This is the way
And if you have a bad testing day for some reason now you lost the testing day AND probably the 1-3 days of rest you took in anticipation of the test.
You shouldn’t need to take any rest before doing a FTP test. I do Kolie Moore style FTP tests - they don’t require you rest beforehand and they’re a decent workout in and of themselves. Working exactly at FTP isn’t too sensitive to fatigue in my experience (unlike working above FTP).
Here’s my cal from the last time I took a test - no rest beforehand.
I am pretty sure that TR has said that aiFTP is an estimation of FTP?
TR considers this to be FTP. There’s a loud group of users who are adamant that FTP and AIFTP are not the same thing. So it depends who you’re asking.
I’m of the opinion that if the model doesn’t know what FTP is anyway, if it is literally just prescribing watts x time, then AIFTP has the wrong name, and they should give it with a more descriptive name, like “training focus” and model something around 30-60 minute power and present that to the user as FTP, so that it tracks more consistently with the rest of industry’s usage of the term.
We’ve never said that AI FTP Detection is an estimation or that it isn’t FTP.
FTP stands for Functional Threshold Power.
It was created to have a functional training benchmark you could use to give yourself the right intensity and duration for your training.
Somewhere along the line the protocols and approximations for FTP became the (many) definitions. Some definitions work well for one person while they don’t work well for others, and in many cases athletes are held back by this.
AI FTP Detection uses models that analyze your performance to figure out what the best training benchmark would be to give you the workouts you need right now to get faster.
In the majority of cases the value from AI FTP Detection aligns closely with what our athletes already had. In some cases it is higher lor lower, and in very rare cases, it is significantly higher or lower.
But in every case, TrainerRoad AI adjusts your training so you get appropriately difficult workouts that give you the improvement you need.
Even if athletes decide to manually set their own FTP, TrainerRoad AI will still do it’s best to give you the right workouts, but it might run into limitations and not be able to get you out of a hole or past a plateau.
The best outcomes are seen when athletes use the value from AI FTP Detection.
16 Likes
I am confused.
Hi Johathan, I asked this question in another thread, but the TR employee may not have seen it:
Has the TR team tried to equate how long of a duration you could/should be able hold for your AIFTP?
I assume the functional part of the definition must have some sort of anchor, but not what the classical FTP has been in the past. For myself, I’m not sure if I could hold my AIFTP for longer than 10 minutes! I’m just looking for some general guidance on the AIFP setting. Thanks!
It would alleviate a lot of confusion if you just produced a white paper
any plans to describe your system?
I don’t blame you, lol. Eddie and I got our wires crossed. 
It’s not accurate to say that AI FTP Detection is estimating FTP. It’s running simulations to find the best workouts (appropriately difficult, maintains sustainable training trajectory, etc.) for you, and it uses this to calculate what the best FTP value would be to increase the likelihood of those favorable outcomes. it has a built in system of checks and balances.
I worry about the term “estimation” because I think we’ve all used different services or had numbers suggested to us that are genuine estimators, and this is far from that.
5 Likes
It varies person-to-person. In some cases it aligns closely with 60 or 40min power, or 95% of 20, or 90% of 2x8, or 75% of highest 60 sec in a ramp test, and it might be somewhere in between for others.
It highlights the importance of training people as individuals and prioritizing getting the athlete the best workouts rather than tolerating sub-par workouts due to a specific testing format or definition of FTP.
I think what we are doing is just the first step in a larger paradigm shift away from viewing FTP through the lens of test formats or how long you can hold it for an hour. I think we’re early movers and as others start to develop their own models, this decoupling from old definitions will become commonplace.
To directly answer your own question, I wouldn’t aim to validate your FTP through how long you can hold it. Instead I’d aim to validate it with, “Are my workouts appropriately difficult, and is the power I’m producing in my workouts going up over time?”
FWIW, in my personal case over the last month I think my AI FTP of 289 was somewhere around my 30min power, and right now I think it is closer to my 60min power, but the whole time my workouts have just felt perfectly difficult and I keep getting power PRs for the year during every hard workout, so I’m seeing that progression and super satisfied!
17 Likes
We’ll continue to produce educational content all about it in addition to the in-depth podcasts we’ve created about it, but we do believe what we’ve created is uniquely advantageous, so we don’t plan to expose all the details.
But maybe a manifesto of sorts on how this process has changed our views on endurance training and endurance training adaptations could be of interest?
7 Likes
…ok
Thankyou for clarifying.
I take it that aiFTP is not trying to be equal to FTP as we understand it then?
If we take FTP to be a proxy for MLSS or maximal metabolic steady state how is TR defining aiFTP?
Thank-you for the very detailed response. To answer the question: are my workouts appropriately difficut? So, far I can do them, and not fail, BUT most of them have not been in the intended zone. For instance, my SS workouts are threshold according to my RPE, and the unders, for my O/U, are not under.
I’m cool with trusting the ML, but has TR decoupled the intent of the workout, say SS, and just want you to do the watts and not care what zone I’m in, even if that means I’m doing a threshold workout? In other words, does it matter that the intended zone or energy system does match the workout description?
This is a really good question. I’m assuming here, but TR did say that the AI uses the plan framework to pick workouts within energy systems, so I’d assume SST should feel like SST, and so on, BUT I also know that if you jack your FTP up manually, the system will turn your threshold workouts into SST because it’s looking for a wattage target. In that case, your SST would indeed feel like threshold.
For Bones and me (and others), we started with a too high detections, and that’s the basis of his question.
For myself, I decided to turn down my FTP manually, and I’ve been extremely happy with the workouts. The AI is serving up great workouts and I’ve already made gains in my SS power since about a month ago.
I would have survived if I stuck with the original estimate, but the system seemed to be converging on shorter intervals rather than decreased power. Now, at least, I’m scheduled to move into 3x20 SS this week, while my over unders go behind the ten minute mark to 3x12. Seems more effective and productive.
I am curious to hear if I didn’t go down the right path with my decision (but my next AI FTP detection is only a week away anyways - right after my rest week).
I also turned down my FTP for a couple of workouts, but I’m going to see if I crash and burn on my next o/u. I’m a 50 year old man with no racing ambitions, so don’t care if it sets me back a bit - I just find going into the workouts quite stressful!
The funny thing, is it already too high IMO, and it’s predicting (likely won’t get there), to go up another 11w in 25 days again! I keep wondering why the ML has so much faith in me lol.
Anyway, I’m going to let this thing play out and see what happens as I said. My main question is really: has TR pretty much abandoned the training plans in many ways, and truly just going by watts - and the energy systems don’t really matter anymore. Are they more for presentation now, just so people don’t freak out more than they have been? Maybe this is the new frontier Jonathan is alluding to!
Getting the best workouts for each person could very well have nothing to do with staying in certain zones anymore I suppose. Again, I’m cool with that, but would like to hear Jonathan’s view on this.
It does read raw watts and it understands your ability to maintain those watts for specific durations, and it can independently manage that for each zone.
As @Jesse_Vernon1 indicated, the plan framework does decide the zone/profile/duration you’ll do, and TrainerRoad AI runs the simulations to find the best workout within that zone/profile/duration. If it can’t find something appropriate, it will alter the duration, and if excess fatigue is present, it may adjust to Endurance or rest.
But I can’t see a scenario where it would turn a lower zone into an upper zone.
Looking at your workouts since Jan 9, I see 3 Sweet Spot workouts and 3 Threshold Workouts, and only 2 out of the 6 are rated harder than predicted.
-
Jan 13: 5x10 SS at 266 (You nailed the power and even went +10w on the last interval, and you also rode 20-30w over target on your rest intervals. It was predicted to be Hard, but you rated it Very Hard, but I think I’d expect it to be harder when you’re riding above target for rest intervals and +10w on the last set. Those adjustments are totally fine, but worth noting that the model isn’t prescribing or predicting that.)
-
Jan 16: 6x4-7min OU @281/281-303 (You rated this one Hard and it was predicted to be Hard. You rode 20-30w over target during rests again.)
-
Jan 20: 6x8min SS @278-260FTP (You rated this one Hard and it was predicted to be Hard. You rode 20-30w over target during rests again and rode over target on the last set by 8w.)
-
Jan 24: 3x9min OU @281-311 (You rated this one Hard and it was predicted to be Hard. You rode 20-30w over target during rests again.)
-
Jan 27: 5x10min SS @278 (You rated this one Very Hard and it was predicted to be Hard. You rode 20-30w over target during rests again. For comparison, a week earlier you did 3x9 OUs averaging 291-293 and rated that Hard.)
-
Jan 30: 3x9min SS @281/311 (You rated this one Hard and it was predicted to be Hard. You rode 20-30w over target during rests again and about 10w over target for the Endurance block after the last interval.)
-
This looks pretty well calibrated to me? 2 out of the 6 workouts were harder than predicted. Assuming you were hitting your targets during rest intervals, they may have felt easier?
4 Likes
This is also a very okay option! You’re welcome to just manually set your FTP. This will make it so you can’t get an FTP Prediction since it would be comparing apples to oranges, but the model behind TrainerRoad AI will still do it’s best to give you the right workouts.
1 Like
Do you still plan on giving users 20/40/60 minute estimates or is that plan abandoned?