Have more questions? Contact support.

How to Use AI FTP Detection

Tired of stressing about FTP testing? So were we. AI FTP Detection allows you to skip testing entirely! With AI FTP Detection, you're presented an option to predict your current FTP instead of performing a scheduled Ramp Test.

Note: AI FTP Detection currently works with Ramp Tests only. We will support 8- and 20-Minute Tests in the future.

How does AI FTP Detection work?

We've used Machine Learning - a subset of Artificial Intelligence - against millions of rides to understand FTP based on a multitude of factors. Our system looks at tons of dimensions of your recent and past training data to understand your most likely FTP if you were going to take an FTP test that day.

How to Enable FTP Detection

AI FTP Detection can be enabled from the Early Access section of Account Settings on the TrainerRoad website.

Step 1. Log into the TrainerRoad website

Step 2. Access Account then Early Access from the navigation menu

Step 3. Under AI FTP Detection, select Enabled

Step 4. Proceed to the apps to use FTP Detection

Screen_Shot_2022-02-08_at_5.15.14_PM.png

How to Use AI FTP Detection

First things first, we need data. To replace a Ramp Test with your AI detected FTP, we require a minimum of 12 TrainerRoad rides or imported outside rides with power. Set up Ride Sync with Garmin Connect or Strava to import outside rides.

If you don't have 12 rides or imported rides, don't stress. You can still enable the feature in Early Access, and FTP Detection will automatically become available once 12 TR rides are completed. The option to "Use FTP Detection" will appear on the Career page of the app whenever a Ramp Test is your next scheduled workout.

Note: AI FTP Detection is currently only available from the Career section within the apps at this time. We currently won't detect a new FTP from the Calendar or from the website.

FTP Detection on Mobile Apps

Step 1. Enable Early Access for AI FTP Detection and make sure you're on the latest version of the TrainerRoad app

Step 2. Make sure a Ramp Test is your next scheduled workout

Step 3. Access the Career section of the app

Step 4. Select Use FTP Detection to be presented your new FTP

Two situations may prevent us from detecting your FTP:

  1. Your data may still be processing. If so, close and relaunch the app after a minute.

  2. Your FTP has changed within 14 days. To use FTP Detection, you need to wait at least 14 days after the last change to your FTP.

IMG_1505.PNG

Step 4. Select Accept to use the new FTP. If your FTP has increased, your Progression Levels may decrease. Check out the following article for more information: Why did my Progression Levels Adjust after an FTP change?

If you accept your newly detected FTP, your workout will now be replaced with Goddard -4. Once you complete or skip the replacement workout, we will check for new adaptations based on your adjusted Progression Levels.

IMG_1506.PNG

FTP Detection on Desktop Apps

Step 1. Enable Early Access for AI FTP Detection and make sure you're on the latest version of the TrainerRoad app

Step 2. Make sure a Ramp Test is your next scheduled workout

Step 3. Access the Career section of the app

Step 4. Select Use FTP Detection to be presented your new FTP

Two situations may prevent us from detecting your FTP:

  1. Your data may still be processing. If so, close and relaunch the app after a minute.

  2. Your FTP has changed within 14 days. To use FTP Detection, you need to wait at least 14 days after the last change to your FTP.

Screen_Shot_2022-02-08_at_4.42.34_PM.png

Step 4. Select Accept to use the new FTP. If your FTP has increased, your Progression Levels may decrease. Check out the following article for more information: Why did my Progression Levels Adjust after an FTP change?

If you accept your newly detected FTP, your workout will now be replaced with Goddard -4. Once you complete or skip the replacement workout, we will check for new adaptations based on your adjusted Progression Levels.

Screen_Shot_2022-02-08_at_4.42.47_PM.png

FTP Detection on the Website

AI FTP Detection is currently only supported in the apps. We will add this to the TrainerRoad website in the future.

FAQ

How should I validate my AI Detected FTP?

You'll know your AI Detected FTP is properly set by being able to successfully complete Productive workouts. If that's not the case, we want to hear about it.

I get FTP updates on other platforms. What makes this any different from what I see elsewhere?

Most other platforms use what we call capacitive efforts to estimate your FTP using an FTP estimation model 1. This means that they rely on you completing all-out efforts within your training data.

For example, if you had a very hard 20-minute climb during a ride (ridden at ~ 105% or greater of current FTP), they might use that effort to estimate a higher FTP. Our model does not rely on capacitive efforts. Instead, our model predicts your FTP based on your training history and your personal biometrics, and many other features. Capacitive efforts and FTP tests rely on one performance. AI FTP Detection accounts for much more with a broad range of data points.

1: ie Monod Scherrer 2 Parameter CP,Morton's 3 Parameter CP

Will AI FTP Detection consider unstructured outside rides as well?

Yes. AI FTP Detection takes into account all rides with power data.

TrainerRoad has always encouraged the Ramp Test to assess fitness. What has changed?

We know that testing (assessing) can be stressful, and because we like constant improvement, we’ve been hard at work devising a better way. Testing works, but it does rely on a bell curve for calculating FTP.

Testing can also be more difficult for some than others. We want to offer a more personalized alternative to testing. We still think the Ramp Test is a great way to assess your fitness, but if you’d rather not do the Ramp Test, you can now use our AI FTP Detection tool instead.

Do I need to use a heart rate monitor to get an accurate FTP Prediction?

Nope! All you need is consistent structured training with a power meter or VirtualPower.

I use a different power meter for my outdoor rides than for my indoor rides. How will FTP Prediction handle any differences between my two power meters?

This is one of the benefits of using a model as opposed to using an estimate. We don’t simply estimate your FTP based on outdoor power data (which is often reads higher than indoors). Instead, we include your outdoor power data in addition to the various data points we already have to predict your FTP

Where can I provide feedback on my experience with the Early Access version of the FTP Prediction tool?

We have a dedicated thread on the forum [link to thread], and you may see a survey from us. We appreciate hearing how we can improve the feature, and we also love to hear what you enjoy about it!

Does trainer mode affect accuracy of your AI Detected FTP?

No. Trainer mode won't affect the accuracy of your AI Detected FTP

Is there a way to revert to my previous FTP after accepting the AI Detected FTP?

Yes. You can access your FTP History from the website and delete the AI Detected FTP entry.

My AI FTP Detected FTP doesn't seem right. Where should I provide feedback?

Please submit feedback from the Early Access web page. Select the Leave Feedback icon under the AI FTP Detection feature. 

I don't see the option to Detect FTP

Make sure you're on the latest version of the TrainerRoad app, and that you've followed all these instructions. If you're still not seeing the option to detect FTP on a Ramp Test, please contact Support@TrainerRoad.com

Is AI FTP Detection better than a typical FTP test?

All FTP tests have their pros and their cons. Regardless of the testing protocol, it is extremely difficult to reliably control all factors that can influence the resulting training benchmark, like weather, sleep, stress, equipment, and more. The Ramp Test uses lab-based protocols to maximize efficacy and repeatability while minimizing stress. Even so, stress plays an enormous role in testing. Instead, AI FTP Detection delivers a custom-calibrated training benchmark without the stress, and allows you to complete a focused workout that advances your fitness.

Isn’t AI FTP Detection just making training easier, and is that not the point of training?

A typical FTP test requires an all-out effort, but due to short durations, these tests don’t generally contribute as much focused, progressive training stress as would the right workout. By using AI FTP Detection, you can do a full, focused workout instead of a stressful, less productive effort.

What does AI FTP Detection look at to detect my FTP? What types of efforts or workouts does AI FTP Detection consider?

AI FTP Detection looks at your training history and your biometrics to detect your FTP. Because AI FTP Detection considers so much of your training data, it’s very unlikely a single type of effort or workout would substantially sway the model. You don’t have to do capacitive or all-out efforts for the feature to work. In fact, it works if you only do sweet spot or aerobic riding!

Does TrainerRoad recommend I use AI FTP Detection or do an FTP test?

AI FTP Detection delivers the training benchmarks you need to progress your fitness and allows you to complete a productive workout in place of testing. Because AI FTP Detection gives you productive training stress without the unnecessary psychological stress of an FTP test, we recommend using AI FTP Detection. That said, you always have the option to test.

Will AI FTP Detection detect my FTP if I’ve never used TrainerRoad?

If you use Ride Sync to upload rides with power data, AI FTP Detection can work for you. If you have no ride history at all, you can enable AI FTP Detection, and it will automatically become available after you’ve completed 12 workouts.

How can AI FTP Detection be accurate if I'm just coming back from an offseason or more than one week off the bike?

AI FTP Detection was trained on an enormous data set and can predict decreases in FTP even after long (weeks to months) training interruptions.

Is AI FTP Detection just looking at what athletes generally gain in FTP after each block and basing the model on that?

No, we are not estimating FTP based on any static equation. AI FTP Detection uses a model trained on our data set to predict your FTP based on your data.

Can I disable this option? I prefer to keep doing Ramp Tests.

Yes. In fact, for now, you need to opt-in to use this feature. If you do not opt-in, your scheduled Ramp Tests will look and function exactly the same as usual.

If I don’t feel like the AI FTP Detection was accurate, will AT adjust accordingly anyways once I start doing workouts?

Yes! Adaptive Training will suggest appropriate adaptations based on how your subsequent workouts go. If you’re over-performing after accepting your detected FTP, Adaptive Training will advance your Progression Levels faster. If you’re struggling with the new FTP, it will suggest workouts with lower levels. All of this will feed into the AI FTP Detection model to improve future suggested FTP values for you.

    Was this article helpful?
    2 out of 2 found this helpful

    Still have questions? Our support experts are here to help. Send us a message and we'll help get you back to training!