Koop AI, Unboxed

We reveal how Koop AI turns 25 years of coaching into an adaptive, terrain-aware training system for trail and ultra runners. We share why we built it, what it does today, where it falls short, and how we’re improving it with real race data.

• why serious runners wanted expert validation without elite pricing
• the three pillars of coaching we modeled: prescribe, analyze, communicate
• onboarding that pulls real history, constraints, and race demands
• dynamic plan changes for travel, missed runs, and time budget shifts
• NGP-based feedback for trail intensity instead of raw pace
• race specificity: course demands, heat, altitude and future prompts
• features live now: chatbot tied to Koop’s content, calendar, swaps, block moves, cross-training, volume trends
• limits we own: early-stage feedback, UI/UX, depth of “why,” and NGP-driven plan adjustments still shipping
• how we validate against coach standards and major races like UTMB
• long-term mission to make top coaching accessible to everyone

Sign up: https://www.koopai-endurance.com/app/

Chapters

• 0:00 Setting the Stage: Why Coop AI
• 3:00 Origins, Fear, and Embracing Tech
• 8:45 Meet the Team and Roles
• 13:30 Turning Coaching into Math
• 19:00 Three Pillars: Prescribe, Analyze, Communicate
• 23:30 Chatbot, Plans, and Feedback
• 27:30 Onboarding and Dynamic Adjustments
• 32:00 NGP, Trails, and Real-World Nuance
• 38:00 UI, Features, and Race Specificity
• 43:30 Limitations, Roadmap, and Iteration
• 49:00 Validation at UTMB and Beyond
• 54:30 Access, Pricing, and How to Join
• 59:30 Mission, Standards, and Closing Reflections

Transcript

Jason Koop: 0:12

Hello members, what is going on? Welcome to another episode of the Koop Cast. As always, I'm your host, Coach Jason Koop, and this episode of the Public Half is a special one because it is the moral public public coaching product that I have been involved with and has been under development for over two years, and that is Koop AI. So, what is Koop AI? Simply put, this is my brain and public. It's an artificial intelligence coaching product that takes all of my knowledge and all of my expertise that I've garnered over the last 25 years of my career and it makes it accessible to anyone through an app that we've developed. Let's face it, artificial intelligence is everywhere. Even big apps like Strava are trying to put it into their product so that athletes can access it. And this is my humble attempt to do so with a very specific goal of essentially mimicking what I do from a coaching standpoint on a day-to-day basis. We've been working on this for over two years and have a core group of users. And I have to say that the results that we've got from these users are quite encouraging and something that I've been extremely impressed with. As an example, most recently, nine of our test users participated in the most recent editions of all the UTB races. Seven out of ten people finished their races, and we actually had one person who was preparing for the most recent trail world championships, the world championships using this product as the coaching platform that they were receiving all of their advice and all of their training community. This product really excels at training prescription and modifying the training prescription based on whatever life throws your way. It's extremely accurate in representing what I would do with actual athletes, so much so it's actually kind of scary. I'm looking at it and I'm like, that's exactly what I would do in that situation based off of this athlete's particular set of circumstances. Needless to say, I wouldn't put a product out in the world that I didn't believe in, and I'm extremely bullish not only on the technology as a whole, but this product for its stage of development, and it's only going to get better from here. So on the podcast today, to illuminate this product even further is the founder of the product, Binette Mansia, who is instrumental in me adopting the technology. One of our Crack CTS coaches, Ryan Anderson, who you guys have recognized from a number of podcasts. He has been instrumental in helping bring this product to life. We go through all of the bits and pieces of the actual product. I'll let the conversation speak for itself. In the show notes is where you can actually sign up. And this is available to everybody right now with the low price of $12 a month. You can access my entire brain, which is still, once again, I'm saying it right now and it's still kind of scary. Coming to the conversation, I'm gonna get running in the way. Here's my conversation with Benem C and Ryan Anderson all about the world of my lunch and the development behind the scenes of our brand new coaching product, Koop A. We could start the podcast out with that good big brain. Okay, so just to set the uh set the stage for everybody, we're in Chamony, France again, all together. One big happy family in advance of uh UTMB 2025. We have no idea what's going to happen, and this is not gonna try to predict what's gonna happen. In fact, this podcast is gonna come out many weeks after UTMB, so the dust will all be settled there. We are not here to talk about UTMB, we're here to talk about something that um I was going to say that I've been working on, but I really haven't been doing all that much. Um, uh, that's been in the works for a couple of years now. Uh in the studio with me today, in the studio is a basement of a chalet in Chemini, France. I have my good friends Binett and Ryan Anderson. Ryan's been on the podcast before, one of our CTS coaches. But many of you guys are not familiar with Bennett. And so just to start out with, before we start to talk about this project that we're gonna kind of unveil to the broader world, Bennett, who who are you?

Benat Mencia: 4:31

Great question. Um well, I I met you two years ago through a common friend. I am a theoretical physicist that transitioned to AI uh about eight years ago. And um I started off doing research in AI and then transitioned to the industry world. Um and yeah, two years ago, yeah, this project arrived to my life. It started as a side project, and the whole thing gained lots of momentum. So I've been yeah, focused on coupe AI for the past couple of years.

Jason Koop: 5:10

So, as the name would indicate, coupe AI is me as an artificial intelligence being, and we're gonna describe a little bit more about that uh kind of like going forward and how we're all piecing it together with coaching and math and AI and and what the outcome of all of this is. But just to give the listeners a even a even a bigger backdrop than that, and I don't think either of you know this origin story, so it'll be kind of like news to you, and you can laugh about it or whatever afterwards. But one of the primary driving forces of why I started to get so incredibly interested in creating an AI coaching product, and I didn't know what it was going to be at the time, was I was actually a featured guest at a business coaching summit. So I happen to have a mutual colleague that has a really big business that's multiple times the size of CTS, and they're and they have a they have a coaching service that's analogous to what we do in ultramarathon coaching and cycling coaching, but they do on the business side. So they work with C-level employees across Fortune 500 companies and things like that, and they coach them to be better C level employees and better leaders and better managers and things like that. And one of the things that came up in this coaching conference, it was several years ago now, was how artificial intelligence is going to present a threat to the kind of the broader employment space, but more specific to them, the sea level and the management space. And the overall tone that I got from that group of people was one of threat and fear. You know, the big bad machines are gonna take over and replace all of our jobs, and they'll never do as good of a job as we can as humans and things like that. And I've learned that over the course of my career that you can't fight technology. The technology is gonna come, whether you like it or not, and it's gonna do some things really well, and it's gonna do other things not so well, and people will adapt to whatever new iteration of technology there is. There that was that way when the internet came about. That was that was the same way when onboard cycling power meters started to come around, and I saw a lot of flavors of those technological iterations and this new AI wave that was kind of coming through. And it was punctuated by this kind of like threatening environment that this group of very successful business coaches actually had. And it was that moment in time where I said, I'm gonna figure out a way to play in this pool. I don't know left from right or up from down in this pool. I, you know, I've heard about it just as much as anybody else. And so I started to sew together the connections to try to make it work. I, you know, networked like I always do. I kind of hit the pavement, I talked to people, I found people, I, you know, got different directions from people. Some of our, uh some of the uh people are here in Chamony, France, with all of our mutual colleagues and partners over at Training Peaks. So I had a lot of counsel in a lot of different areas, and that winding trail eventually led me to you, Binett, through really serendipitous circumstances, and you happen to be the right person in the right circumstance with the right background and the right education at the right time that was sort of interested in trail running and endurance sports and things like that. And now we're kind of finally turning, you know, kind of like turning around to it. But um I guess my point with that is it's been a really long, windy, like four or five roads, four or five year road to kind of like get to this point where we've got this product that actually now has a form and a shape and delivers something that it was actually that we've kind of cooked up for to to to intend to deliver, which is really cool. So with that as a backdrop, really long, kind of like long-winded backdrop, we're now here to kind of reveal what this, what this actually is, and then Ryan, how you finally get involved kind of from the coaching side of things. So I think the first thing is is like outside of us just like Binette, you and I just like physically meeting and like shaking hands and kind of like figuring out why don't you take the listeners through the first part of the iteration of what eventually has been formed? Like the first few times that you and I kind of like sat down and said, Okay, what can this actually be? What did that like look like for you? And how did you start to figure out how to like solve ultimately what is, and you can describe this however you want to, but what uh how I've described it is putting my brain in a technological box that other people can access. And my brain being the knowledge base, the programming, kind of everything that I've acquired from a coaching perspective over the course of the last 25 years, putting that in a technologically accessible being or entity or thing that people can that kind of like people can access. Take us through like the very beginning of it. Like, what did we actually go through during the formulation of this to start to start to piece it together?

Benat Mencia: 10:28

So one of the first things we did was to try to talk to runners um to try to figure out whether there is a need or a pain point out there in the running community uh that we could help with. And so we talked to about 50 runners back in May 2024, and what we realized is that there is a group of runners out there that take running very seriously in the sense that they prepare hard races, follow structured training, they take the time to read books and listen to podcasts, etc., to you know, be in good shape to prepare their training plans. And these runners would complain about two things. One, the time and energy it takes to do this well, i.e., the time it takes to read books, keep up with the information that keeps coming out, listen to podcasts, um, and also they complain about the fact that they tried their best uh trying to prepare the training plans, but then they would miss the validation of the expert. Um so when we asked them, well, why don't you hire a coach to do this, that's exactly what a coach does for you, they would say that it's too expensive to be coached by a top coach. So that was yeah, that was a very, very clear outcome of of that first round of communication with with runners, and so we decided that we should uh focus on that and and build a product that would be a solution to that problem, i.e. give access to everyone to top coaching. Um so that's how it all started. Um I guess then we given that's what we wanted to achieve, we had to decide okay, how are we gonna achieve that? And what this has been about for the past two years mainly is about building a mathematical theory of your methodology um so that we could then put it in a computer. And uh this happens to be a pretty challenging task um uh because well it's it's easy, you know, taking a specific case, working with a specific athlete and and figuring out what's what's best for this athlete according to your knowledge and your methodology, but building uh an app that can potentially be used by millions of users require capturing the the general the general shape of your methodology, i.e. finding the complete set of mathematical rules that would apply to every single case, not only the mainstream 60-70% of the cases. And so that's that's has been our focus uh for the past for the past two years. We are that part of the app is quite mature now. Um so we will start focusing on other aspects uh that are let's say less this is the core of this product, this is the the main value of this product based on what we hear from our users. But of course, um once the the main the main part of the product is built, one needs to also address other things like user experience, user interface, etc etc. which which also matters um for for most users.

Jason Koop: 13:56

So the the way that I've always viewed this is there's uh three primary things that I do as a coach and that any coach really does. We prescribe training, meaning, hey, let's go out and run two hours on Tuesday. Maybe there's some intensity structured around it a couple of times a week. Training is also how the macro view of training looks over the course of nine months or 12 months or maybe 18 or even 24 months. But we're prescribing training. That's one fundamental thing thing that we do. Second thing is analyzing that training. So seeing what's coming down the pipeline. Okay, are you better, worse, or the same than you were yesterday, the day before, the month before that, and how does that impact what we have what we theorized we were going to prescribe next week and next month and things like that. So prescribing training, evaluating training. And the third piece is communicating with the athlete. And there's a lot of different layers to that. Some of that is technical communication. Hey, your intervals were better than they were last week, or hey, your workload is higher than it was last month. Some of it is emotive communication, which is what I'm doing a lot of this week, right? Hey, your training's going great, you're gonna crush it, you know, on Friday, like that kind of, you know, that that kind of stuff. But there's a communication piece. I think the way that I've kind of viewed the first part of this project is mathematically solving for those first two pieces, right? So looking at all of the different scenarios and kind of coming up with you you keep saying a mathematical model, I'll say an extremely elaborate rule set um uh of which any runner can kind of like look at it and come out with an outcome that if it meets its merit, it's within 95% of what I would actually prescribe. It's within the human error of what I would, what I would actually uh what I would actually prescribe. And then taking that training and looking at it and coming up with uh coming up with a uh a way to mathematically solve for the second piece of it, which is analyze the training. Are you better, worse, or the same as compared to your last week in that and last month? The fair fair assessment of for how I kind of view it from a coaching perspective versus uh versus the customer perspective.

Benat Mencia: 16:09

Yeah. Yeah, I think I would describe it quite similarly. Actually, I you know, when I find myself explaining to others what Koop AI is, I say it's got three parts. One is the chatbot that is connected to your content, which allows runners to kind of quote unquote talk to your content. Then there is the training plan generator, which prescribes training, um which is fully tailored and is dynamically dynamically adjusted based on how training is going. And then the third bit is feedback on training, um, which is something that we recently deployed. We've been working on this right now, and I have been working on this for the past couple of months. It's it was very clear, it's been very clear, users have been very outspoken about the need for feedback. And so we finally deployed, let's say, version zero, a simpler form of feedback, which um analyzes the NGP of of the run and gives feedback on NGP, that is whether the intensity of the run or the intensity of the intervals on hard workout days was the right intensity, or whether it should be higher, lower, etc. etc. So, yeah, I I would say that that's that's a a fair description. I mean, here what we want to do is we want the the user of Koopai to get as you say 95% of what they would get if they were coached by you. Of course, we're missing the human component here, and and it remains to be seen how important that is, the absence of there being a human on the other side, and actually that that remains an open quest open question to me. But I believe that everything to do with the exchange of information between coach and athlete, I believe that we can capture that with high accuracy in finite time, and and we will do that with Coupei.

Jason Koop: 18:03

Wow, that's a pretty incredible statement. I was kind of I was remembering about like this first iteration of like the fear of you know machines are gonna take over or whatever. I very distinctly remember in one of these meetings, I'm like, listen, I'm not afraid of being obsolete. If I can build something that makes myself obsolete, that's a win for everybody. That's a win for other people, that's a win for me, like that's a win for whoever else we can kind of bring under the umbrella. So I'm not I'm not scared. So you keep mentioning we. So let's kind of go over like who's a critical part of the team. And once again, to the theme of me being obsolete, I have been only very kind of like interestingly enough, kind of like loosely involved in the development. You can describe like who's all involved, and we can bring Ryan in the conversation because he's been one of the key players in how this whole thing developed and putting some like coaching, just some real-time like coaching checks and balances on things.

Benat Mencia: 18:59

So, you want me to go through who has been involved in this project? Yeah, so uh I would say on the on the technical side it's been mostly me full-time for for the past couple of years, but there have been three other friends who have also developed part of the app. Those are Andy Andy Highsmith, Jonas Narkelunas, and Gasper who is just starting now. So that's on the technical side, and on the coaching side, it's been Ryan Anderson who is here with us today, and then you yourself, Jason Koop. Um so yeah, so but I would say it's been mostly Ryan and me, me on the technical side, Ryan uh building theory that then I would I would put on a computer, and also you you've been also you've been involved in the in the theory building, especially in the first 10 months of this project, you kind of build the backbone, the the base of of the whole of the whole training theory. And then Ryan joined joined us about a year ago and has been building on top of what you had built initially.

Jason Koop: 20:08

So, Ryan, how would you describe like your specific role? Because the the way that I, when Bennett and I were organizing this, one of the things that I very quickly recognized is that I was gonna log jam things. I I work with you know a lot of athletes. I'm somewhat hard to get a hold of and get responses to, and Bennett is very fast and numble and needs a response like right then and there. And I needed to bring in somebody that I trusted a lot, that also knew the backbone that you just mentioned intimately well, and you you kind of like fit that profile. And I kind of went into the project kind of describing it just in just in that way. But now that you've like had your hands dirty with it for over a year, like how would you describe to the listeners like what you've actually been doing kind of behind like underneath the hood, so to speak?

Ryne Anderson: 20:57

Yeah, it's applying the art of coaching and answering all that well, it depends questions, because that's always the can coach answer to anything. Because it it truly does. It always depends. But how do you how do you come up with these rules that can be applied to uh this format of delivering plants to people?

Jason Koop: 21:19

It depends on, which is which I always like force the coaches to think about.

Ryne Anderson: 21:23

It depends on you can't just say it depends and then pull something out of nowhere or leave it at that. Like, no, based on your experience and expertise, it depends on, and then there are answers, models that then define what is the next best thing to do. Um, and so if I was to explain very simply what I've been involved with is that coming up with like the it depends. And so you you created the the theory of it all of like, okay, this is how the different types of intensities are gonna flow. Um, this is how volume is gonna be modulated based on intensities, and then coming up with all the contingencies that come into play of like, well, if we have eight weeks and it's a 50k race, we're gonna do this block to this block and and all these different rules. Um and probably the the part I'm most proud of of working with this is like making it specific to the athlete. It's not like somebody goes in and says, Um I'm a beginner based on this rubric I see. I'm doing a 50K in eight weeks plug and play. It is not that it's they they have to input or we have a way to pull out their past training data and find their volume, find consistency or lack thereof, and then meet the athlete where they're at because that's what a human does. So a good human coach is gonna do that always. Meet the athlete where they are at first. And one of the first things you told me, Koop, is answer and solve all these as you would as a coach. It was like, don't think too hard of like, well, this is how um it needs to be programmed or think of this contingency. It's like, no, just first and foremost, you have a problem. How do you solve it as a coach? And then we'll massage that and work through it and figure out how to apply it from the ones and zeros side of things.

Jason Koop: 23:25

Um that's that's the way that I've always like tried to communicate with you, Bennett, about the project. Is this like I don't know shit about shit in your world? This is how I would always start out the my answer with this. This is how I would do this as a coach, and then kind of like walk through, walk you through the scenario, and then let you figure out how to take that strategy and operations and put it into put it into a electronic and mathematical package, so to speak, right? And I I think one thing that's that that I think the listeners should probably come to appreciate is this isn't just go forward programming that we're coming up with. So to your point, like it actually takes an athlete's history and analyzes it like we would as a coach. How much volume were you doing, how much intensity were you doing, when were you training? Exactly. Yeah, like all those things that we would go through as a coach gets taken into account before day one, workout one actually gets programmed. So I'm wondering if you can like uh briefly synopsize the run of show as the user would experience it. New person signs up, what are they gonna what are they gonna go through, and then what ultimately is the thing that they get to interact with?

Benat Mencia: 24:52

So when user logs in for the first time, the first thing is to go through onboarding. And the onboarding form contains all the relevant questions, i.e., it's the job of the onboarding to gather all the relevant variables to get the athlete started. Um and so this is a long list of questions, and uh these questions are to do with the volume they've been doing in the past two months, with the consistency uh they've had in the previous two months, with the intensity, where they've been doing intensity consistently or not, whether this led to fatigue or injury, um it's to do with Well, this is okay, it's a with the past, that's that's the most important thing, what they've been doing in terms of running. And then there is everything else to do with the feature, like um when do you like to do your longer runs? When do you like to take your rest days? What's your daily time budget for training? Um what's what are the races you have in mind for for the coming for A race?

Ryne Anderson: 25:58

Is it an A race? Yes.

Benat Mencia: 26:01

Um Yeah, so these are these are the key elements. And again, the the way, as with any other part of this app, the way we designed this onboarding form was by asking you and Ryan, all right, so what do you talk about on your first day when you first meet an athlete? What are the relevant variables you need to gather to get the athlete started with an initial training plan that will then of course be adjusted dynamically based on everything that happens throughout the journey? Um okay, so that that's the starting point, and after that, the first, let's say the first version of the calendar is generated, what we've been calling the static plan. Um and yeah, the athlete is told what to do every day. We've we've put all the information that athletes have requested. There to be no ambiguities in terms of what needs to be done every day. Um and then the athlete we ask runners to provide feedback on training, uh both objective and subjective. There is integration with the Strava. Down the road, there will be integration with all the watches, of course, but at the moment we found a quick hack that did the job to gather the objective numbers. And there is a whole set of rules, what we've been calling the dynamic theory that adjusts the training plan based on how training is going. Actually, you, Koop, you were very involved in the dynamic theory, so it's been mostly defined by you actually.

Jason Koop: 27:24

Um I've got a question on that. How often do you find the dynamic theory actually kicking in and like supplanting whatever the static theory had initially? Like how much is it actually adjusting? I wonder if you can kind of like encapsulate that at all.

Benat Mencia: 27:41

Um the answer is I don't know. I I wouldn't be able to say whether it happens a lot or not. Um what I what I will say is that based on conversations with with runners, uh there seems to be the perception that the dynamic theory is not really there. So I'm guessing that it doesn't happen too often. So so every time there is uh someone reaches out asking what is the dynamic theory, I I need to remind them what the actual set of rules is and say, well, in your case, there hasn't been none of these rules have been triggered because your training pattern has been this or that. Um we have a pretty compliant initial group.

Jason Koop: 28:26

Let's just put it that way. I mean I think it's worth saying that like the initial people that have come on board, which what's the number on that right now, Bennett?

Benat Mencia: 28:37

So at the moment we have eighty paying customers, out of which about fifty-five are active users. That is, users that are using the app on a daily basis, checking the calendar, giving feedback on training. Um yeah, those are the numbers now.

Jason Koop: 28:49

And those were I'm gonna use the word curated. But they were curated to the extent to where like we didn't blast this out to everybody. We kind of used some selective like it's not like we were hand choosing them, but we used some selective channels to acquire those people.

Benat Mencia: 29:06

Yes, that's right. It's true for about half of of these people. Um so we first gave the app to 10 runners about a year ago, and that was a hand-picked group. Uh, we then extended the group in October, so we were working with 20 runners uh at that point. And then for the first time ever, at the end of January, we well, you posted on Instagram, and that brought a new wave of users. So the current group is a mix of this initially handpicked group of runners and people that join afterwards. Something I wanted to add on the dynamic theory side though is that well it remains to you know, a lot of work remains to be done in this front, and specifically one we've been talking about in it's become part of the existing theory. It's just that it's not implemented yet, is the adjustments. coming from NGP. So the initial dynamic theory contained well uh a set of rules then or so um but one that uh we've defined recently with Ryan well it's been defined by Ryan actually is how does your plan change based on NGP?

Ryne Anderson: 30:19

It's based on like NGP normalized great pace um that's from training peaks if you just use Strava that'd be gap great adjusted pace um because there's other AI coaching programs out there for road and it would just use pace. But for trails, you go uphill, you go downhill if you take raw pace, you're gonna get really whack feedback and adjustments because you go do a six hour run, you have a 15 minute raw pace, but that could have been a normalized grade pace of 1130 and you're in in zone as we've determined it so it wouldn't adjust or whatever. So when he's saying NGP normalize grade pace that's essential for our user base trail and ultra runners because we have to take into account the elevation change. Yeah.

Benat Mencia: 31:06

Yeah so what I wanted to say is that we deployed the first version of feedback on training which is feedback on NGP about a month ago but we have not implemented yet the rules that will adjust your plan based on NGP that is say you're on your first week within your block and it's expected for you to be at the top of your zone on your hard workout days on the intervals for example so if you are not there then the theory would prescribe your intensity throughout the block to be to be changed, to be lowered one notch let's say etc etc so this is to say this could let everyone know that the dynamic theory also the static part but then now we're talking now that we're talking about the dynamic theory um this will keep increasing and will keep adding nuance and and so the perception of it being fairly static will will change. I think it will change a lot specifically with with this feature because it's very manifest as in you when you get feedback on NGP it's very manifest whether you were in the right zone or you were not in the right zone and it's and it will be very clear to see how your plan changes according to this.

Ryne Anderson: 32:16

And it's going to integrate the subjective feedback as well somehow. Because again it all comes back to how do you solve this problem as a coach. And it's not just the data it's the subjective feedback. And in terms of that the dynamic part with the static plan, they can go in there and change their time budget or whatever and then boom boom boom boom boom it backfills and corrects it. So that's a very dynamic part of it all that's a critical part of a coach of oh I've got this work weekend I wasn't planning. How do I adjust? Like that's the dynamic theory you're talking about now, which is like you're very much in the cave trying to figure out is utilizing their uh data and how they're performing on the runs. But a key part that's already pretty damn good is they can go in and edit their time budget travel or whatever and boom it fixes it. They don't have to be left in the dark of I'm not gonna get that run in, even though it's my four hour day, blah, blah, blah.

Jason Koop: 33:18

And all of that's based off of just just to reiterate, all that's based off of what we would actually do, me being Ryan and I, like looking at that situation, really common one, which is just one of several dozen, I'm gonna miss this weekend due to my kids' soccer game, or I got sick, or I ran out of time, or I didn't want to I wanted to watch football instead of instead of go out and run. Like those types of training adjustments happen all the time as a real coach. And seemingly you have infinite numbers of ways that you can solve for those. You can simply let the time go, you can add it to the next week, you can add it to something four weeks down the road. The adjustment piece of it has tried to encapsulate and I agree with you Ryan does a really good job of encapsulating what we would actually do based on what is going on with the athlete at the time. It's taking our coaching workflow and then putting it into a system that would that would essentially automate it and does it with kind of remarkable accuracy. Okay, so what is the what does it look like? So describe the user interface today.

Benat Mencia: 34:34

So you've got the chatbot that you can talk to and you've got the training calendar where you see what what's prescribed for for the coming 14 days actually that's that's what we have at the moment and um then there are all these features that revolve around the training plan like well we just mentioned one the ability to change your daily time budgets but there is a long list of features there that that revolve around the plan and which is by the way I would like to say based on our conversations with runners this seems to be the most important part of of the app you know runners care about being given a training plan that will extract the best of their fitness potential so so yeah all these other features revolve around the training plan itself and and these features are the the ability to to swap days, the ability to move your recovery blocks say you're traveling and you won't be able to to run as much volume as you were prescribed so so you you're able to move your blocks so that there is no volume wasted. But then we have um you can add cross-training that's a very another recent feature we've deployed. You can see the evolution of your volume throughout the months and see why your volume is being modulated the the way it is based on where you're coming from and based on what your targets are for for for the coming foreseeable feature.

Jason Koop: 36:31

Based on the race that they're eventually choosing.

Ryne Anderson: 36:33

That's another thing it's again you don't just put in a 50k a hundred miler it's the hundred miler this hundred miler it's this hundred miler and we'll probably get to a point of like these hundred milers you must do heat acclimation for sort of like altitude considerations where it gets flagged and then chatbot goes in there and say if you're gonna brace this you either need to do the day before seven days out blah blah blah again it's it's very individualized and it's not just very basic things like I've already said if it's it's just this race. It's this race and what are the demands of it. Because again, how do we solve this problem as a coach? We're digging in to find these things to serve the athlete best and be specific to the race and then with their training history and how much they can train.

Benat Mencia: 37:24

Yeah. Something I would like to add is that today we are where we are and there is a very long list of limitations with this app not only on the user experience side but also on the nuance to do with training theory. But this product will never end its development process as in we have a system to prioritize what to build first. So there is a roadmap built which gets gets adjusted uh based on the feedback we obtain from runners but it's a never ending project and so there will be the day we will arrive today where when I'm completely obsolete the app is absolutely perfect. There's no such thing as okay you know we've got distant tasks and after we've done this product is finished and now we can all chill. No like best products best products never end uh developing and this will be such a product that for as long as we are alive we'll keep evolving. So we are where we are today it's still an early stage even though it's been a couple of years but we do what we can with resources we have we move as fast as we can given the resources we have but yeah like if I had to put numbers in terms of how much we've done out of everything that needs to be done for it to be the perfect app for runners I would be under five percent of that it has been done um so so I just want to be very clear that this we won't stop working until it's not and it's not close. Exactly because even even if we could define now what the perfect running app looks like new technology keeps coming out new information keeps coming out new science keeps coming out and we want to be connected to to how the times change and and so we will always be able to improve the product for our runners and that's what we care about. It's our mission to to make top coaching accessible to everyone and so yeah this is an infinite task in that sense.

Jason Koop: 39:50

Mainly from the perspective of who are the really good candidates for this in terms of their like athletic profile and what they're training for and then who who and what athletic profiles maybe are not good candidates for it, that there are too many exceptions or they wouldn't come through the initial filter or whatever. But before I want to get into that I just thought of a really great thought experiment. So one of the primary ways that I let me back up but just a little bit what one of one of my fundamental roles at CTS is not only coaching uh coaching athletes but also recommending our coaches to athletes that are coming in we have an athlete services team that's kind of dedicated to doing that but I also help that athlete services team out as well as people just reach out to me directly and say hey Koop what would you kind of recommend for this I've developed that recommendation kind of knowledge base through our educ through our continuum education system, our internal continuum education and open office system and primarily through our schedule review process, which we've talked about many times on this podcast. A coach throws up a training plan that they're going to it's kind of like feared and you know loathed and loved and everything kind of like all at once. But uh it's it's it's it definitely has evolved to this thing that we do routinely in the office where our coaching director Cliff Pittman will pick out one of our coaches and say hey I want you to do a schedule review based on whatever's coming up sometimes it's based on a race that just happened sometimes it's based on whatever is kind of like going on in the social media space. Ryan I want you to find an athlete that's kind of like this throw up a schedule and we'll kind of talk about it. And it's when I get to view those, it's through that lens that I can very keen I'm very keenly aware of where that coach is really strong, where they need to develop a little bit more, how they communicate, what they think about load management and stuff like that. And it kind of gives me a you know a scoring system essentially based on you know how they're kind of how they're doing with it. But I guess my point with that is is the I've been able to recommend coaches to specific athletes as well as recommend how they need to develop through this schedule review mechanism. And you've been through a lot of that Ryan you actually do a great job with that. That's one of the reasons you're involved with this project how would coopai stack up in that environment like if we went through that process with the schedule that Koop AI generated and we know the athlete profile coupe AI develops the schedule what like what do you think that would be what would the banter be like based off of what we normally do in our coaching environment who would be the first one to say I think you're doing everything wrong which I've done with a couple of our coaches over the course of the year.

Ryne Anderson: 42:52

But I guess what I'm trying to say is it's like how like is it how re how realistic of it is approximation for what we would actually put through a lot of scrutiny I think yeah if if you were to see the plan all of our coaches would recognize the flow of the intensities how the volume is modulated and everything. The workout vocabulary yes the workout vocabulary all that like if you're if you're taking an athlete that is straightforward so to speak and that we've got 12 weeks we're not coming back from injury we're not dealing with anything uh crazy travel wise or like if it's 12 weeks to the race it it will input based on the things specific to the athlete and the set of rules we have for the distance boom honestly like I don't know you have to really split hairs to look at it and say like hmm like why did you do that? Why did you do this? Maybe you could nitpick the volume modulation and like oh this person can handle more or they're they're gonna be a 30 hour finisher do you really think they should be doing steady state intervals they just need to do more volume like you can nitpick things like that but in terms of how it flows and the periodizing the intensity it's what we would do and what we should do. Which is that's not easy to do not saying that's always right. Yeah yeah yeah but it's following sound principles that we know work.

Jason Koop: 44:32

That's not easy to do because I've always felt that like from a coach development perspective it takes like 12 or 24 months just to get there. Like when I work with coaches and I start to kind of develop them through our educational system and they have different touch points within our company and things like that. It's really 24 months before they go into that schedule review environment and I'm like okay that's that's really reasonable I'm only gonna nitpick 10% of this the rest of the 90% is good. But for the first two years it's like okay we need we really like we okay let's like figure this like not that it's like it's really bad in my eyes because I have like I have a very sharp eye for that stuff. Most people wouldn't even notice but I guess what I'm trying to say is is is like I've I've always observed that whenever I've gone into the schedules and you guys have forwarded them over to me and things like that I look at it through that lens of that would pass the muster in a schedule review that any one of our coaches could pick up and say yeah I I don't you know Ryan built this Adam Ferdinand built it cliff built it Darcy built it Nicole built it it would kind of have like the fingerprints of all of that methodology kind of alchemized into one thing you could you could see that come through which is exactly how it is intended to is intended to flow through so I want to go back to like the limitations piece now Bennett so this is like specifically for you because you've been so hands-on with the users where have you seen some of the bigger pitfalls? I mean we can kind of be open and honest here like this is going to go out to a pretty big audience like where are some of the bigger pain points in terms of like athletic profiles that you've that that we've either yet to solve for or you kind of anticipate is going to be a pain point in the future.

Benat Mencia: 46:27

You can describe it however you want to so based on conversations with runners the the most important elements that they were missing um let's say three or four months ago we sent a survey in in May and based on this survey we learned that runners care about not only being told what to do to maximize their their fitness but also knowing why they are being prescribed what they are being prescribed. They want to have this um this confidence that okay it's not just a random number generator. Exactly and also I I guess actually you're touching something interesting here. I guess it's also the whole process of building trust between the AI and the athlete so so it's important to them to know why they are being prescribed what they are being prescribed so we've kind of deployed a version zero of that and we're now obtaining feedback and we'll keep iterating that until everyone is happy and there's enough information for for everyone to be happy with that. It was important for them to be able to add cross-training many of them from day one.

Ryne Anderson: 47:40

Yes many of them when we went through that filtering process we filtered out a lot of people who like cross training is my number one priority I want to know how to fit that in because we weren't there yet we it's like we have to figure out how to get it to that point just to just program the running. Yeah exactly um and then like that's a big thing for people they want to know how to fit it in we're like we've kind of deployed first theory of that but yeah that's an example of a big request for people.

Benat Mencia: 48:06

Yeah so this sort of big request on the most important one I think is feedback on training. Runners really want to get feedback on training because they don't know whether what they are doing they are told what to do they go do it but then they are not sure whether they did it correctly or not. And so we've been working on that for the last couple months we've also deployed version zero of that but still you know very simple form. Feedback on NGP and no dynamical adjustments and no judgment on more nuanced things as you know whether you are at the top or the bottom of the zone you're supposed to be in etc etc for now we were just you know testing the waters we've also deployed the first version of our NGP model in-house Coup AI NGP model before runners would need to have a premium training PIX account to get LAP NGP they could get in average NGP but not LAP NGP now we've deployed the first version first version of the Coup AI NGP model which is working well we'll keep we'll keep monitoring and we'll keep um assessing whether the behavior is the expected behavior um but that was a nice piece that was missing as well. I would say yeah these are the most important elements based on the last survey version zero of these elements have been deployed but you know this all these features need to be brought to the right level such that everyone is happy with this. And it will be interesting to see once we are done with these key things that we're missing and once everyone is happy with how this is behaving it'll be interesting to see what's the next thing that people care about. And for people always care about what they don't have. Right. Scarcity. Yeah but it's also a matter of priority right you know if if I ask a runner how can we improve Koop AI for me probably they won't go through everything but they will want to focus on the most important things they are missing and they will tell me all that but once we fix that problem then we go to the next level of of polishing and nuance and then and and as I said before you know this is an ever-ending process and so we'll keep talking to runners on a daily basis to understand how we can improve Koop AI for them. So how is the feature looking uh short term improving these elements I just mentioned improving feedback improving the cross-training feature improving the part of the app that explains why you're being prescribed what you're being prescribed at the moment it's focused on volume modulation and feed per mile modulation um but there are other elements that runners will also want to know about but this seem to be very important. Then there is everything to do with UIUX. Gasper is working on it now UIUX being user experience yeah user interference user experience that's everything to do with how pleasant and unpleasant it is to use the app. So far we've been focused on what runners seem to care most about as I said already 10 times which is being told what to do such that you know they will go crush the the race. But next level is okay not only you need to be given the right information but it should also be fun and pleasant to look at the app and you know move around the app. So and that's clearly important. Perhaps it's not important for the power user that you know the power user cares so much about being prescribed training following Koop's methodology that you know it doesn't matter whether it's ugly and painful because they care about the the core of the product but not everyone is a power user and not everyone is a an early adopter and so and of course we want to serve everyone and for that we need to also make it not only good but pretty as well.

Jason Koop: 51:57

We're we're gonna have a somewhat of a proof point in the next few days with the races out here. I mean there's how many people racing all the races again Banette?

Benat Mencia: 52:06

Eight Coupé A runners will be competing in Chamonix this week.

Jason Koop: 52:09

Yeah and that's across UTMB TDS OCC and CCC are also UTMB yeah for for yeah so smattering of everything and that's not it's not like this is like the first foray anybody's had into races we've had it before but that's a pretty decent gaggle I mean I have eight athletes across UTMB and CCC like just me personally and very much so my my personal coaching product has a little bit of a litmus test. Every big race we do this after Western states how did our you know success rate compare to the success rate of the race and we beat it every single year with our coaching staff we better be doing that compared to compared to the rest of the field. It'll kind of be the same with this we'll look at it how did all eight people do how does that compare against the norms or the averages and we can even use our coaching as a cross section of that as well as a comparative group across that and then how do we iterate from there and I you know I guess to be transparent I can post the results of that in the outro of this podcast since we don't know as we're recording it and then we'll just go from there but I do I do think that like it's important to know like people are actually using this for a what is for many people a once in a lifetime race and that's I think a really cool thing to kind of just just yeah just to trust you're absolutely right absolutely that's a great way to put it Ryan yeah yeah yeah so you're gonna be out there cheering these people on so that you have 100% finished right yes yes 100% you were out here last year and got your first taste in like five different positions I remember um last year one of the first users did a TDS I think Yonas not kill Yunas finished on a Wednesday what go see this is uh things that we'll figure out um okay we're we're gonna wrap it up here um first off thank you guys I know it's been a lot of hard work over the last few years and it's not like there's gonna be you know a $20 million marketing budget that all of a sudden like rolls out and launches this thing it's gonna be slow you know slow iterations that you know kind of creep along here and there this will be another iteration where we'll where you guys will onboard some people with this I will have links in the show notes for this but where do you want to direct people to find out more information about Koop AI to potentially sign up for Koopai where can we direct them?

Benat Mencia: 54:43

The website coupeaindurance.com and so they can find some information there and they can sign up there. And of course I'm happy to have conversations with whoever would like to discuss this or would like to know more about the project so they can email me and arrange a call if they would like to know more about the project.

Jason Koop: 55:05

Man you're taking that on I've had other guests do that and that's about like half half and half half an hour so let's see.

Benat Mencia: 55:12

Actually fun fun fact I realized that it helps a lot if there is an intro call with runners at this stage at least where you know we don't have a world class self-service onboarding so um for every new runner I always send them an email and tell them offer them to have an intro call and this is usually very useful for many runners. Not everyone wants to do it but yeah happy to talk to anyone that would like to talk to me.

Jason Koop: 55:43

When pe when you've offered that to people I don't think I've told you this before when you've offered that to people I've had maybe four or six people who I who I know or I've met say is this real or is this just some scammer like the kid like the king of Syria like you know wants to wire you a bunch of money give them your bank account numbers like those kind of old school scams they actually who's this who's this Binette guy is he real and are you associated it's like he's very he's very much real.

Benat Mencia: 56:12

Okay so we'll put it all in the show notes man uh I'll turn the floor over to both of you guys to wrap it up what are you like what are you looking forward to the mission of of Coupe A is to build the running app that will serve hopefully all all runners down the road and that yeah as I said we want to give access to top coaching to everyone without money or accessibility being a limitation so so we'll be working hard towards that objective and I have the conviction we'll get there. It's just a matter of sitting down and doing it. The technology is ripe we have the best coaches here we just need to sit down and execute and we're doing that as I said I think that at least 95% of the work remains to be done but we'll keep working until we get there.

Ryne Anderson: 57:04

I'm gonna say raise the standard raise the bar of coaching I'm glad you talked for a while because I was gonna say a much more harsh way but people don't know what they don't know and they they get a pre-made plan they get their buddy to make the plan and oh this is cool I have organization but I think I think athletes can be served much much better than they realize with either an experience they're currently having or they aren't aware of what coaching looks like. So I think I'm looking forward to it raising the bar and challenging other coaches to like care about their athletes care about their coaching practice and deliver a service and product that these athletes are like oh I got to this race and I'm confident in it. I understand why I'm doing these things. Yeah.

Jason Koop: 58:07

I couldn't have said it better myself. I'm grateful to both of you guys can't wait to see how this weekend unfolds first off because I know we got a lot of a lot of really important athletes that are racing across all the distances but more importantly I can't wait to see how this unfolds after UTMB and uh maybe we'll make a little bit more progress on that 95% progress bar. Slowly but surely all right thank you thanks my friends there we have a much week to the minute and Ryan you guys have been amazing at pulling this together and the job's not done yet and we keep integrating this thing every single week and it keeps getting better and better and better and better and I remember the first couple of revisions of the actual product UI UX and left a lot to be desired and still there's a lot of work to do there but it really left and left a lot to be desired when we first wanted to place where we can look at it and go hey this does a really good job and cannot remark enough description itself which is what most people find the most value and is remarkably accurate in representing what I would do with any athlete and that's how it was always intended to be designed. So once again channel mainly to Banette and Ryan for getting all of this together just done a remarkable job remarkable job with the product if you guys check it out links are in the links in the show notes to it. I'd also be remiss to not to mention that it's been a hot minute since I've produced the podcast and what I'm starting to find is that as my time gets more limited this becomes one of the things that in addition Into that, let's face it, we get our information differently these days, and that value proposition is going to continue to change as technology rapidly evolves. And what I'm finding is trying to squirrel away an hour or two of my time to produce a podcast, and squirrel away an hour or two of guest time to produce a podcast is just getting more and more challenging, particularly because this is an information-based podcast, it's not an entertainment podcast. I don't make any bones about that. But what I will say is I've always been grateful for the opportunity to get in front of you guys on a somewhat frequent basis and hopefully deliver some knowledge to everybody for the betterment of athletes and coaches out there. That's not something that I take for granted. Um, I've always considered myself very fortunate to have that type of influence and to be able to uh produce content kind of for the betterment of the entire community. Uh it's not lost on me. So thank you guys. Uh thank you, thank you, thank you for all that and all of your attention and all of your support over the years. I'm gonna continue to bring it in other forms of content, and this app is just uh one uh one piece of that. So I'm not going anywhere, it's just gonna be in a much different format. Alright, folks, that is it for today. Go check the links in the show notes. Hope you guys go check the app out. Super psyched about it. And as always, we will see you out on the trails, maybe perhaps coached by Coupe AI.