likes
I took a peek at your Calendar and saw that your Outside Workouts are missing Survey responses.
The more information we have, the more accurate our AI FTP detection will be. I suggest you complete the post-workout Survey for all of your rides to ensure we have all of the information to detect your FTP accurately. Check out the article below:
Without the subjective feedback from the Surveys, it is difficult to determine whether those outside rides are Endurance Workouts, or VO2 Max Workouts for you! If you are completing ride after ride at this level, it may be presumed that intensity is easy for you!
Furthermore, did you set these PRs after doing the test? Those PRs will certainly be accounted for in the prediction. It may be that your fitness and, thus, your FTP has increased since this test, as evidenced by those shiny new PRs 
!
Finally, what test did you do to determine your FTP? Was this inside or outside? Were you using the same equipment? I want to make sure we are comparing apples to apples!
3 Likes
Thanks for the response - I’ll give the survey responses a try going forward! I had previously assumed that survey responses didn’t have any effect for unstructured outside workouts since those don’t impact progression levels.
The PRs were set about a week before the test so I definitely think they impacted the prediction. I ran the prediction the day after I tested. The test I used is the 40 minute baseline TTE test as described by Kolie Moore - this one. Not a TR-endorsed test I know, but one I’ve found to be very reliable provided I pace it correctly, which I did! (nothing left in the tank at the end)
I did it indoors, but using a different power meter than I use outdoors. It’s possible that accounts for a very small part of the discrepancy, but I’m quite confident that the number suggested by AI FTP is unsustainable for threshold work on either setup.
It sounds like survey responses might be the next thing to try! At some point I may also try to run a test comparing the two power meters, since one is crank-based and the other is pedal-based so I could run them simultaneously and compare them, just to ensure I’m accounting for any difference there might be.
1 Like
Have you reported this to TR support with specific numbers? E.g., what AI detection says your FTP is versus what you think it is? If not, you should. The only way it will get better is if people provide quantifiable feedback that the team can use to revisit / tweak it
1 Like
My main reason for not doing this is that I know and recognize that the types of rides I’ve been doing would not result in very good or useful data for the system to come up with a reliable estimation, so I mentioned it here more for the sake of curiosity and discussion than anything. Perhaps if it’s still not accurate once I return to more structured training based on TR workouts I’ll raise it with support. They responded above with some suggestions anyway which is always appreciated!
1 Like
Being selfish 
I think your use case is a great one for the team to look into. We all do unstructured outside rides, and these get factored into AI Detection. If AI Detection doesn’t handle these correctly, then it throws off the results for all of us.
So a case of “pure” unstructured rides is a good test case that the team could work with to improve AI Detections ability to “correctly” figure out the impact on FTP from unstructured rides
3 Likes
Hello Sarah - are we supposed to be giving survey responses to outdoor unstructured rides? I assumed that since they are not included in adaptive training, that the survey responses were not a factor in anything. But if I am wrong, I will gladly start doing that.
Yes, Post- Workout Surveys will have an impact on your AI FTP detection! This subjective feedback allows us to compare Training Stress against perceived exertion, which is useful information when determining your fitness level.
So yes, it will only be more accurate with more information! 
7 Likes
@SarahLaverty I probably missed it or mixed it up amongst the various discussions on AI FTP and AT, but will AI FTP auto adjust your FTP on it’s own if it seems off? Asking as I am returning from a prolonged, unplanned break. I would expect my FTP to bounce back to a point, however so far it has not prompted me to up it. I’ve been cruising through most of the workouts rating most as easy and seeing bumps in progression levels, however I did do close to two hours outdoors with an average and normalized power greater than my current estimated FTP a few weeks ago with no change. Do I need to manually adjust the FTP in these situations or just keep plugging until the next scheduled FTP test? Normally I wouldn’t expect a substantial change over the period of time I am talking about, but based on my situation leading into this block I would expect an initial quicker ramp in FTP as I return to training.