# Anyone field testing the AI FTP number?

**URL:** <https://www.trainerroad.com/forum/t/anyone-field-testing-the-ai-ftp-number/111542>\
**Category:** Uncategorized\
**Created:** [February 28, 2026, 3:59am UTC](https://www.trainerroad.com/forum/t/anyone-field-testing-the-ai-ftp-number/111542 "2026-02-28T03:59:37Z")\
**Posts on this page:** 20\
**Page:** 4

<div class="post-metadata">

**Author:** ![JoeX](https://sea2.discourse-cdn.com/trainerroad/forum/user_avatar/www.trainerroad.com/joex/32/6640_2.png) [@JoeX](https://www.trainerroad.com/forum/u/JoeX)\
**Post date:** [March 3, 2026, 8:56am UTC](https://www.trainerroad.com/forum/t/anyone-field-testing-the-ai-ftp-number/111542/62 "2026-03-03T08:56:03Z")

</div>

> [@timon](#):
>
> I’d like to think my 10+ years of interval training and 10k+ miles on the bike every year for a decade count for something.

Of course they do.

Do they mean that you, and more importantly everyone, can intuit your/their FTP on any given day? Accurately? No, I won’t accept that without evidence.

I’m 13yrs in training, when I’m fit I’d expect my ftp to be around 250-260. But that could easily be ten watts more or less. And I’ve used the same meters for seven years, unlike most.

> [@timon](#):
>
> all I’ve heard on their podcast since it’s inception is that your easy days should be easy so that your hard days can be hard.

I don’t see the connection between this and zoning systems that you do. If a prescribed day (series of days/training plan) at X watts makes you faster, then it makes you faster. Whether that can be translated into OldSpeak or inherently vague terms like “Zone 2” really doesn’t matter.

Your underlying question of whether it _really does_ make you faster is valid.

But not the zoning stuff. IMHO.

---

<div class="post-metadata">

**Author:** ![OreoCookie](https://sea2.discourse-cdn.com/trainerroad/forum/user_avatar/www.trainerroad.com/oreocookie/32/8298_2.png) [@OreoCookie](https://www.trainerroad.com/forum/u/OreoCookie)\
**Post date:** [March 3, 2026, 9:59am UTC](https://www.trainerroad.com/forum/t/anyone-field-testing-the-ai-ftp-number/111542/63 "2026-03-03T09:59:36Z")

</div>

> [@JoeX](#):
>
> I don’t see the connection between this and zoning systems that you do. If a prescribed day (series of days/training plan) at X watts makes you faster, then it makes you faster. Whether that can be translated into OldSpeak or inherently vague terms like “Zone 2” really doesn’t matter.

It also forgets one important fact: at least if you stay within the TR ecosystem, since AI FTP works with absolute power (as opposed to fractions of your “FTP”), the system should prescribe the right workouts for you.

TR’s database is huge, much better than anything researchers at a university can come up with. So TR’s solution have the potential to uncover and exploit relationships that are beyond reach for coaches and exercise physiologists.

That could lead to some breaks with orthodoxy and “established truths”. Hence, concepts like zones need not coincide with the definitions Coggan and the early contributors to power-based training came up with.

Overall, what I would look at is whether TR AI represents an improvement, i. e. whether it works better.

---

<div class="post-metadata">

**Author:** ![Rad-ler](https://avatars.discourse-cdn.com/v4/letter/r/7ea924/32.png) [@Rad-ler](https://www.trainerroad.com/forum/u/Rad-ler)\
**Post date:** [March 3, 2026, 1:43pm UTC](https://www.trainerroad.com/forum/t/anyone-field-testing-the-ai-ftp-number/111542/64 "2026-03-03T13:43:00Z")

</div>

> [@OreoCookie](#):
>
> he did agree that maximal 20-minute power minus 5 % is a viable way to estimate MLSS power — on average.

> [@OreoCookie](#):
>
> That’s why I wrote AI FTP has the potential of being a much better way to gauge FTP than any test protocol.

The funny thing is that the estimated 20/60min values coming from TR (only a few data points available) are ~105% of AIFTP for 20min and ~95% for 60min. There were some outliers but that’s the ballpark. Which means that they didn‘t reinvent the wheel in this case.

---

<div class="post-metadata">

**Author:** ![BenB](https://sea2.discourse-cdn.com/trainerroad/forum/user_avatar/www.trainerroad.com/benb/32/7721_2.png) [@BenB](https://www.trainerroad.com/forum/u/BenB)\
**Post date:** [March 3, 2026, 5:31pm UTC](https://www.trainerroad.com/forum/t/anyone-field-testing-the-ai-ftp-number/111542/65 "2026-03-03T17:31:31Z")

</div>

> [@timon](#):
>
> Jesse Coyle did a youtube on it and iirc his AI ftp was 10 watts higher than his all-time best 60m power.

Nate did a write-up on this, but being within the margin of power meter accuracy, it seems like TR got his FTP pretty close to me.

> [@Is Your FTP Number Actually Real? | Cycling Coach Reacts](https://www.trainerroad.com/forum/t/is-your-ftp-number-actually-real-cycling-coach-reacts/111096/36):
>
> We’re releasing a podcast soon (I think today) that goes over this a bit. This was before I saw this video. I’d love to have Jesse on our podcast and talk to him about this. I’m going to: Share his hour power he mentioned in the video Show what kind of workouts he’d get in TrainerRoad today Then we can decide if our AI is whacky or not. First note: Jesse has zero TrainerRoad rides, no RPE rating, and doesn’t wear a heart rate monitor. (HR monitor improves AI Accuracy) Here’s his hour po…

---

<div class="post-metadata">

**Author:** ![timon](https://sea2.discourse-cdn.com/trainerroad/forum/user_avatar/www.trainerroad.com/timon/32/12895_2.png) [@timon](https://www.trainerroad.com/forum/u/timon)\
**Post date:** [March 3, 2026, 7:54pm UTC](https://www.trainerroad.com/forum/t/anyone-field-testing-the-ai-ftp-number/111542/66 "2026-03-03T19:54:13Z")

</div>

> [@BenB](#):
>
> Nate did a write-up on this, but being within the margin of power meter accuracy, it seems like TR got his FTP pretty close to me.

Unless his power meter was reading _high_ in his own 1hr tests.

---

<div class="post-metadata">

**Author:** ![BenB](https://sea2.discourse-cdn.com/trainerroad/forum/user_avatar/www.trainerroad.com/benb/32/7721_2.png) [@BenB](https://www.trainerroad.com/forum/u/BenB)\
**Post date:** [March 3, 2026, 8:01pm UTC](https://www.trainerroad.com/forum/t/anyone-field-testing-the-ai-ftp-number/111542/67 "2026-03-03T20:01:02Z")

</div>

That’s true, but my comment was meant to be about 3% off of a “true” FTP is pretty close. Especially with all the caveats around if that was an actual max effort (pacing, nutrition, previous days’ workouts, cooling, motiviation, etc.)

---

<div class="post-metadata">

**Author:** ![timon](https://sea2.discourse-cdn.com/trainerroad/forum/user_avatar/www.trainerroad.com/timon/32/12895_2.png) [@timon](https://www.trainerroad.com/forum/u/timon)\
**Post date:** [March 3, 2026, 8:35pm UTC](https://www.trainerroad.com/forum/t/anyone-field-testing-the-ai-ftp-number/111542/68 "2026-03-03T20:35:56Z")

</div>

> [@JoeX](#):
>
> Do they mean that you, and more importantly everyone, can intuit your/their FTP on any given day? Accurately? No, I won’t accept that without evidence.

I would say my evidence is specifically the past 7 years of training on TR. Dating back to the OG SSBHV plans and the ramp test protocols and through the og AI FTP detection my FTP has consistently come out of the offseason in October/November around 370 or so and increased to 400-408 by February/March. Typically I’m doing level 7-8 sweet spot workouts and 4-5 threshold workouts at that FTP. Without going down to sea level there’s been no evidence I can do more than 405-410 for 30+ mins at any point in my life. In March/April I either hit my genetic ceiling, I get sick and lose 10-15 watts of fitness and then race with what I can get back….and the temps warm and I struggle with cooling and hitting those same numbers when it’s 80+ degrees, or I use that fitness on ultra endurance stuff and tend to lose the interval consistency that got me to that point, or some combo of all that.

This year I’ve stuck to the same script and followed my plan fairly well and been as consistent as past years, and TRs telling me at 40 years old I’m 20 watts better than my all-time bests at the same time in the year?? Their reasoning is that the “scale\* is now more accurate. So that means it was 20 watts off before? I was undertraining that whole time, despite running a 130 CTL? I underperformed at every ramp test? Their AI ftp detection was always off? I should’ve been doing Tallac +3 at 390 instead of 370? Sorry if I don’t buy it without any evidence except “trust the AI, it has lots of data”. My evidence says my all time best up my local climb is 435 for 12 minutes, and now being way older, I’m supposed to believe without evidence I can do 428 for an amount of time that would justify it being called an FTP?

What are we doing here?

---

<div class="post-metadata">

**Author:** ![Bioteknik](https://sea2.discourse-cdn.com/trainerroad/forum/user_avatar/www.trainerroad.com/bioteknik/32/7721_2.png) [@Bioteknik](https://www.trainerroad.com/forum/u/Bioteknik)\
**Post date:** [March 4, 2026, 3:01pm UTC](https://www.trainerroad.com/forum/t/anyone-field-testing-the-ai-ftp-number/111542/70 "2026-03-04T15:01:11Z")

</div>

> 

You should care about zones as they are supposed to target different physiological responses. The error is only setting them based on ftp.

This is where the ai workouts and tr in general is missing the boat. They always want to push power up instead of focusing on increasing time in zone.

---

<div class="post-metadata">

**Author:** ![timon](https://sea2.discourse-cdn.com/trainerroad/forum/user_avatar/www.trainerroad.com/timon/32/12895_2.png) [@timon](https://www.trainerroad.com/forum/u/timon)\
**Post date:** [March 4, 2026, 4:59pm UTC](https://www.trainerroad.com/forum/t/anyone-field-testing-the-ai-ftp-number/111542/71 "2026-03-04T16:59:36Z")

</div>

> [@mrtopher1980](#):
>
> I know that isn’t your entire point but you seem to be thinking that you are older and can’t possibly beat your younger self.

No, what I’m saying is there’s little evidence for that. I’d love to be fitter and maybe I am a little but, but not enough to justify 428, as I keep saying. If I was doing the same workouts now at 20+ watts higher, then that would be evidence. And maybe I should go replicate a week of what I did years ago at higher wattage and see what happens.

Here’s examples from spring of 2022:

 ![Screenshot_20260304-082102](https://global.discourse-cdn.com/trainerroad/original/3X/0/0/00a1909cef9bbb0930a62adbd660df8303a6cff7.png)

 ![Screenshot_20260304-084232](https://global.discourse-cdn.com/trainerroad/original/3X/e/2/e260836ccb5d22d745fa0143b3a1a6ccf6aa68c8.png)

 ![Screenshot_20260304-082335](https://global.discourse-cdn.com/trainerroad/original/3X/d/6/d6cac3ba4052878360410cb5388960d3d3bf1f04.png)

Here’s 2026 from the weeks preceding an AI FTP bump to 420 (and then shortly followed by 428 because it re-prompted after a few completed workouts)

 ![Screenshot_20260304-083916](https://global.discourse-cdn.com/trainerroad/original/3X/3/c/3c6b7a02ff64034ea6dd5b51b06f83cb54e57775.png)

 ![Screenshot_20260304-083834](https://global.discourse-cdn.com/trainerroad/original/3X/e/f/ef9dbcc3c1ec9fe7e381139525378a3cf9fc5bdc.png)

 ![Screenshot_20260304-083740](https://global.discourse-cdn.com/trainerroad/original/3X/9/3/9375a3a930d9e4c769e54fb924c6b281de262fdd.png)

 ![Screenshot_20260304-091811](https://global.discourse-cdn.com/trainerroad/original/3X/4/3/43ac5b8b1f7d128bf1ebbccd21c07fe5c490eb2f.png)

To me those look like someone with very similar fitness. At least within the margin of power meter/kickr core error 😉. It’s similar workout levels, similar RPE, similar power/np. To TR AI that’s a 4% difference. I don’t think either one is capable of pushing 420+ for a time duration that would justify calling it an FTP.

> [@mrtopher1980](#):
>
> Unless you were training the same and as diligently as you are now then it is very possible you will. I trained harder at swimming in my 30s than I did in HS and was approaching my HS times in the pool because I was better at training despite being 15 years older.

As a former triathlete that’d consistently get his ass kicked by much older men and women at masters swim, I know firsthand that swimming is as much technique as it is fitness. Not saying you are, but you can be less fit and be faster by moving through the water better with better technique. On a bike, watts are watts are watts.

---

<div class="post-metadata">

**Author:** ![JoeX](https://sea2.discourse-cdn.com/trainerroad/forum/user_avatar/www.trainerroad.com/joex/32/6640_2.png) [@JoeX](https://www.trainerroad.com/forum/u/JoeX)\
**Post date:** [March 4, 2026, 5:56pm UTC](https://www.trainerroad.com/forum/t/anyone-field-testing-the-ai-ftp-number/111542/72 "2026-03-04T17:56:40Z")

</div>

> [@Bioteknik](#):
>
> You should care about zones as they are supposed to target different physiological responses.

I accept the point you’re making, but. And I’m not suggest AI is doing this now, as plans determine zones.

Yet, if ML find your path optimal to improve is some thing weird like three anaerobic a week, should it be constrained by a zoning system?

---

<div class="post-metadata">

**Author:** ![BCM](https://sea2.discourse-cdn.com/trainerroad/forum/user_avatar/www.trainerroad.com/bcm/32/137631_2.png) [@BCM](https://www.trainerroad.com/forum/u/BCM)\
**Post date:** [March 4, 2026, 6:00pm UTC](https://www.trainerroad.com/forum/t/anyone-field-testing-the-ai-ftp-number/111542/73 "2026-03-04T18:00:19Z")

</div>

> [@JoeX](#):
>
> Yet, if ML find your path optimal to improve is some thing weird like three anaerobic a week, should it be constrained by a zoning system?

No, but it shouldn’t call it Anaerobic if it’s VO2. Or call it VO2 if it’s Threshold. Or Call it Endurance if it’s Tempo. Or call it an Over-Under if it’s Supra-Threshold.

This isn’t the way it’s working for everyone, but it is the way it’s working for some people. And there’s a time and a place for each zone.

---

<div class="post-metadata">

**Author:** ![JoeX](https://sea2.discourse-cdn.com/trainerroad/forum/user_avatar/www.trainerroad.com/joex/32/6640_2.png) [@JoeX](https://www.trainerroad.com/forum/u/JoeX)\
**Post date:** [March 4, 2026, 6:03pm UTC](https://www.trainerroad.com/forum/t/anyone-field-testing-the-ai-ftp-number/111542/74 "2026-03-04T18:03:03Z")

</div>

> [@BCM](#):
>
> it shouldn’t call it Anaerobic if it’s VO2

Fair

---

<div class="post-metadata">

**Author:** ![LarB](https://sea2.discourse-cdn.com/trainerroad/forum/user_avatar/www.trainerroad.com/larb/32/11720_2.png) [@LarB](https://www.trainerroad.com/forum/u/LarB)\
**Post date:** [March 4, 2026, 10:11pm UTC](https://www.trainerroad.com/forum/t/anyone-field-testing-the-ai-ftp-number/111542/75 "2026-03-04T22:11:50Z")

</div>

I did used Critical Power testing the beginning of December, and a Zwift 20 minute test and both provided the same FTP number. I trained through January and then restarted my TR subscription and the AI gave me an increase of one whole watt. Following the plan set by TR AI I would say it was accurate, and the increase I got a week ago seems to bear that out.

So far the start to this training plan has felt more challenging yet more successful than the past. It will not be perfect, but it feels like the company is very much on the right track with this.

---

<div class="post-metadata">

**Author:** ![derearte](https://sea2.discourse-cdn.com/trainerroad/forum/user_avatar/www.trainerroad.com/derearte/32/132170_2.png) [@derearte](https://www.trainerroad.com/forum/u/derearte)\
**Post date:** [March 4, 2026, 11:31pm UTC](https://www.trainerroad.com/forum/t/anyone-field-testing-the-ai-ftp-number/111542/76 "2026-03-04T23:31:08Z")

</div>

My experience with this new AI tool:

Before this major update, AI FTP Detection estimated my FTP at **247 W**. After the update, just a few days later, a new AI detection set my FTP to **212 W**.

How is that possible? Three days ago it was reported as **247 W** , and now after huge update it’s **212 W**.

That’s a **35-watt drop** — this is not a small fluctuation. It’s hard to take this result seriously.

---

<div class="post-metadata">

**Author:** ![Trix8806](https://sea2.discourse-cdn.com/trainerroad/forum/user_avatar/www.trainerroad.com/trix8806/32/155132_2.png) [@Trix8806](https://www.trainerroad.com/forum/u/Trix8806)\
**Post date:** [March 5, 2026, 12:53am UTC](https://www.trainerroad.com/forum/t/anyone-field-testing-the-ai-ftp-number/111542/77 "2026-03-05T00:53:29Z")

</div>

Can you take some photos of your calendar for the last 3-4 weeks and post up?

---

<div class="post-metadata">

**Author:** ![GravelSteve](https://sea2.discourse-cdn.com/trainerroad/forum/user_avatar/www.trainerroad.com/gravelsteve/32/7725_2.png) [@GravelSteve](https://www.trainerroad.com/forum/u/GravelSteve)\
**Post date:** [March 5, 2026, 9:48am UTC](https://www.trainerroad.com/forum/t/anyone-field-testing-the-ai-ftp-number/111542/78 "2026-03-05T09:48:09Z")

</div>

> [@derearte](#):
>
> How is that possible? Three days ago it was reported as **247 W** , and now after huge update it’s **212 W**.

Nothing about your fitness changed, only the wattages at which the system thinks you should train with to get faster.

Which number do you think is better for training? Is 247 believable for you?

---

<div class="post-metadata">

**Author:** ![Bioteknik](https://sea2.discourse-cdn.com/trainerroad/forum/user_avatar/www.trainerroad.com/bioteknik/32/7721_2.png) [@Bioteknik](https://www.trainerroad.com/forum/u/Bioteknik)\
**Post date:** [March 5, 2026, 9:58am UTC](https://www.trainerroad.com/forum/t/anyone-field-testing-the-ai-ftp-number/111542/79 "2026-03-05T09:58:13Z")

</div>

> [@JoeX](#):
>
> I accept the point you’re making, but. And I’m not suggest AI is doing this now, as plans determine zones.
> 
> Yet, if ML find your path optimal to improve is some thing weird like three anaerobic a week, should it be constrained by a zoning system?

It depends, their ai engine might be boosting “ftp” while simultaneously killing your tte. The fastest way to improve fitness doesn’t necessarily translate in to race day performance. Tr likes to push sweet spot work in to threshold, which will end up with a different physiological response.

I’ve actuality been using Gemini to help me build and interpret my previous fitness gains and race results.

I haven’t verified ftp for a bit since I’m still working back in to consistency after having another kid at 45, but the ai ftp is usually within 5 watts of my manually set ftp so I never accept the updated number. It seems silly to update the number in the middle of a block.

---

<div class="post-metadata">

**Author:** ![JoeX](https://sea2.discourse-cdn.com/trainerroad/forum/user_avatar/www.trainerroad.com/joex/32/6640_2.png) [@JoeX](https://www.trainerroad.com/forum/u/JoeX)\
**Post date:** [March 5, 2026, 10:24am UTC](https://www.trainerroad.com/forum/t/anyone-field-testing-the-ai-ftp-number/111542/80 "2026-03-05T10:24:20Z")

</div>

> [@Bioteknik](#):
>
> depends, their ai engine might be boosting “ftp” while simultaneously killing your tte.

I can’t accept this TTE didn’t exist in isolation like that, FTP/MLSS is a good enough proxy for cycling fitness.

> [@Bioteknik](#):
>
> the ai ftp is usually within 5 watts of my manually set ftp so I never accept the updated number. It seems silly to update the number in the middle of a block

I think that’s just pandering to TSS trackers 🙂 , there is surely no justification to ignoring fitness gains during a training block - whatever you perceive a block to be.

Not that FTP really matters in this sense, for this paradigm!

---

<div class="post-metadata">

**Author:** ![BCM](https://sea2.discourse-cdn.com/trainerroad/forum/user_avatar/www.trainerroad.com/bcm/32/137631_2.png) [@BCM](https://www.trainerroad.com/forum/u/BCM)\
**Post date:** [March 5, 2026, 12:21pm UTC](https://www.trainerroad.com/forum/t/anyone-field-testing-the-ai-ftp-number/111542/81 "2026-03-05T12:21:54Z")

</div>

> [@JoeX](#):
>
> I think that’s just pandering to TSS trackers 🙂 , there is surely no justification to ignoring fitness gains during a training block - whatever you perceive a block to be.

Sorry - this is just not broadly true. While TTE doesn’t exist in isolation, neither does FTP.

First - FTP does not equal fitness. You can have a higher FTP and be way slower because of how you train (within reason of course.)

For people who are relatively untrained or still new to structured training, sure it works better, but there are absolutely scenarios and events where it’s beneficial to pretty much ignore FTP gains from a point and focus on extending TTE and durability because of the demands of the specific event.

---

<div class="post-metadata">

**Author:** ![JoeX](https://sea2.discourse-cdn.com/trainerroad/forum/user_avatar/www.trainerroad.com/joex/32/6640_2.png) [@JoeX](https://www.trainerroad.com/forum/u/JoeX)\
**Post date:** [March 5, 2026, 2:52pm UTC](https://www.trainerroad.com/forum/t/anyone-field-testing-the-ai-ftp-number/111542/82 "2026-03-05T14:52:46Z")

</div>

You haven’t countered my (misquoted) points and I think you’ve argued yourself into a corner there 🙂

The new AI is finding paths to better performance. You’re trying to argue for the same thing.

[Previous page](https://www.trainerroad.com/forum/t/anyone-field-testing-the-ai-ftp-number/111542.md?page=3)

[Next page](https://www.trainerroad.com/forum/t/anyone-field-testing-the-ai-ftp-number/111542.md?page=5)
