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

[00:00] I 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. One of the things that I have never seen anybody do yet, I've seen a lot of folks drop in their [00:30] for 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 [01:00] Right. And 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.

[01:26] Welcome back to How I AI. [01:30] 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 AI and AI [01:40] 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 chat GBT to optimize his nutrition his workouts and keep him feeling 25 even though he's a little bit older than that [02:01] This is a really fun episode with some practical insights for people just trying to make their lives better with AI. [02:06] Let's get to it. [02:07] 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. [02:21] 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. [02:46] 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.

[03:16] today. [03:18] 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 [03:33] How I AI for business. 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. [03:55] I have always been super active into sports and and. [04:01] would consider myself a pretty competitive person. And so that means really constantly pushing myself on that. [04:09] to the limits of what my body can do and how much I can deal with in terms of the stress of these sports. [04:19] on [04:20] Naturally, that means injuries. [04:22] And so I've had surgeries on my foot, two surgeries on my knees, [04:29] surgery on my shoulder. And this is through various sports from surfing to Muay Thai to playing tennis. [04:41] weightlifting. [04:42] and kind of changing it up over the years as the injuries come and needing to move into sports.

[04:48] We were joking about this before the show, but obviously as we enter 40, things start becoming a little bit more dire, and you start paying more attention to how your body feels and reacts. [05:05] daily to the things that you didn't feel before. [05:09] And I started becoming really obsessed with [05:13] how I could optimize my body, you know, um, [05:18] 40 years old, I'm running a company, I play competitive tennis, I lift weights, and I'm recovering from all these old injuries. [05:26] And [05:27] I'm trying to keep up with these teenagers on the tennis court, playing these amateur tournaments and running around and [05:34] And I'm wanting to demand of my body to feel like 40. [05:40] I feel like 25, sorry, in a 40-year-old's body. [05:44] And [05:46] You know, data is so siloed. [05:49] 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, you get data from your world. [06:04] nutrition plans, in-body scans, and [06:08] For me, it became a little bit too much. And so as soon as [06:13] the chat GPT launched, I started experimenting with aggregating this data so that I can

[06:22] Get more. [06:24] a more clear synthesis of what I can do to actually optimize the body, right? Because the problem isn't the lack of data. The problem is the lack of synthesis and putting it all together. [06:34] And I started having a few breakthroughs, actually, and it started helping me [06:40] feel better and perform better. And I just started using it on a daily basis. So [06:46] It came from a need of [06:50] getting injured and trying to perform and getting back on the horse to now actually [06:55] having interest in technologies that are allowing me to [06:59] Tup. [07:00] that have really, really [07:03] specific actions that I can take to actually perform better. 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, [07:13] You strike me as a person and you've described yourself as a person that is pretty proactive about... [07:18] 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 information. [07:31] experts, but for all this data and all this effort and all this access, [07:37] 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, [07:45] even given that whole portfolio of things that I've put against my body and my wellness goals, [07:50] 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. So I'm really interested that, you know, that last mile of optimization.

[08:04] 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. [08:15] It's a really interesting conversation because I think we all see it [08:20] in our numerous interactions in the field of health and wellness. You were describing that you do a lot of PT [08:30] 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. [08:42] So the interesting because the doctor makes the diagnosis, you guys are treating [08:48] the patient, but. [08:49] this person needed to go into surgery because there's a missing link. There wasn't someone looking at this guy's stroke and saying, well, you need to change [08:58] your tennis grip like this, or you need to change essentially a biomechanics specialist, right? [09:03] And to me, [09:06] That's... [09:07] really interesting because there is always a lack of communication and the information is a [09:15] What I'm about to show, when you start thinking about the possibilities of how this can scale, even to not [09:22] true performance you know we're talking about the edge of the edge of the edge of trying to gain a little bit to to to be better [09:30] I can talk more about that, but I think it's really interesting how essentially,

[09:36] This is a performance strategist, right? It's trained to personally think about my joints, optimize my energy, extend my peak and [09:45] you'll see that it answers me filtered through rules I've created. [09:50] Um... [09:51] And that helps me sort of compile all this information that is usually really disparate 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... [10:03] got to something that meets your standards, which from what I can hear are [10:08] are quite high. So you're going to pull up your screen and show us this well-coached UPT that you built. [10:13] Yeah, well, let's let's get into it. Let me let me dive into this. So [10:19] When I configured this GPT, I set it a few files that were important for it to have the context of what I wanted. [10:29] information to be reflected on, right? [10:32] Here you'll see that it has an x-ray of my left me [10:37] my left knee, my right knee. It has my physiological cycles. This is a CSV file coming in from Whoop data. [10:46] on my journal entry. So what I described in my day-to-day, 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. [11:02] and my sleep data on how much [11:05] 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.

[11:13] I mentioned I had a couple of knee surgeries, so it has the MRI of my knee, pre-surgery, post-surgery. [11:21] And it has a few blood exams from... [11:26] this year and last year. So three different blood exams. So it can compare the evolution of the tests and how I'm doing. [11:33] In addition to a nutritional plan from [11:38] a nutritionist slash dietitian that helps me think about food as fuel and how I can perform better based on, on fuel. [11:47] 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, [12:01] to have context around myself. And so that was an important element to be able to gather this state, are manually inputted into this GPT. [12:09] What I think is interesting about this for folks that are listening or watching are a couple things. One is... [12:14] All this data is in all these different formats, right? So you have... [12:19] imaging data from MRIs and x-rays. You have like semi-structured data from sleep from a wearable. [12:27] You have blood tests in PDF form where it's got to parse a bunch of stuff, a textual nutrition plan. [12:34] 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. And then one of the things that I have never seen anybody do yet, I've seen a lot of folks...

[12:50] drop in like their daily workouts or their food diaries. But I have not seen [12:56] 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, under the hood. So it's really interesting that combination of, 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? [13:19] 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? Because 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 [13:38] 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. [13:53] Let me tell you about how I configure this. [13:57] I'm telling you to act as my performance strategist and health optimization coach. It has access to my physiology, labs, imaging, wearables. [14:08] And I wanted to coach me like I'm a high performance operator. That'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, I'm balancing tennis.

[14:22] lifting, recovery. [14:24] and mainly running our company, which takes the majority of my time. [14:28] I don't [14:30] want to be the most competitive person in the world. I don't want to be the best. [14:35] My main objective is for it to safeguard my joints and to amplify my output and to extend my peak. I want to feel [14:44] healthy and pain-free. That's super important. But I do want to perform like a 25-year-old in the body of a 40-year-old. So I give it that instruction. [14:54] When I share my prompt, I wanted to interrogate it through my context, right? Looking at my blood exams, my scans, my WUP, other specific information that it has. I wanted to flag what we call [15:11] red and yellow zones, right? Um, we see this in a lot of wearables or early signs of over-training, under-fueling, inflammation. And it's important. I want shy ROI actions. Um, no fluff, no hacks, nothing that hasn't been proven and I wanna, [15:30] be kept inside this zone where I'm moving pain-free, I can play at high-alpha tennis, I don't break down. - I wanna 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

[15:58] 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 [16:06] X, Y, and Z. And so [16:09] You know, say you're a performance coach. That's the kind of your role. My role is I'm running a company. [16:16] I want to feel 25 in a 40 year old body and I want to be rested, move pain free, [16:21] and play tennis. Like it's a very clear input output structure. 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. [16:50] Thank you. [16:51] Absolutely. And super important for it not to tell me to go get [16:56] ozone therapy or to go sit inside a hyperbaric chamber, which may work. I'm not necessarily giving it a ding. But I do want things that are accessible in my day to day and are proven, that are scientifically backed. That's really important to how I wanted to think about [17:19] I don't know. [17:20] the recommendations. [17:22] Yeah. And the other thing I see a lot when people prompt is they go to these extremes where they're like, you are...

[17:28] 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 [17:46] Let's go down and show me what you optimize for. [17:49] Yeah, so, so I think part of this is the context that, that I mentioned of how, for example, it has my nutrition plan. Right. 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. [18:13] to my nutrition plan unless there's data. [18:16] a driven reason to adapt [18:18] um [18:19] 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, [18:32] Thinking about creating and load management. [18:35] 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 [18:49] mess with in surgery. And so [18:53] When thinking about recommendations, we can't overload the HRV, we can't

[19:00] be outside of sort of the readiness score. Um, and I needed to help me pull back because I will overtrain. I, I, [19:07] I do want to get better and better and better. Right. And so, [19:12] One of the things we hear about the most when studying and thinking about [19:15] um performance is people don't pay enough attention to recovery and to rest and so this is super important for me [19:23] The third one, again, going back to recovery and regeneration is, [19:28] uh, [19:29] Sleep is the main factor here, right? And yes, PT, mobility, sauna, cold, massages, mindfulness, [19:37] need to be [19:39] important and not optional. They're part of the training cycle because they're part of recovery. So. [19:45] I need recommendations of how to have [19:48] It gives me nudges so I can maintain those up on my day to day. And lastly, these, this idea of, of tracking and feedback loops, it's integrating data across whoop in body labs, diet. [20:01] journal entries and I needed to cross validate the decisions and not recommend something that is not aligned. [20:09] um with what i have said it just like from pulling some random thing from the internet [20:14] 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.

[20:32] This sort of reflects how, in an ideal world, [20:36] All these experts that are supporting you, your doctor, your PT, your coach, your [20:41] would all be fully integrated. [20:44] aligned on a strategy, like consistent in their recommendations, data backed. But the reality is when you bring a team of individual experts together, [20:54] One, they're all going to come with their unique point of view. Two, it's very hard just tactically to stay aligned on recommendations and kind of resolve things across the board. And so what I like about this is... [21:06] you know ideally you'd be able to sit all those experts in a room with you and say hey hey guys [21:11] 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 to, [21:20] your own ambitions and goals and then sort of like putting it in the system that will [21:24] operate optimally for you over time. [21:28] Absolutely, and we'll talk more about [21:30] vision and a little bit of provocation of where I think this will go and how this is a prototype of something that, [21:39] Um... [21:40] will be much bigger and that many, many [21:43] I mean... [21:44] practitioners, health systems, physicians will adopt in the future. [21:48] 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. Yeah. [21:55] Exactly. Hard boundaries. [21:59] No pushing past the volume and intensity. One metric 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.

[22:13] uh, [22:14] creatine or anything that, although super popular at the moment, right? That, that we, we don't know is absolutely measurable scientific. [22:22] backed and has ROI. [22:25] They'll give me novelties, stick to what actually works to perhaps even ancient [22:31] data, [22:32] And act on red flags. 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 push when I can't push. [22:45] Yep. [22:46] Great. [22:48] 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. [22:57] Give the GPT a roll. Give it a goal. [23:00] Give it some input and data. [23:02] 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 check that it's all following the rules. And this is how I want you to respond piece. So we can go through that really quickly and then maybe show a couple examples. [23:16] Totally. So values, right? Precision, energy, adaptation, kinetics, all about movements, all about energy, it's all about precision. And then the tone. [23:26] Write like a coach, be clear, tactical, no fluff, no lectures. Connect the dots that's super important about everything that we're talking about. [23:35] and prioritize what matters this week, not vague long-term theory around what's possible. [23:43] Great. And so...

[23:44] 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? [23:51] Many times. Yeah. I can tell from the emojis. From the emojis. You can always tell. [23:56] This podcast is supported by Google. Hey everyone, Sreshta 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. [24:26] 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. Thank you for sharing. 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 set it up. So. [24:48] how does it work show me what what are common things that that you would do with this gpt [24:54] Yeah, let me give you let me give you an example. I'll give you a few fun loans here. So. [25:00] This morning, I woke up and my wife told me that we have a... [25:05] a birthday dinner that we need to attend. [25:09] Good friends of ours are going to celebrate an amikase birthday dinner, which means plenty of rice and sake.

[25:16] And so how should I manage my day [25:20] to balance the fact that I'm going to indulge [25:23] in the evening. [25:26] This may be simple, but actually it's really interesting that [25:31] It thinks about [25:33] 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. [25:56] and have something that's going to be a little bit different and not necessarily feel destroyed. And so it's prepping me. [26:02] for something that's going to happen. And 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? [26:12] 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. Um, 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. [26:30] All right. [26:31] This is... [26:34] Most people... [26:36] Um, not what most people need, right? If we think about most people, they perhaps just need to move a little bit [26:43] More. [26:44] sleep a little bit better,

[26:46] not eat processed food. [26:49] 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. 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. Yeah. [27:12] And... [27:13] At the end of the day, the like, I'm going to a birthday party later... [27:16] And I don't want to feel crummy. [27:18] tomorrow. [27:20] 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. [27:31] You know, it's really... [27:32] on-demand coaches and nutritionists and experts, [27:37] are expensive they are inaccessible to a lot of people and just this sort of short loop like am i doing the right thing [27:46] You know, give me an answer. [27:48] 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. [28:00] And so, you know, I do think something like this makes... [28:05] some of these like tactics, you know, that sound very basic. [28:08] 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.

[28:24] I think that's a, that's a great point. And the fact that you now have a coach in your pocket is super interesting because things change. Um, [28:35] Another scenario I fed it the other day is [28:39] 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 3:00 AM and [28:49] I didn't need to think so much about what I needed to do because I prompted it, gave it that information. [28:54] And then it reacted based on that change of plan. And so having [28:58] 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 i think is a super interesting point of just how [29:20] accessible [29:21] some good information for you to [29:25] be optimal is becoming [29:28] So I would love to see. I think this is a really great sort of like day-to-day... [29:32] practical example, [29:34] I'm curious if you have anything that shows a little bit more of the kind of like physiology side of things. You know, you mentioned a lot at the beginning. [29:41] injuries and protecting joints and making progress. Has any of that come into play in your coaching? You know, we see the nutrition side, but I'm curious if there's anything else there. [29:53] So late. [29:54] um let me show you what i also want to call out for folks that i love as you're scrolling is

[30:00] context changing, content changing. It's like, [30:04] Now I want to talk about nutrition. Now I want to take a screenshot of my workouts. Now I want to do, do this and do that. And, and the chat can kind of adapt to all that information and not need. [30:15] you to follow any rules or any schedule or any structure. So I think that's really interesting. [30:21] And then I love that this is in Portuguese, some of it, and then switches to English. I caught that on the screen share. [30:28] Yeah. [30:30] So I think this one's really interesting. [30:33] I have been dealing with not a tennis elbow, but an elbow injury. And I went to a doctor. I gave it the diagnosis of the doctor. [30:45] Um, I gave it the prescription of physical therapy. [30:49] And basically I talk about my pain. I would talk about my pain on a daily basis and I would take pictures and I would record movies of how I'm feeling pain and basically it would confirm what the doctor [31:02] Amin has said, [31:03] You know, I tell it to doctor discarded tennis elbow. Um. [31:07] And it's like, you know, I've been, I've been off the courts for a week, how much longer? And the doctor has told me and the PT has told me, but I'm trying to test it if, if it's going to say something different and it's saying the same thing and really frustrated. You know, I'm following all the prescriptions. I'm, I'm doing all the exercises, but it's like, it's not, not getting better. And then one day I actually go into PT and it does feel better because of something specific that they did with electrical currents and strength training at the same time.

[31:37] Thank you. [31:38] And so. [31:39] Now I'm prompting it [31:42] to think about if, you know, based on the evolution of the recovery that I've been telling it, will I be able to play this amateur tournament that I want to play on September 18th? And so it's thinking about how many weeks are left, what's realistic, you know, decision checkpoints, um, what it thinks. And then I asked it to put, put everything on the table to think about the recovery, um, [32:06] the recovery process, [32:08] uh, [32:10] plan for how we're going to do this. And honestly, it is exactly the same thing the PT told me, which is really interesting. But, [32:18] It is contextualized in a way that [32:22] I can digest. [32:23] And now sort of the anxiety of me every day thinking, man, is the pain gone? Is the pain gone? Is the pain gone? [32:30] is eased a little bit because I can manage the expectations of what will happen in just a very visual manner that you don't usually get from your PT or from your doctor. And so I'm contributing at this information so it can [32:45] think like them, but perhaps process and synthesize the data a little bit better because it has so much knowledge about [32:53] myself and what I'm doing and how I act. [32:55] Yeah, one of the you know, I want to just go back and reflect on what you just showed us. I think there's a couple of really interesting things here for people to listen to. One is. [33:03] I think people really underuse what you just showed, which is a video or a picture of

[33:09] circling a thing into into chat GBT. I found that that's such a useful [33:16] a useful kind of workflow for folks that are new to AI and not sure what it can do for it. I don't know if this is an appropriate metaphor or not, but I live in a 114-year-old house. It's like very similar to living in my 40-year-old body. And we, you know, we have leaks here or cracks there or bubbles here or whatever. And I'm constantly taking a picture of something, circling it and saying, [33:41] What could this, you know, tell me what this could be. And so you can do that. You know, I have a, it's not tennis elbow. It's I sit at my laptop elbow and put my arm on my desk at a bad angle. I know I do it. But taking that and just saying like. [33:56] I've got pain here. [33:58] not not here not here but like here um what could that possibly be [34:04] It's a really good use case. I think people also don't know... [34:07] A lot of these models can process video really well. And so that is another input you can put in and, you know, kind of do the thing that they make you do at PT, which is like, I can go to here, but not further. I can do this. [34:19] So I think that's a really interesting workflow. I think the second thing that people are using ChatGPT for a lot is just validating expert opinions, not to dismiss expert opinions. [34:31] But you know what? [34:32] My personal doctor is not on demand 24 hours a day. When I leave the office... [34:38] That's about as much as I'm going to get for them. So being able to go back and saying, can you explain this to me?

[34:43] Is there anything else it could be? [34:45] just gives you a more accessible outlet for sort of validating some of that stuff. And then the last thing I would say is often when you leave a certainly in the health profession, but an expert, [34:58] And they give you some takeaways, right? They give it to you in the format they give it to you. They explain it to you verbally. [35:04] They text it to you. They give you a little takeaway sheet. And you're like, no, I want this, but I need it in a day by day plan. [35:12] until September or... [35:14] Can you re-explain this to me in this format? And I also think this ability to grok the same information through a different format by having an LLM translate it. [35:24] it's really useful especially when it's information from an expert where you may not understand the terms or the language or the mechanics [35:33] And so I think those three things are really interesting use cases of AI. You can see them all in just this one flow. [35:39] Thanks. [35:39] I think that's a really [35:41] Fantastic point and [35:43] I think we can extrapolate and think about what what I'm doing here for myself, you know, manually uploading MRIs, whoop data labs just exposes. [35:53] a much bigger opportunity. And AI could be [35:59] a missing synthesizer of personal health [36:03] And I think that [36:04] Healthcare has obviously an interoperability problem and the data is siloed and [36:13] It's interesting to think what, what if every person could have a coach that, that organizes all this.

[36:19] action into into clarity right and [36:23] 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. [36:38] 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 this of themselves. [36:50] Well, what's really funny about this is I'm thinking about you as, you know, a more high performance athlete operator. I was just reflecting, I want to make this for my eight year old wants to get much better at basketball. Like that's his performance goal. I'm like, oh, you could take the same. [37:04] framework, right? He's eight. He's got this much time. You know, we have to walk to the basketball court. [37:11] what what do we do and you can do everything from videos to to um you know pictures all that kind of stuff and so i think it's just really interesting to think about this no matter what your goals are [37:22] setting up a framework like this that can help you day by day [37:26] increment your way to them so before we before we wrap this up you know you've you've kind of um [37:33] Talked about it a little bit. [37:35] But [37:36] you know, what do you think the future of this is? Are everybody going to make this themselves? [37:41] "Do you think there's a product here?" Like what do you think is the gap between I have a GPT and [37:48] everybody can kind of do this on their own.

[37:51] Thank you. [37:51] Yeah, I think there's a really interesting notion when you think about this and you think about how this can potentially scale in the near future. I see a vision in which. [38:03] in five years or less, [38:06] Everyone will have access to a personal AI health coach and not to replace doctors, but to help us show to doctors. [38:15] um show up more in form and to live healthier between visits and to make these micro decisions every day [38:23] Additionally, I do think that the doctors will also have this, and so our AI [38:29] will talk to the doctor's AI [38:32] And it's interesting to think about what are the spaces that need to be designed and what type of interactions will occur once that happens. It's going to be a different world. [38:43] because they will have all the context. They will meet, have all the context. And when the doctor and the patient show up, [38:50] there's just much more clarity. [38:53] to have the conversation. And so... [38:57] I think that the future of health isn't just about medical breakthroughs. It's a lot about synthesis and the ability to turn this overwhelming amount of data into something that's simple and very, very personalized. I also believe in an era of seamless capture. [39:16] you know, we're talking about manually uploading all these things to the GPT.

[39:21] Bye. [39:22] It will be seamless. We will have micro sensors around [39:25] potentially in your bloodstream, tracking information, glucose, hormones, smart fabrics, [39:33] eventually toilet sensors measuring microbiome, hydration, and it will all be ambient, passive and invisible. [39:42] And I think that there is a world where the healthcare leaders will eventually sell their knowledge as trained AI models. [39:50] Imagine having a coach in your pocket that's been trained not just on you, [39:54] but on decades of patient data from institutions like Mayo Clinic or Advent Health. Yeah. [40:01] It's just really interesting to think about what happens when you combine that passive data. [40:08] And you put it next to the guidance... [40:11] that's grounded in the best medical science and personalized to you. [40:16] And I think this also gives the ability for the doctor to get out from in front of the computer and be [40:22] a storyteller and a long-term strategist. [40:25] and to have this hyper-personalized aspect around food supplements habits. [40:30] um, [40:31] And so I think that I laugh because I think that in 10 years, we'll look back [40:37] And [40:38] Talk to all. [40:39] about how much manual effort we've put into health tracking. [40:44] And we'll think about just like no one today types in GPS coordinates into their phone. No one will manually log workouts or meals.

[40:51] and help data will capture itself and we will have [40:55] coaches in our pockets to go back and forth and evolve. And so, [41:00] Just... [41:01] Last words. [41:03] I do think that's important to [41:06] reflect that this is absolutely not about [41:09] Gimmicky. [41:11] It's really a precision tool for [41:14] consistency, I am looking for high ROI choices and it's helping me do that through injuries or food. And I do think that when we think about [41:24] a potential population-level impact [41:27] That's where this becomes powerful to imagine. [41:30] Um... [41:31] what this can be. And it's actually something that [41:34] my company does quite a bit and maybe this is not the place to talk about it, but it's something that I'm seeing a fast adoption to how [41:46] health systems and wellness companies and doctors are thinking about this or i think there's there's a brave new world coming [41:52] Well, I'm excited for that world. I was just thinking, I spent a hot minute in health tech and I was like, where is my... [41:59] FHIR, EPIC, uh, [42:01] MCP that I can plug into. And then I'm going to go wild. But again, I think that is a future. I want to bring it back to people who are maybe watching the podcast saying, how does this apply to me? I'm not an athlete. And just the use cases that I think of are caregiving. [42:17] When you're a caregiver of an elderly relative, you have so much information, so many specialists, so much points of data.

[42:25] that you have that you know you go visit you have pictures you have recordings you have all this stuff and just having this this coach to maybe help with the caregiving journey is one I think kids are super interesting I think athletics is very interesting I think there's probably product market fit for people that apparently there are many on this podcast recording right now that are [42:47] 39 turning 40 but want to be 25. And so I just think like, [42:53] You know, maybe people listening don't have the exact same goals, but the framework really applies to... [42:59] a lot of health care and wellness challenges or or goals for people. So I'm really excited that you showed this to me. It gave me so many. I have so many ideas. I won't bore everybody with my. [43:10] achy hip and elbow, but I have, and sleep issues, which I can attribute to my kids, but [43:16] I think it's really interesting and it's inspired me to want to go build a couple of these for different coaching topics I have. Okay. Well, we are, this was fabulous. I want to do kind of three lightning round questions. One is just, you mentioned a couple other workflows. So this is your favorite, but can you just tell me a couple other maybe that you use in work? Maybe flash us one or two that you think are interesting that people can think about. [43:41] Yeah, absolutely. I'm also happy to share [43:45] the prom so that you and others can configure their own GDPTs. Yeah, we'll put that in the show notes. Cactus is a firm that works at the intersection of physical space and digital technology, and we work for healthcare and wellness.

[44:02] developing [44:04] essentially digital products and thinking about physical space. [44:07] It's an intersection of a consulting firm and a design firm. And so many times we're thinking about [44:12] new products, new services for our clients. And this is an example where [44:17] we have [44:19] taken [44:20] the client, who is a brilliant, fantastic doctor. [44:24] But she is extremely [44:27] busy and so we have synthesized a lot of this information from articles and other podcasts and [44:35] things that are available on the internet, and we have [44:40] setted this information so that [44:43] We can ask it questions when she's unavailable and try to get the work [44:47] to 80 or 90% of where we think she would agree with so that when we present it to her, it's not taking time that could [44:56] be skipped over because we have a lot of how she thinks and how she makes decisions. [45:02] I love this. We have seen one or two synthetic bosses on the podcast. And I love this from a kind of like consulting firm, design firm perspective, which is like synthetic clients are very interesting ways. Because as you said, you know, just going back to everything we've been talking about, your expert's not always available. Your client's not always available. People's time is scarce. But if you know enough about how they might react to information,

[45:32] also give your team insight into how they might react to things. And then, you know, I love these as people make them for their bosses or for their clients. A little pro tip to the bosses and clients out there, you want... [45:46] you want to make this even easier, make one of yourself that you can share with people, because you probably have the best understanding of what's important to you and how things matter. And so it's one of those tips I tell everybody to do is go replicate yourself in a GPT. [46:01] to give your team a first line passive feedback. And then sometimes you end up like me, whereas you build that GPT and then it accidentally becomes an enterprise software business, which is how my company started. So I think this is a great idea. And then one other thing we talked about before the show, and maybe you could just voice over what you do here is you have an AI co-founder as well. So lots of [46:22] synthetic people. Tell us a little bit about that. [46:25] Yeah, I love my co-founders. They're brilliant. And I do not need an AI co-founder. But this is a new world that we're living in. [46:39] the company that [46:40] We Run is a distributed firm. We're no longer in an office and we no longer have access to each other. [46:48] you know, by going and tapping on them and saying, Hey, do you have a minute? [46:53] and you have to schedule a call or column and many times [46:56] You just need a little bit of a partner to think about a potential for me problem.

[47:03] that you would only think with your co-founder. And it's really interesting to load it up with data around [47:10] how your co-founder thinks, how you think, some of the problems that you're going through, [47:14] and being a voice to brainstorm with you so that you're not starting from a blank slate, which is something obviously you hear a lot. [47:23] But it's really helpful. It's almost like business therapy. [47:25] Yeah, well, on that point, I'm laughing to myself because as you were describing this, [47:30] I was thinking, oh, maybe I can save my husband a little bit of trouble if I make a synthetic Claire. And he just double-checked, like, should I say or do this to Claire before I do it? But I do think that we're in this interesting world where, you know, wanting the expertise of someone on demand is not always possible. And AI has made an approximate version of that. [47:56] possible and it's not you know it's not the real thing um but it does help you in in the moment um [48:04] Especially in a distributed world where, you know, you don't want to mention your colleague in Slack at, you know, 11 o'clock when you're thinking about a problem. And so I found similarly that AI can be a really great, again, co-pilot or partner in some of those moments where you just need a quick check. [48:21] Can I just mention, [48:22] Going back just to the synthetic line, just so I don't get in trouble with my clients, it's important to highlight that. [48:30] None of the information that we put in the synthetic clients are proprietary. They're all available on the internet.

[48:37] And so we're not training any of the models with the information that we get from our clients. It's just an exercise that we run through presentations publicly available. Yeah. So, um, [48:49] Yeah. Well, this is awesome. You, you know, I'll wrap with our final favorite question, which is you are clearly an expert prompter, which I love to see. [48:58] But when your coach is giving you bad advice or, you know, the AI is not responding how you like. [49:05] You seem like a very reasonable person, so you probably act quite politely, but... [49:09] What is your go-to tactic? How do you get AI back on track? [49:14] Do you ever find yourself frustrated? What do you do? [49:17] Not frustrated. And I think this ties into how the models have evolved as we see the iteration of models. [49:25] I see definitely an evolution of how it [49:29] hallucinates less or it [49:32] makes up less things. [49:34] I do think that [49:36] Putting guardrails around how we're allowing it to think and not necessarily access outside information makes it a little bit easier. [49:45] And so when it gets something wrong, [49:48] I see it as [49:50] the evolution of technology. This is brand new technology. It's going to get it wrong. And I try to [49:57] perhaps help it like I help my children when they get things wrong. [50:01] I have said this consistently on this podcast. The answer to that question is always a reflection of your parenting tactics and strategies. Well, Lucas, this has been amazing. Thank you so much for sharing your coach. I'm actually going to go spin off into ChatGPT. I have a really good idea for one that maybe I'll share.

[50:19] in the show notes as well i appreciate you joining howaiai where can we find you and how can we be helpful [50:24] Well, you can find me at, I'm actually off social media. Wow, I love that. [50:29] So we can't find you. [50:31] Where can we find your company? [50:33] You can find my company. It's captus.is. [50:37] as in Sam. [50:39] And [50:41] That's where I spend most of my time, to be honest. So if you want to find me, just go to Cactus. Great. Go to Cactus and find him at that amateur tournament, tennis tournament on September 18th. Or challenge me to a tennis match. That's the other way to get my attention. Perfect. Well, thank you so much for joining. I really appreciate this. It's been a great conversation. [51:01] All right. [51:02] Thanks, Claire. It's a pleasure to meet you and thanks for having me on the show. It's been wonderful. [51:16] You can also find this podcast on Apple Podcasts, Spotify, or your favorite podcast app. Please consider leaving us a rating and review, which will help others find the show. You can see all our episodes and learn more about the show at howiaipod.com. [51:33] See you next time.