How to create your own AI performance coach: Optimizing your unique nutrition, recovery, and injury management needs | Lucas Werthein (Cactus)

0:00I have always been super active into sports, really constantly pushing myself to the limits of what my body can do. And naturally, that means injuries, right? And for me, it became a little bit too much. And so as soon as Chachi PT launched, I started experimenting with aggregating this data so that I can get a more clear synthesis of what I can do to actually optimize the body.

0:23Lucas Werthein:One of the things that I have never seen anybody do yet, I've seen a lot of folks drop in their daily workouts or their food diaries, but I have not seen MRIs and imaging here. And what important context for somebody who's an athlete to say, not only is this how I'm performing on an output basis, but this is actually like the structural setup under the hood. So it's really interesting, that combination of data into these files. I'm wanting to demand of my body to feel like 25 in a 40-year-old's body. And it's interesting to think, what if every person could have a coach that organizes all this action into clarity, right?

1:00And part of what we've been talking about is that not everyone is looking for this type of performance. Most people don't need six packs or match prep, but they could use help with the basics, right? Eating less, processed food, sleeping better, moving more. And I think an AI coach could meet people where they are and actually give them the necessary nudges and contextualization of information that they need to be a better version of themselves.

1:26Lucas Werthein:welcome back to how iai i'm claire vo product leader and ai obsessive here on a mission to help you build better with these new tools today we have lucas worthing head of technology at cactus who has done work for basically everybody apple coca-cola mtv and even beyonce herself but today we're not going to talk about product development we're going to talk about how lucas has built a wellness coach inside ChatGBT to optimize his nutrition, his workouts, and keep him feeling 25, even though he's a little bit older than that. This is a really fun episode with some practical insights for people just trying to make their lives better with AI.

2:06Lucas Werthein:Let's get to it. This episode is brought to you by WorkOS. AI has already changed how we work. Tools are helping teams write better code, analyze customer data, and even handle support tickets automatically. But there's a catch. These tools only work well when they have deep access to company systems. Your copilot needs to see your entire code base. Your chatbot needs to search across internal docs. And for enterprise buyers, that raises serious security concerns. That's why these apps face intense IT scrutiny from day one. To pass, they need secure authentication, access controls, audit logs, the whole suite of enterprise features.

2:46Lucas Werthein:Building all that from scratch? It's a massive lift. That's where WorkOS comes in. WorkOS gives you drop-in APIs for enterprise features, so your app can become enterprise-ready and scale up market faster. Think of it like Stripe for enterprise features. OpenAI, Perplexity, and Cursor are already using WorkOS to move faster and meet enterprise demands. Join them and hundreds of other industry leaders at WorkOS.com. Start building today. Lucas, welcome to How I AI. Thanks for being here. Thank you. Glad to be here. And thank you so much for inviting me to be on this wonderful podcast and show. What I'm excited about is so much of How I AI so far has really been How I AI for business.

3:35Lucas Werthein:And I really want to show your use case because it really is a personal how I AI and how you can actually use AI in your daily life to really make improvements and build something for yourself. And so tell us about the story that got us to what you're going to show us today. I have always been super active into sports and would consider myself a pretty competitive person. And so that means really constantly pushing myself to the limits of what my body can do and how much I can deal with in terms of the stress of these sports. And naturally, that means injuries, right? And so I've had surgeries on my foot, two surgeries on my knees, surgery on my shoulder.

4:31older and this is through through various sports from surfing uh to Muay Thai uh to playing tennis weightlifting and kind of changing it up over the years as the injuries come and needing to move into these sports and we were you know joking about this before the show but obviously as we enter 40, things start becoming a little bit more dire and you start paying attention, more attention to how your body feels and reacts daily to the things that you didn't feel before. And I started becoming really obsessed with how I could optimize my body. You know, I'm 40 years old i'm running a company i play competitive tennis i lift weights and i'm recovering from all these old injuries and i'm trying to keep up with these teenagers on the tennis court playing these amateur tournaments and running around and and i'm i'm wanting to demand of my body to fill to feel like 40 um to feel like 25 sorry uh in a 40 year old's body and you know data is so siloed um and to make sense of everything that people tell you that professionals tell you and put it together is actually really hard right you get blood tests you go to the nutritionist you go to the physical therapist um you get data from your world you know nutrition plans in body scans and for me it became a little bit too much and so as soon as As the chat GPT launched, I started experimenting with aggregating this data so that I can get more, a more clear synthesis of what I can do to actually optimize the body, right?

6:29Because the problem isn't the lack of data. The problem is the lack of synthesis and putting it all together. And I started having a few breakthroughs, actually. And it started helping me feel better and perform better. and I just started using it on a daily basis. So, you know, it came from a need of getting injured and trying to perform and getting back on the horse to now actually having interesting technologies that are allowing me to have really, really specific actions that I can take to actually perform better.

7:07Lucas Werthein:And what I want to reflect on before we get into actually what you built, which is going to be really interesting to see is, you know, you strike me as a person and you've described yourself as a person that is pretty proactive about seeking out data, seeking out advice, going to medical professionals, getting different advice, reading. And so it's not that you're not informed. It's not that you don't have access to experts. But for all this data and all this effort and all this access, you were still struggling a little bit with with some things here and there. And it's pretty amazing to me that what you're telling me is, you know, even given that whole portfolio of things that I've put against my my body and my wellness goals, this AI tool that I built was actually one of the things that helped me unlock a couple of things that had been bothering me for for a really long time.

7:58Lucas Werthein:So I'm really interested that, you know, that last mile of optimization is really being driven by this tool that you built. And it's pretty cool to see somebody who is a deep expert still get a lot of value out of going even further. It's a really interesting conversation because I think we all see it in our numerous interactions in the field of health and wellness. you know you were describing that you you do a lot of pt i'm dealing with an elbow injury right now and i was having a conversation with my pt today and they were telling me about a patient that had to have surgery for their elbow after a while and i said you know it's really interesting because the the doctor makes the diagnosis you guys are treating the patient but this person needed to go into surgery because there's a missing link.

8:54There wasn't someone looking at the sky stroke and saying, well, you need to change your tennis grip like this, or you need to change essentially a biomechanics specialist. Right. And, and, and to me, that's really interesting because there, there is always a lack of communication and the information is a little bit siloed. And I think that what I'm about to show when you start thinking about the possibilities of how this can scale even to not through performance you know we're talking about the edge of the edge of the edge of trying to gain a little bit to to be better um but we're gonna i can talk more about that but i i think it's really interesting how you know essentially this is a performance strategist right it's trained to personally think about my joints optimize my energy extend my peak and you'll see that it answers me filtered through rules i've created um and that helps me sort of compile all this information that is usually really disparate

9:55Lucas Werthein:and really separate but yeah okay so let's actually let's go ahead in and show it because i'm really interested to see how you got to something that meets your standards which from what I can hear are quite high. So you're going to pull up your screen and show us this well-coached GPT that you built. Yeah. Well, let's get into it. Let me dive into this. So when I configured this GPT, I set it a few files that were important for it to have the context of what I wanted information to be reflected on, right? And so here you'll see that it has an x-ray of my left knee, my left knee, my right knee.

10:39It has my physiological cycles. This is a CSV file coming in from whoop data on my journal entry. So what I described in my day today, am I stressed? Do I have anxiety? Did I sauna? Did I do compression therapy? My workouts that are logged on a daily basis and essentially my strain and how hard I work and my sleep data on how much good sleep that i get rem sleep deep sleep so a lot of lot of data being fed into into here in addition to that i mentioned i had a couple of knee surgeries so it has the mri of my knee pre-surgery post-surgery and it has a few blood exams from uh this year and last year so three different blood exams so it can compare the evolution of the tests and how I'm doing.

11:33In addition to a nutritional plan from a nutritionist slash dietitian that helps me think about food as fuel and how I can perform better based on fuel. And an in-body scan that essentially measures percentages of fat and muscle and distribution across the body. And so it's using all these files to think about, to have context around myself. And so that was an important element to be able to gather this data manually inputted into this GPT.

12:09Lucas Werthein:What I think is interesting about this for folks that are listening or watching are a couple of things. One is all this data is in all these different formats, right? So you have imaging data from MRIs and x-rays. You have like semi-structured data from sleep from a wearable. You have blood tests in PDF form where it's got to parse a bunch of stuff, a textual nutrition plan. And what I love about AI now for people that maybe haven't built some of these tools for themselves is you can just dump all that data in. You don't have to worry about is it clean? Is it organized? Is it structured? Just put it in.

12:45Lucas Werthein:And then one of the things that I have never seen anybody do yet, I've seen a lot of folks drop in like their daily workouts or their food diaries, but I have not seen MRIs and imaging here. And what important context for somebody who's an athlete to say, not only is this how I'm performing on an output basis, but this is actually like the structural setup under the hood. So it's really interesting, that combination of data into these files. And then how is this GPT set up to actually work? What are the instructions? Would you walk us through that? Yeah, just to add something, I think you mentioned something really interesting around how the data is structured, and it's also coming in from different languages, right?

13:28Because I spend a lot of time in Brazil, some of my exams are in Portuguese. A lot of them are in English, but some of them are in Portuguese. And so I don't need to worry about that either. I just dump it in and it process that information. And so I think that's also a valid point about how easy it is now to port that data into something that can unify it. Yeah, you're absolutely right. Let me tell you about how I configure this, right? And so I'm telling you to act as my performance strategist and health optimization coach. It has access to my physiology, labs, imaging, wearables. and I wanted to coach me like I'm a high performance operator.

14:12That's really important. I'm not trying to be a professional athlete. I wanted to understand that I want to perform, but I'm balancing tennis, lifting, recovery, and mainly running a company, which takes the majority of my time. And I don't want to be the most competitive person in the world. I don't want to be the best. my main objective is for it to safeguard my my joints and to amplify my output and to extend my peak i want to feel healthy and pain free that's super important but i do want to perform like a 25 year old in a in the body of a 40 year old so i give it that that that instruction um when i share my prompt um i wanted to interrogate it through my context right looking at my my blood exams, my scans, my WUP, other specific information that it has.

15:08I wanted to flag what we call red and yellow zones, right? We see this in a lot of wearables or early signs of overtraining, under fueling, inflammation, and it's important. I want shy ROI actions, no fluff, no hacks, nothing that hasn't been proven. and I want to be kept inside this zone where I'm moving pain-free. I can play at high-alpha tennis. I don't break down.

15:38Lucas Werthein:I want to reflect to you something that, one, I think is personally interesting, and two, I think is interesting from a prompt perspective. So, you know, the top of your prompt is very common. You act like a blank. You are a blank, that sort of instructive point to the LLM to give it a role. What I think is really interesting about this last bullet point here is it's the opposite side of that coin, which is at the end of this, I want to be X, Y, and Z. And so, you know, say you're a performance coach. That's the kind of your role. My role is I'm running a company. I want to feel 25 in a 40 year old body and I want to be rested, move pain free and play tennis like it's a very clear input output structure.

16:24Lucas Werthein:and then the human in me wants to reflect these are very reasonable nice goals so again you know we're talking about this like hyper optimization and at the end of the day you want to wake up you want to feel good you want to engage in your company and you want to be able to play the sport that you want to play and so i think the kind of idea of like a role and then a really realistic outcome for yourself is a nice framing for something like this kind of personal coach prompt It's absolutely and super important for it not to tell me to go get ozone therapy or to go sit inside a hyperbaric chamber, which may work.

17:04I'm not necessarily giving it a ding, but I do want things that are accessible in my day to day and that are proven, that are scientifically backed. That's really important to how I wanted to think about the recommendations.

17:22Lucas Werthein:Yeah. And the other thing I see a lot when people prompt is they go to these extremes where they're like, you are the best in the whole world and you're going to make me the most elite, blah, blah, blah. And, you know, what I like about this is you're saying I'm getting good outcomes by like pulling in the bounds of reason on both sides of those and having reasonable roles and reasonable expectations. So it's a really good insight from a prompting perspective. Uh, let's go down and show me, show me what you optimize for. Yeah. So, so I think part of this is the context that, that I mentioned of how, for example, it has my nutrition plan.

17:57Right. And so when you think about performance, so much performance is about how you eat and how you rest. And so having the basis of how I wanted to eat has been absolutely fundamental for it to think about the recommendations. Right. And so I wanted to stick to my nutrition plan unless there's data, a driven reason to adapt. So this is all based on fueling and avoiding inflammation, right? I wanted to prioritize energy, stable glucose, low inflammation, and muscle retention. Number two, thinking about training and load management, you can't overtrain. If you overtrain, you burn out. And so I needed to think about balancing strength, endurance, and mobility, because I need to protect my knees and my shoulders and my joints, which have been messed with in surgery.

18:51And so when thinking about recommendations, we can't overload the HRV. We can't be outside of sort of the readiness score. And I needed to help me pull back because I will overtrain. I do want to get better and better and better, right? And so one of the things we hear about the most when studying and thinking about performance is people don't pay enough attention to recovery and to rest. And so this is super important for me. The third one, again, going back to recovery and regeneration is sleep is the main factor here, right? And yes, PT, mobility, sauna, cold, massages, mindfulness need to be important and not optional.

19:42They're part of the training cycle because they're part of recovery. So I need recommendations of how to have it give me nudges so I can maintain those up on my day today. And lastly, this idea of tracking and feedback loops. It's integrating data across in-body labs, diet, journal entries, and I needed to cross-validate the decisions and not recommend something that is not aligned with what I have said it, just like from pulling some random thing from the internet.

20:14Lucas Werthein:One of the things I want to reflect on here that I've said in other podcasts, more in sort of a business context, is when people are designing these GPTs, I really read these prompts and I'm like, oh, they reflect like the perfect employee or they reflect the perfect team. And when I'm looking at this, this sort of reflects how in an ideal world, all these experts that are supporting you, your doctor, your PT, your coach, would all be fully integrated, aligned on a strategy, like consistent in their recommendations, data backed. But the reality is when you bring a team of individual experts together, one, they're all going to come with their unique point of view.

20:57Lucas Werthein:Two, it's very hard just just tactically to stay aligned on recommendations and kind of resolve things across the board. And so what I like about this is, you know, ideally, you'd be able to sit all those experts in a room with you and say, hey, hey, guys, this is how I want you to take care of me. But because that's not actually practical, what you're doing is bringing some of the data and insights those people have, your own ambitions and goals, and then sort of like putting it in the system that will operate optimally for you over time. Absolutely. And we'll talk more about the vision and a little bit of provocation of where I think this will go and how this is a prototype of something that will be much bigger and that many, many practitioners, health systems, physicians will adopt in the future.

21:48Lucas Werthein:Yeah. Okay. And then you do what everybody does, which is you give it a bunch of stuff to do and then a bunch of stuff to not do. Exactly. So hard, hard boundaries, right? No pushing past the volume and intensity when metrics show under recovery. My whoop is showing a red or yellow. I can't go train hard. Don't get any supplements that are unknown. Don't, you know, don't tell me to go take uh creatine or anything that although super popular at the moment, right? That, that we, we don't know is absolutely measurable scientific backed and has roi they'll give me novelties um stick to what actually works to perhaps even ancient data and act on red flags uh if if i tell you there's a lot of soreness or low hrv or decreased sleep quality that means perhaps i'm getting sick don't don't push when i can't push yep great and i think this again for people i'm just kind of giving the meta commentary which is it's a very common prompt structure for anybody trying to build something for themselves it's like give you a role give the gpt role give it a goal give it some input and data give it an anti-prompt i say which is like tell it what not to do and then i like that you're closing on like the the check that it's all following the rules and this is how I want you to respond piece.

23:13Lucas Werthein:So we can go through that really quickly and then maybe show a couple examples. Totally. So values, right? Precision, energy, adaptation, kinetics, all about movement. It's all about energy. It's all about precision. And then the tone, right? Like a coach, be clear, tactical, no fluff, no lectures. Connect the dots. That's super important about everything that we're talking about. And prioritize what matters this week, not vague, long-term theory around what's possible. Great. And so, you know, it's very clear you put a lot of thought into this. Did you also use ChatGPT to help you like craft the structure of this prompt?

23:51Many times.

23:52Lucas Werthein:Yeah. I can tell from the emojis. From the emojis. You can always tell. This podcast is supported by Google. Hey, everyone. Shrestha here from Google DeepMind. The Gemini 2.5 family of models is now generally available. 2.5 Pro, our most advanced model, is great for reasoning over complex tasks. 2.5 Flash finds the sweet spot between performance and price. And 2.5 Flash Lite is ideal for low latency, high volume tasks. Start building in Google AI Studio at ai.dev. Okay, awesome. So this is a great deep dive into instructions and I hope people are paying attention to it because one, like what a great prompt.

24:33Lucas Werthein:Thank you for sharing. It's super useful. And two, just the structure of it is very classically well set up for setting up a GPT. So whether it's this topic or another one, I think people can learn a lot from how you've set it up. So how does it work? Show me what are common things that you would do with this GPT. Yeah, let me give you an example. I'll give you a few fun ones here. Um, so this morning I, I woke up and my wife told me that we have a birthday dinner that we need to attend. Um, good friends of ours gonna celebrate an amikase, uh, birthday dinner, which means plenty of rice and sake.

25:16And so how should I manage my day to balance the fact that I'm gonna indulge in the evening? And this may be simple, but actually it's really interesting that it thinks about how to change my actual diet. Right in the morning, I would usually eat something post training, but here it's saying basically like eat only protein, minimal carbs. At lunch, it's saying the same thing. And so it's guiding me how to go along my day based on the fact that I'm going to indulge in the evening and have something that's going to be a little bit different and not necessarily feel destroyed. And so it's prepping me for something that's going to happen.

26:04And it's really useful because I don't have to think about it. I prompted, I asked it, it gives me a response and I try to adapt. Right. And so, okay, great. It told me to have no carbs. I took a picture of my breakfast, a little bit of eggs, avocado, coffee. And then it feeds me information about, okay, that's fantastic. Got a little bit of pepper for inflammation. You know, I'm very cognizant also that this is most people, not what most people need, right? If we think about most people, they perhaps just need to move a little bit more, sleep a little bit better. not eat processed food. And I'm very cognizant also that this is for something very specific that I'm personally looking for, but it's very useful to how I can then program my day and how I can think about the next day as well.

27:01Lucas Werthein:Well, I think the other thing is, yes, your goals are maybe a higher level of what the kind of like baseline person might have for their own performance health goals. And at the end of the day, the like, I'm going to a birthday party later and I don't want to feel crummy tomorrow. Are there any things that I can do before this birthday party to keep me from feeling crummy is like a very applicable problem. I think one. Second thing is, you know, it's a really on demand coaches and nutritionists and experts are expensive. They are inaccessible to a lot of people. And just this sort of short loop, like, am I doing the right thing?

27:46Lucas Werthein:You know, give me an answer. And I like this piece that you showed us, which is like, look, I did it. And you get like a very short blip of a good positive feedback loop can actually help people reinforce habits that I think compound over time. And so, you know, I do think something like this makes some of these like tactics, you know, that sound very basic, a little bit more accessible, a little bit easier to implement and gives you sort of an on-demand feedback loop that as social human beings, we respond to. And so I don't think it's kind of too far aground from what most people would find useful.

28:24I think that's a great point. And the fact that you now have a coach in your pocket is super interesting because things change. another scenario I fed it the other day is I said I was going out to dinner I prepped the day but there was a change of plans and we went to a party and we were going to drink and have a bunch of gin and tonics and get home at 3 a.m and I didn't need to think so much about what I needed to do because I prompted it gave it that information and then it reacted based on that change of plan And so having that be accessible now to so many people, whether you are able to make that change at home because you have access to food, but even if, you know, you need to go eat at Chipotle and it can tell you the things that you can eat or that you should order at Chipotle, because that is your only option.

29:16I think is a super interesting point of just how accessible good information for you to be optimal is becoming.