I’m on a 12 week Increasing FTP plan. I’m a Masters 60yr old with a lot of prior racing training experience but basically stopped training hard for a about 2 years due to “life” and am now getting back into it. My scheduling is basically 2 hrs on Sat/Sun and 1 hr on Wed, though most of the time it wants me to take Sun off, completely (which to me seems ridiculous, but that’s another gripe for another time). At the start of my plan, TR said my FTP was 185. I accepted that, despite it seeming low. At the start of the plan it said my FTP would increase to 195 in 4 weeks. That sounded great. I followed the plan, as prescribed, but missed one Wed night workout due to work and it basically dropped my FTP from 185 to 181…which again seemed insane given that I missed ONE workout. None the less I accepted it and moved on, because it was then telling me in another 4 weeks my FTP would again be 195. Now as I’m nearing the next AI FTP prediction it has been dropping my predicted FTP by about a watt a day, despite the fact that I am hitting or exceeding the numbers for EVERY interval on EVERY workout! Example: Threshold 12 mins at 166-186. I average 186 and have 186 NP for that interval. NOTE: ALL of my workouts are outside. I don’t get it. If I’m hitting or exceeding the numbers for every interval in every workout AND the workouts don’t seem that difficult so they get a rating of “Moderate”, why is it DECREASING my predicted FTP?!?!?!? This just doesn’t make ANY sense to me!

Wasn’t the beta for this feature last winter? That might have impacted the visibility of problems with outdoor workouts. FWIW, I do all my hard workouts inside, all year long.

How do you find the prediction and actual detection?

Prediction has always been higher than what I’ve actually achieved, but every drop in prediction corresponds to me either struggling with or failing a workout. One thing that I’ve said in other threads that bears repeating is that “struggling with” is fairly independent of my reported RPE. If I have a workout that is harder than it should be (usually due to poor decision making on my part), my elevated heart rate gives me away, regardless of how much I protest that the workout felt fine.

Thank you @eddie , it would be great to get some feedback on this one. Hopping off the bike in the recovery between intervals is what I tend to do. Just to stretch a bit and have a bit of a shake out. I can’t recall this happening previously. I think it does go beyond a visual thing. I downloaded the FIT and imported into my own app. This is where I noticed the lap avg watts were off (some intervals weren’t picked up). So I guess what I saying its recorded into the FIT file. Oddly enough when I looked on Strava for the synced workout it showed my maximum speed and distance was 253kph / 253km! I can’t remember taking off on the workout :rofl: EDIT: Just remembered something else that caught me by surprise - I got asked why I found the workout difficult question. Assuming it thought I didn’t complete full interval at prescribed power (when I did).

I understand the thought experiment, but this isn’t how TR has ever worked for me. Here’s a diagram of the TR-exported FIT file showing how the lap boundaries drifted relative to the paused workout timer. I completed every interval, pausing when needed—the TR software displayed “Paused.” However, the exported FIT advanced the lap boundaries using wall-clock time rather than the paused workout timer. This appears to have pinged my AI FTP prediction, and I guess future workouts may now be adjusted. No dramas, I just thought this could explain some of the issues others are seeing. cc: @eddie may be helpful for finding out what happened [trainerroad-fit-lap-comparison]

ah I assume this was the issue I hit @eddie [Screenshot 2026-07-31 at 2.32.47 pm]

[image] Pbase: I think that’s true and it’s a great point, but it’s not clear to me if the bug only hits you if you do more than x% outside? I needed exactly one structured outside ride to be affected by the bug.

[image] Pbase: I think that’s true and it’s a great point, but it’s not clear to me if the bug only hits you if you do more than x% outside? Or, if you did one workout outside in February, will it still be impacting you in August? Does it only happen if you do outside workouts “predominantly”? That’s a very good question, and without access to the data, one that none of us can answer conclusively. Even though we don’t know the finer points, this discussion is important in several ways, at least in my mind: If one specific athletes encounters unreliable/unrealistic AI FTP predictions, what are the most significant contributing factors for that particular athlete? Discussing this will help athletes understand why predictions may move one way. For instance, due to a serious illness in the family, I haven’t been able to train since end of March or so. But I continued to commute outdoors. My predicted FTP is close to my all-time low even though with the experience I have amassed, I am significantly higher. Knowing about the outdoor FTP bug helps me understand why. Many athletes feel there are issues with AI FTP predictions even if the predictions were perfect (no insight into why you haven’t reached a predicted value, no visualization of uncertainties, and whether it is good to make it such a prominent figure in the first place). When other athletes share their experiences and tell us how they use TR — or not — can genuinely be useful for all of us. [image] Pbase: This is why I keep trying to nail down what the true known issue and end state is. I know it comes off a little combative, but that’s honestly not my intent. I just want to clearly understand what the known issue is and what the “bug fix” will truly solve. Same here with the apparent combativeness. :handshake: So no worries, I don’t take it personally. Overall, it is important to figure out what bug(s) athletes are affected by, whether perhaps they are statistical outliers one way or another. Perhaps some issues can be mitigated by understanding what TR AI tends to do and then (re)act accordingly. [image] Torneng: I needed exactly one structured outside ride to be affected by the bug. Sure, and if I drop a pen, this will have an impact on the orbit of the moon around the Earth. The question is how significant the impact is. Figuring out “how much” is the a major point of discussion here.

I thought it was obviously implied that it had a noticeable impact. How else would I know that I was affected by the bug? My upcoming prediction went from +3 watts to -11. Which was fair enough based on my performance in that workout. The issue was that after that detection my next prediction was +35 watts.

Ah, I misunderstood. Sounds like it may have been fixed in the latest release based on the notes you found.

Feeling EXTREMELY frustrated with AI FTP detection/plan!

TrainerRoad Software

bradskuse July 31, 2026, 6:33am 282

ah I assume this was the issue I hit @eddie

Workout pauses all of the sudden mess up laps

Topic		Replies	Views
Help Us Track AI FTP Prediction Drops After Outside Workouts TrainerRoad Software	612	26746	November 15, 2026
FTP Prediction Drops 10 points after successful workout TrainerRoad Software	99	5111	October 26, 2026
FTP prediction dropped from from +11 to no change the day after my last workout of the block TrainerRoad Software	78	2400	June 3, 2026
AI FTP: Seems Legit 😂 TrainerRoad Software bug	50	1974	June 7, 2026
Perfect Example of why the Ai Prediction is so incredibly frustrating Uncategorized	180	5691	October 14, 2026

Feeling EXTREMELY frustrated with AI FTP detection/plan!

Ask a Cycling Coach Podcast

We Are Here to Help!

Feeling EXTREMELY frustrated with AI FTP detection/plan!

Related topics

Get Faster with Adaptive Training

Ask a Cycling Coach Podcast

We Are Here to Help!