Did I miss something or did the group workout feature get removed with this new update?
3 Likes
Obviously isn’t going to have the details of the 3 hours worth of podcasts, but have you seen this? It’s a good primer. Introducing TrainerRoad AI - TrainerRoad Blog
It was removed but is on the list of items being worked on.
How does this apply to long intervals, e.g. if you do 2x30 sweetspot, and it was reasonably comfortable (except for maybe the last 5 minutes), but you maybe couldn’t do a whole extra 30, how should you rate that?
1 Like
Where do I find the training approach feature in the TR app?
I can’t remember who posted it but here it is..
Key Changes in the Release
• Simulation & Prediction Engine: The AI runs hundreds of simulations to predict how a workout will affect you in the future. It can forecast your fitness (FTP) and fatigue up to 28 days out.
• Raw Data Analysis: The AI now looks at raw power and heart rate data directly rather than relying solely on “Workout Levels” or “Zones” to understand your fitness.
• Predictive Fatigue Detection: It forecasts “red days” (high fatigue) before they happen. If you do a hard unplanned ride, it recalculates your future fatigue and may suggest a rest day to prevent burnout before you crack.
• Dynamic Endurance: You can set time caps (e.g., “I only have 2 hours”) and the AI will scale the difficulty and duration of your endurance rides to fit while ensuring progression.
- Benefits for the User
• Reduced “Failed” Workouts: The new engine is 70% more likely to pick the “right” workout intensity than a human coach or the old algorithm.
• Vision of the Future: The predicted FTP graph for the next month offers massive motivation; you can see how training consistency changes your future fitness number.
- Handling Non-TrainerRoad Rides (Outdoor / Zwift)
This is the most significant improvement for hybrid training.
• Automatic Ingestion: When you record a ride on a Garmin/Wahoo (outdoors) or Zwift (indoors) and it syncs to TrainerRoad, the AI analyzes the raw file.
• Fatigue & Fitness Impact: It immediately calculates how that effort impacted your fatigue and fitness.
• Immediate Adaptation: If the AI detects high training load from a raw file, it will automatically lower the intensity of upcoming workouts or suggest a rest day.
• No Manual Matching: You no longer need to manually “associate” an outdoor ride with a TR workout to get credit; the system “sees” the work through the raw data.
- How Progression Levels (PLs) Work Now
Progression Levels have shifted from being the driver of your plan to being a visualization of your fitness.
• “Leveling Up” via Raw Data: The AI analyzes the raw power duration curve of every ride. If a 15-minute effort on an outdoor climb is equivalent to a “Level 5.8 Threshold” interval, your PL updates automatically.
• Resultant, Not Prescriptive: The AI predicts your fitness daily. PLs reflect your current capability based on these predictions rather than just a rigid staircase of workouts.
• Sub-Zone Recognition: The engine recognizes “accidental” work. A long Zone 2 ride with steep hill sprints will update both your Endurance PL and your VO2 Max PL.
• Scoreboard: Progression Levels now act as a holistic scoreboard for all your cycling, not just indoor intervals. You can see your strengths and weaknesses across all riding.
2 Likes
Go to calendar and at the top where it says Balanced/Moderate/etc you can tap on it and change it.
2 Likes
And not impact FTP aI/ red light? Otherwise, would the plus and minus button for intensity work for this?
Personally I’d rate it ‘hard’. I can see how others might got for moderate; there is no ‘right’ answer, what’s important is that you’re individually consistent in your responses.
To me that sounds like the last 2 bullets under “moderate”. If you’re still on the fence though, I would ask myself if I wanted it to respond more or less aggressively for upcoming workouts and choose that way.
2 Likes
thank you for pointing that to me! I ignored it when I originally clicked on it because I thought it was only a link and PR to the podcast.
I guess i’m now officially Old - I just want the text summary of things, with headers. so I can easily skim it 
1 Like
On the threads about failure and “not recommended”:
yesterday (before the AI switchover happened), I was assigned Eclipse-1 (2x20 sweet spot, 15min rest between intervals) and completed it feeling great. I even told my spouse “I hit a 2x20 SS for the first time in a long time I don’t feel gassed!” I marked its RPE intensity as moderate - good workout, but I think another 20 min set would have put me over the top.
This morning, just to the new platform, I searched for Eclipse-1 in the library and TrainerRoad cautioned I should not do it because there’s a good chance of failure, i.e, I think the Fail %age was over 2% ?? I’m a basic at this stuff and I’m not super-trained like some of you, but that seemed weird. I understand this could mean that the old TR AI setup delivered to me a workout that was not as well-tuned to me as it should. But my actual feeling after the workout, and this morning, has me in a good spot physiologically.
Is the intention that these things will round themselves out as the new AI robots get more inputs from us? I genuinely think that yesterday’s workout would be at least “achievable” in the old setup, For it to move to “not recommended” has me confused! Thanks.
Garbage In, Garbage Out…
As @Rizzi wrote, begin providing correct RPE feedback, and revisit your previous workouts over the past couple of months and do your best to update their RPE ratings to something better reflecting the true effort. Use the “Chad Guide” to inform your ratings.
Good luck.
1 Like
Something has changed - you can now edit RPE for all previous activities.
4 Likes
Interesting how different we all use the RPE system…giving you my example: 3x20 sweet spot 90%…HR was ok…of course I could have done another interval without any problem…but I hated that workout at the end when the legs just felt uncomfortable and tired…so I rated it very hard. I always opt for the harder rating. Out of curiosity I looked what the upcoming workouts would have been if I just rated Hard…was happy to have chosen Very Hard.
Usually I would have said: Don’t overthink it, just stay consistent within your RPE system. But as I said above…better pick the harder rating because with the new system I can imagine some people will learn the hard way when otherwise being pushed towards grinding workouts and then might come here later telling “TR burned me out”…
2 Likes
I just stick to the Chad chart. It’s the only way for me to ensure consistency in my ratings.
4 Likes
Really good points. And why I would love a deep dive on the dev project side. Seems like a project that would been better in smaller releases. A bunch of new features overshadowed by Ai FTP.
If you are working fine at a higher FTP than the new Ai gives you, you are hesitate to go down. When you are like us seeing 7-12% increases you are skeptical. Especially given our history of the effort it takes to get said increases. What have been easier to not lower FTPs and predict lower FTPs based on some quantitative buckets and let people know why they are in the bucket.
Higher FTP increases are fine within reason. Only increase some percentage. Predict FTP and let people know why. Part of which is TR is picking rides you historically do well with. Too black box the way it is rolled out today
I’m all in but not caught up in achieving a 12% increase or skipping a workout to run because sitting in doors all winter bites.
As a side note, anyone else want a forum topic on how bad iOS 26 is? I digress
A little different approach would have kept the zones equal across platforms. As long as the workouts were done and the new FTP was gained over time bumping FTP across all platforms would have been easier to wrap one’s head around.
1 Like
Agreed. I keep hearing that it’s not really TR’s AiFTP isn’t really FTP anymore, etc etc. If that’s the case why don’t they just call it something else altogether? It would really reduce confusion…
7 Likes