Well that would be highly problematic. If he rode at 323 watts average for 30 minutes his threshold is unlikely to be calculated at 306. I mean I guess it’s possible, but seems low for any normal ballpark measurement. What is that, 106% of AI FTP for 30 mintues? impressive.
For an ftp of 315 (based off intervals) and 30 mins at 323, that’s about 102% ftp. No way I’m setting my ftp to 323 based off Friels advice for a 30 minute test.
Intervals.icu has usually been fairly accurate if I feed it the right data.
I just wonder how much Ai ftp takes into account outside rides, even tho they say it always does. 
well, its not really “AI” its machine learning. For myself I’ve repeatedly proven over 7 years that I can reliably estimate FTP on the basis of power-to-HR at tempo/SS power. Rough estimate and then feel it out on the road when training near FTP (say 105% and below).
TR uses power and its workouts to do basically the same. It’s an estimate, like my method, and the accuracy will waver a bit depending on the data you feed it.
Let’s say your Intervals 316 estimate is correct, without knowing more.
Then I would say TR is within 3% and depending on your current training the TR estimate might be fine or you might be leaving some really minor optimizations on the table. On the flip side you would be unlikely to overreach, which is a good thing except near the end of the a block when you might want a little overreach before going into an adaptation week (to send the body a stronger adaptation signal).
Can you post an Intervals screenshot of the 30 minutes? Here is one of mine:
With default of eFTP model and eFTP minimum duration of 210-sec. Change min duration to 10 minutes and eFTP gives 263W for ftp estimate. Change min duration to 180-sec and Intervals has paused updating so I can’t tell you 
But back to the theory, here is meanmax power curve in Strava:
because its harder to see the knee of the curve in Intervals.
Point being, if you have a long enough near-max effort all these fancy algorithms are doing is finding the breaking point where the curve goes from flat-ish to trending down.
same in Intervals:
and in WKO:
I’ve got more control over graphing in WKO, so it’s a bit more obvious. Plus I added a yellow band of 95-105% manually set FTP (272 in this example, so yellow band is 258-286W).
My point being… when looking way back, its often easy to pull up an old ride in Strava (premium) and see the knee of the curve and visually estimate ftp.
1 Like
Well, but the fact is you did it… you rode that power for that long. so unless ai ftp doesn’t believe you… your ftp is de facto higher than what it gave you. Just the actual current data.
That’s wrong. it’s wrong, unless you road at 105.5% of your FTP for 30 minutes. (which maybe you did). :D. My point is, it doesn’t matter if it looked back to the beginning of time. YESTERDAY you did a thing that invalidates its prediction. It should change its mind.
1 Like
ftp tte can be as low as 30-35mins, so it wouldn’t be too outlandish to use 323 as ftp, you’d just begin a threshold progression at 3x10 and go from there
5 Likes
I agree! I was surprised by the 306 ftp, but definitely agree it’s an estimate that I proved wrong. During the ride I could feel that 320 + felt high and around 310± felt right for ftp setting.
I don’t know how to play with intervals to well, when I look at the ride it breaks everything down in intervals. I don’t know why when I hit the lap button at the start and finish.
At the bottom of the page showing your ride data, click on “Actions” and choose “Use laps.”
1 Like
Within the context of a “one off” testing protocol, I’m not disagreeing with you, and let me preface my next statement by saying I haven’t read through this ENTIRE thread, but I think it’s unfair to try and compare systems that likely don’t work in the same way… in this case “one off” tests vs AI FTPD… they simply don’t work the same way… as I mentioned before, AFAIK AI FTPD works off a series of data points… so if a user provides it the following data…
30m @ 323w
30m @ 285w
30m @ 290w
30m @ 310w
etc… i wouldn’t be at all surprised that AI FTPD spit out a much lower value than expected… HOWEVER, if a user gave it a series of data points that was much more CONSISTENT…
30m @ 323w
30m @ 319w
30m @ 322w
30m @ 325w
etc… I would then expect AI FTPD to spit out a MUCH CLOSER value due to the consistency in the repeatable data it was fed…
Remember what TR folks always talk about… consistency… if athletes consistently hit power targets in each workout, over time AI FTPD will dial the athlete in to where they need to be…
A challenge to @ChefAcB, if you feel your FTP is closer to what intervals and/or strava gave you (and you weren’t simply having a GREAT testing day during your 30m effort), manually enter that FTP value into TR and use it for your base phase… if you can consistently hit the power targets it provides for each session and not fail workouts, the next time you run AI FTPD, it won’t be 306 anymore…
1 Like
This is such a great point. Let’s say for the sake of argument that you have half a dozen GREAT days a year when the stars align and you’re the very best version of yourself.
Do you really want to hold yourself to that standard for the other 360 days of the year?
1 Like
I don’t think AIFTP takes an average. We don’t know how it works, but it’s not algorithmic and it’s not looking at mean maximal efforts, but they must go into the calculation. It’s also unclear what duration it’s meant to represent.
323 doesn’t mean you could hold 323 for 60 minutes, it means you can hold it for 30 minutes. Your 60 minute MMP could be 306. Depends on your power curve. Maybe TR is picking up a high anaerobic component. If you’re using TR, why not use 306? If the workouts are easy, TR should suggest harder ones.
I wasn’t trying to imply that AI FTPD takes an average, just that feeding the machine consistent data (over a period of time… whatever that period may be) is likely to produce a more accurate result.
Like you said, we don’t know how IT works, but we also shouldn’t be be surprised by the value it suggests based upon the results of ONE data point, which is where the crux of my argument began.
We shouldn’t be comparing various testing protocols vs AI FTPD… IMHO, that’s like comparing apples to bananas.
2 Likes
This is where Coggan would come in and say PPP or something like that. “The best predictor of performance is performance itself”
I get what you’re saying, my Ai ftp 4 weeks ago was 316 and since I have done less volume and took a week and a half easy. It thinks my ftp dropped, I thought it did too. I have no problem lowering it if I fail workouts.
This past effort I beat out my 20 minute power from a month ago and was 2 watts under my all time best 30 minute power. Maybe I needed the rest and my fitness is expressing itself.
I think it’s interesting why it’s lower compared to when it’s normally the higher estimate.
It could have been a great day and vibes were high because I was excited to go hard. I’ll find out in the next month when I use the 315 “estimate”.
1 Like
Is he related to Coggan?
1 Like
We do know the basics of how it works:
And I listened to the podcast where Nate provided a few more high level details. I’m paraphrasing and oversimplifying, but it’s pretty straightforward and I could build a model having dabbled in modeling and machine learning since the early 1990s (learned it from 3 Stanford PhDs and an IEEE Fellow) 
Not saying my programming skills are up to snuff for production quality code…. I’m a sales engineer not an actual engineer.