New AI-based training platform Vekta: a TP & TR replacement for the pros?!

By accident Youtube served me a snippet of this video on a new AI-enabled cycling training platform called Vekta. They claim to be working with pro teams and it seems like a mix of TR and TP, but with more advanced analytics tools. They make some big claims, but judging by the screenshots, the app/platform looks very capable.

The design looks clean, it starts from the assumption that you might have a human coach and tries to put relevant performance metrics front-and-center (and both are different for coaches and athletes).

Interestingly, they have publicly shared their roadmap and seem to be plugging away. Members can apparently leave feedback on the roadmap.

Overall, it seems like something where TR wants to be in a few years’ time (judging by what @Nate_Pearson has said publicly on the podcast) … assuming it works.

Does anyone have experience with them?

2 Likes

Does it have a built in workout player (app based) or do you also need to subscribe to zwift etc..

2 Likes

No idea. One of the touted features was automatic interval detection, so it seems to be outdoor-first. I’m tempted to give it a try, but wanted to see if anyone has heard of it.

2 Likes

They have some cool integration ideas and the UI looks very nice. Digging through their website, it does have a workout creator, but it doesn’t appear to me to have a plan builder or a workout player, and the post-ride AI analysis appears to be similar to Strava or FasCat in that it just tells you what you already know. Cycling only for now, but running and swimming planned for the future.

I might test it out for a month on the free trial because I’m curious, but with no training plans, it would be a non-starter for me unless I just absolutely hated using GarminConnect/TrainingPeaks/Intervals.icu.

3 Likes

They also have nutrition on the planned feature list. After seeing parts of the interview, this seems like a very serious attempt.

If you ever tried it, would you be willing to share your feedback? I might give it a try during my next off season/shortly after. But it isn’t quite clear to me

One of their features is called AI session planner, and I assume session = workout?

Edit: I see what they mean, they used an LLM and standard ML APIs to generate workouts from a description.

If these metrics were presented in a more user-friendly and more easily trackable fashion, this would be a net positive. intervals.icu is extremely powerful, but you need to know what to look for.

2 Likes

Yep. Agreed on all. So no plan, but if you say “give me 4x4 VO2 with 5 minutes rest and 10 minute warmup and cool down”, it will build a workout. Fascat does that too, I think. But, if you’re going to do all that, I think it’s faster to just build or edit a workout in TP/Intervals.

And yes, I’ll share if I try it!

1 Like

So the AI can take over some of the busy work of coaching (creation of standard workouts, do standard adaptations of the training plan) and reason about why it did what (within some limits). That’s neat. So it seems as if TP should be worried more than TR.

Nate mentioned that he hopes TR will be able to do this at some point. However, TR will very likely need major re-engineering to introduce concepts like coaches and make it coach-centric (to introduce coaches and coached athletes as well as the amenities you expect these days).

If this were a start-up with zero customers (like, say, replacement-for-Zwift-with-no-active-users), I’d be more skeptical. But it seems they are serious people working with other serious people, and if the screenshots correspond to the actual apps, then I think this could be an interesting addition to the market. TP’s UI is ancient and not fun to use.

1 Like

Struggling to see what the USP is here?

So just to confirm (as I haven’t jumped in yet to look), this app doesn’t have the ability to create any training plans?

The breakdown of CP W’ Max Power seems very similar to Xerts signature right now which is what I’m using. This looks to be a much cleaner interface vs Xert but at least it can create me a plan to follow.

1 Like

Just took a look. Doesn’t show a workout from Zwift yesterday. Doesn’t offer any plans etc. Maybe it’s useful if you’re a coach, it’s utterly useless to me.

1 Like

This is really a TrainingPeaks replacement as far as I can tell. It is already being used by some World Tour teams.
They have replaced FTP and TSS with their own metrics, which they claim are better and more accurate. Access is free for coaches and the athlete pays a subscription. There is no plan builder as in Trainerroad - you can get it to build workouts for you but you need a Zwift (or alternative) subscription to do the workouts. There is a podcast with one of the creators for a better explanation: https://www.youtube.com/watch?v=I_QFSnTga7c&ab_channel=TheRoadmanPodcast

3 Likes

I heard about it on podcasts and elsewhere. It’s pretty sub-average imo. It’s claims of world tour are imo potentially similar to SIS and stages was to team sky. I tried hard to make it work. But free strava + intervals + copilot makes it look pretty silly, pretty fast. Uninstalled and do not recommend.

4 Likes

I have the 1 month trial a go in June but still felt like it was an unfinished production y at the time. Any new updates from those who have tried it recently?

2 Likes

Seems interesting…

Hi everyone, Dominic here from Vekta :waving_hand:

Really appreciate the conversation, it’s been great reading through everyone’s feedback. Thought now would be a good time to share a bit from our side to offer some clarity and answer a few questions. Hopefully the folks at TrainerRoad don’t mind.

Vekta is a training and coaching platform designed for both athletes and coaches. We take a human-first approach to AI, using it to push the boundaries of what coaches and athletes can achieve. Unlike plan-builder platforms, Vekta doesn’t generate training plans. We focus on analysis, insight, and the tools that help coaches and athletes adapt and enhance training for real-world demands.

We currently use AI in several key areas of the platform: adaptive training zones that update daily, automatic interval and stimulus detection (indoor and outdoor), race detection and classification, session comparison, and the ability to build workouts directly from text. Over the next few months, we’ll expand this further as AI becomes a deeper part of planning, analysis, and day-to-day decision-making.

Our performance models are built around Critical Power and W′, along with our proprietary metrics, Vekta Load and Intensity, which go beyond legacy measures like FTP and TSS. We also factor in kilojoules (kJ) to capture the true work performed, and Durability to understand how performance changes as fatigue builds, giving a clearer picture of an athlete’s capacity over time.

Our goal is to close the gap between fragmented tools and the reality of how athletes train. We aim to bring everything that shapes performance. Training, recovery, sleep, nutrition, and lifestyle data, into one connected ecosystem, giving coaches and athletes the full picture, not fragments of it.

Although we only launched around seven months ago, the platform was developed in collaboration with WorldTour teams and coaches, and built for athletes and coaches at every level. We’re proud to currently support Team Jayco–AlUla, FDJ–Suez, and Arkéa–B&B Hotels, with a lot more WorldTour teams joining us for 2026, which we’ll share publicly over the coming months.

A key pillar of Vekta from the start has been design and user experience. This space has long been known for bad UX and overly complex workflows, and we’ve worked hard to change that. The aim has been to modernise the experience for both coaches and athletes, creating a platform that feels fast, intuitive, and genuinely enjoyable to use.

Integrations have been another major focus. Vekta now connects with Garmin, Wahoo, Zwift, Hammerhead, WHOOP, Oura, Ultrahuman, and CORE, with more being added constantly.

In the coming weeks, we’ll also launch Running, which will include planning and analysis, and utilises Critical Pace and Critical Power, bringing the same depth of advanced insight that cyclists have had from the start, and swimming will also be added in the new year.

As mentioned above, we are new, but the pace we develop at is something we’re very proud of. Those who use or follow Vekta will know that updates across both the app and desktop happen regularly, and the platform has evolved massively since launch in April.

Our Roadmap and Changelog are public and open to everyone. Feature suggestions that gain traction are prioritised for production, and that feedback loop between users and development has been central to how we’ve grown so far.

https://vekta.supahub.com/

Thanks again for all the discussion. It’s great to see people digging in and being honest about what works and what doesn’t. I’m here to answer any questions or share further resources, and there’s a 30-day free trial available for anyone who wants to take a closer look.

Dominic
Brand Director, Vekta

4 Likes

Overall, the design looks sleek and modern. :+1:

Can you sketch in what way Vekta supports coaches? In what way does Vekta help coaches create training plans? Do you e. g. compute, say, number of weeks until athlete’s A event automatically and already suggest some broad goals such as a taper before the A event? Is it possible for coaches to create placeholders for workout types without specifying the details (say, long VO2max intervals, endurance or sweet spot)?

Out of curiosity, do you plan to integrate with other platforms such as TR? For instance, in the past I used TrainingPeaks for things like race analysis, and it seems that this is something Vekta can do as well.

Can you sketch how Vekta alerts athletes and coaches of relevant factors? E. g. I slept badly, does Vekta automatically suggest a rest day or an easy endurance ride?

1 Like

I signed up today to check it out. My training is all synced to Garmin connect and Intervals.icu. My indoor work is done on TR while I run Zwift on top. Garmin doesn’t do pass through data so anything from Zwift doesn’t get sent, and Vekta doesn’t grab historical zwift data.

It appears there’s no good way to import historical data into Vekta. Ain’t nobody gots time to upload files on by one and I haven’t been able to find a way to bulk upload data. Also, while the UX is pretty, it ins’t that intuitive to use, especially in the App. The web version is better.

Anyway, if there’s no simple way to import my old data, it isn’t much use to me.

2 Likes

I was thinking the same thing. I would expect that the platform at least support the decision making process of coaches. For instance, it could flag if an athlete has not slept well or if the indicators in aggregate show the athlete can either push harder or needs a little more rest. I don’t think listing e. g. numbers of hours slept last night/average sleep within the last week, HRV, etc. really helps coaches.

Does Vekta do that?

1 Like

@OreoCookie really appreciate all the questions and the time you’ve taken to go through everything in such detail.

We believe coaches bring qualities AI can’t replicate: intuition, empathy, and the ability to understand the athlete behind the data. Where most platforms look to replace the coach with AI, we use it as a tool to enhance the coach’s expertise.

Vekta is designed to handle the heavy lifting for the coach, aggregating data and surfacing insights across an athlete’s training, racing, and recovery, saving time and allowing coaches to focus on what matters most: the athlete.

Here are a few articles on some key features:

Vekta doesn’t automatically create plans or tapers. The platform is built to keep the coach and athletes in control while giving them the data and tools to plan efficiently. Coaches or athletes can map out seasons and target events on the calendar, then use that structure to guide planning as they see fit.

You can also create placeholders for workout types, like VO2, endurance, or sweet spot sessions without defining every detail. These can later be built out using the Training Structure Generator, which turns a short text description into a structured workout. Or if you don’t feel like planning the structure of the workout, our AI will detect your workout structure only from the power stream and assign each interval an Intensity type (VO2Max, Threshold,..) as well as give your workout a Training Stimuli tag.

At the moment, there are no plans to integrate with TrainerRoad. Vekta is designed as a complete ecosystem rather than a companion platform, so all analysis and insights happen natively within Vekta.

Vekta tracks daily recovery data like sleep, HRV, and readiness, and flags when values deviate from the athlete’s normal range. These insights appear directly on the coach dashboard and in the athlete’s daily summary.

Vekta doesn’t automatically prescribe rest days or new workouts. Our approach is to keep the coach and athlete in control, surfacing the data and context that matter most so they can make informed decisions.

We’re currently working on enhancing this side of the platform with a more intelligent alert system that gives coaches and athletes clearer context around recovery and readiness. We’ll be sharing more details on this in the coming weeks.

If you’d like, I’m more than happy to jump on a call and take you through all the above in a bit more depth. Let me know!

2 Likes

Hi @Bbt67. Exactly, you’ve captured it really well. Coaches bring the expertise, and Vekta gives them the insight and tools to act on it. The platform doesn’t replace the coach, it enhances their IP and philosophy, giving them the ability to efficiently make data-backed decisions.

After each session or race, Vekta automatically detects intervals and climbs, classifies them by intensity, allows comparison across similar sessions or races, and maps peak efforts against power curves recorded at different fatigue levels (0–50 kJ/kg). It then generates a summary showing how the session was executed. Combined with metrics like Critical Power, W′, Vekta Volume, and Intensity, coaches can quickly see how the athlete is responding to work and where adjustments might be needed.

The aim is to make feedback loops faster. Coaches get clearer context, athletes get more relevant guidance, and both spend less time trying to interpret raw data.

1 Like