How I AI - Building an iPhone app with zero technical skills | Bryce Rattner Keithley

Starting point is 00:00:00 I built an app called Daily Hundreds. I opened Lovable and Replit actually on the same day and left the simplest prompt. It was incredible to me that I could tell these AI tools, I want this, and it spit out a very basic minimum viable product of it. I asked you the other day, I was like, are you in test flight? And you're like, yeah, it was in test flight. And so now it's in the app store. You got it approved. It's ready to go.

Starting point is 00:00:24 We have anthropomorphic animal demos. This is my favorite part, and we're going to see some pretty amazing ones. But can you walk us through how you generated this? I make the animal in Gemini. I film myself doing the exercise. And then I mash up the anthropomorphic animal with Bryce exercising to create the videos. Were there any hard skills you felt like you developed

Starting point is 00:00:47 as you went through this process? I got really good at copying and pasting, but I think I knew how to do that beforehand. I don't actually really know what Railway does, and yet it's there now. The fact that you, a very very non-technical person are buying or acquiring railway as your infrastructure without really knowing what it is. It's kind of amazing from a go-to-market perspective for these AI tools. And I'm

Starting point is 00:01:11 sure saying what you don't know and then trusting the beep-boop robot gods also helps you discover and push further than you would if you knew the boundaries of things. Welcome back to How IAI. I'm Claire Vaux, product leader and AI obsessive here on a mission to help you build better with these new tools. Today I have my friend Bryce Ratner Keatley, who is decidedly not technical. She's actually spent her entire career in talent and people, but she has somehow beat me to the app store with a vibe-coded fitness app, including customized animal videos for any workout you want to do. She's going to walk us through her step by step and show you how a beginner's mindset can mean you can build anything you want with AI. Let's get to it. This episode is brought to you by WorkOS.

Starting point is 00:02:01 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 co-pilot 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're going to pass, they, They need secure authentication, access controls, audit logs, the whole suite of enterprise features. Building all that from scratch? It's a massive lift.

Starting point is 00:02:40 That's where WorkOS comes in. WorkOS gives you drop-in APIs for enterprise features so your app can become enterprise-ready and scale upmarket faster. Think of it like Stripe for Enterprise features. Open AI, perplexity, and cursor are already using WorkOS to move faster and meet enterprise demands. them and hundreds of other industry leaders at workOS.com. Start building today. Bryce, to start our podcast, can you remind me as one of your very good friends? Are you technical? Claire, not at all. Perfect. So just to get that out of the way for everybody listening, I have my friend Bryce here. She is talented in many, many ways, but I still have her beat on the Software Engineer Index. And yet,

Starting point is 00:03:31 She has been the first of us that has vibe-coded a iPhone app to production and to the app store. So you beat me, you beat me there. So tell me how you turned from your background, which I'll let you talk about a little bit, to a iPhone app developer. Yeah, so most of my career has been in talent and recruiting. And I've had the privilege to work with really talented, incredible technical leaders throughout my career. And on one hand, through working with these folks, you come to see how talented they are with what they build. And on the other hand, do you come to see that they're living, breathing humans as well? And without being a computer scientist myself, there was this massive gap and full abstraction between who they are and what they could do.

Starting point is 00:04:20 And with these new tools that came out, even going back to last fall, I kind of got an inkling of like, well, maybe, I can try something too and see what the magic is all about and see what the high is you get from beep bopping into a computer and having what you build show up on the screen. So what did you build? I built an app called Daily Hundreds for Consumer Number One. The story dates back to the pandemic where I spent 20 hours per day every day in this literal room and wasn't moving and had two young kids at home and I craved exercise and there was this very short-lived 100 push-up a day challenge that I started doing but felt like it was boring and monotonous doing push-ups every day

Starting point is 00:05:12 and I kind of thought I wish someone could just tell me something different to do every day. I would happily do 100 of them and it kind of came back to mind. I've been doing it intermittently throughout of just jumping jacks or squats here and there between meetings. And I was like, that seems like a lightweight thing that I can try. And so I opened lovable and replet actually on the same day and left the simplest prompt of, hey, build me a tool called Daily 100 that pushes a different exercise to me to log 100 reps. And it ended up building something remarkably fast. It's not what you'll see today. But it was incredible to me that I could tell these AI tools, I want this, and it spit out a very basic minimum viable product of it.

Starting point is 00:06:00 I ended up sticking with Replit because I could phone a friend. I have a friend who's a director of engineering there, and I figured out of the worst case, he could unblock me. But that was really how it started. And I built this starting in October, and I got it into the app store earlier this month. So it took a couple months, but walk me through a little bit of how you used Replit. I think this is a really great platform for folks who really want to go zero to 100 into production. We had one of our early HowI AI episodes with John Blackman, our 91-year-old vibe coding grandpa,

Starting point is 00:06:36 who used Replit to build an app for his church. Replit is pretty amazing when you're building stuff that has a database on the back end, that you really want to be functional. So how are you interacting with Replit on a kind of daily basis? And how are you moving forward the app? Just kind of tell me your process. I tend to think that a beginner's mindset can be used to your advantage here because I truly don't know what I don't know. A big unlock somewhat from your pod is that there's a plan mode.

Starting point is 00:07:07 I would sometimes get myself in trouble by asking Replit, you know, how can we change the progress bar? The progress bar is like you're adding some reps and now it's in a circle. But it started as a line. And initially, I would say, let's change the progress bar to a circle. And it would just do something, bananas. And I would have to quickly undo that. We don't like that. And coming to see they have a plan function was really helpful and profoundly changed how I would approach things and tend to start really big picture of like, okay, robot, here's what your non-technical friend wants to do. How can we collaborate on our new idea? It has a preview panel that y'all can see right here, which makes it really easy to see if you're on the right track or the wrong track. Sometimes it magically happens on the right track right away. Other times it goes on the wrong track many, many times over. But it's really all in one and made things very simple to at least work at a small scale. I have a question.

Starting point is 00:08:15 So what concepts, development concepts or software engineering concepts, Did you find yourself learning as you built this with Replit? Were there any things that you just kind of got like a little, you know, because you've done technical recruiting again, your friends with me, your friends with directors of engineering. You've been around technology for a long time. But were there any sort of like hard skills you felt like you developed as you went through this process? Oh gosh. Are there any hard skills that I felt like I developed? I got really good at copying and pasting, but I think I knew how to do that.

Starting point is 00:08:49 beforehand. I got way better at labeling things so I could find things on my computer. I still don't think I know candidly any more about software than I did when I started to the extent that like when I learned that heaven forbid I had to take my app from my precious replet and move it to somewhere else before it can be an app. I moved it to railway. I moved it to railway. I just don't actually really know what Railway does, and yet it's there now. Okay, so I actually really, really love this. Let's just one, we're going to say I got really good at copy and paste. We're going to save that one from the trailer.

Starting point is 00:09:32 But what I, you know, what I reflect on this is like, you really are vibing. You are really the true vibe coder. And it's so interesting to me, you know, something like railway, just like a hosting kind of platform. My friend, my friend works there. We know the CEO. We're good friends with railway. We love them.

Starting point is 00:09:53 But the fact that you, a very non-technical person, are buying or acquiring railway as your infrastructure, would that really know what it is? It's kind of amazing from a go-to-market perspective for these AI tools because I think, you know, they used to be selling, I was in DevTools for a long time. They used to be selling Dev tools to developers. And now non-developers are discovered. dev tools. And it's just a totally different market. It's a totally different go-to-market. And I, again, I think you said something at the beginning when I want to reiterate for folks,

Starting point is 00:10:27 which is a beginner's mindset is how you stay. And you are unabashedly fine with saying what you don't know. Saying you don't know. And I'm sure saying what you don't know and then trusting the beep-boop robot gods also helps you kind of like discover and push further. than you would if you knew the boundaries of things. I think so. I mean, sometimes I'm sure it's a limitation or at least causes me to spend more money. But like as one example, it'll tell me,

Starting point is 00:10:58 oh, look here for that thing. And I'm like, no idea where you're telling me to go. So I'll send a screenshot of, you know, perhaps all of the library and which one? Where is that? Please give me more idiot, proven. Eli 5, everything. Or don't do it and tell me where I plug in.

Starting point is 00:11:16 I love this so much. But one of the parts of Daily 100 that I like, which is this is a really cool app, get up to 100 reps, is there's actually a little secret video functioning here. I guess it's not secret, but we don't have it popped open. So let's pop it open and show folks the best part of the app, which are these videos of animals doing the exercise. We have anthropomorphic animal demos. Yeah. So it turns out that micro workouts, like exercise snacks, are really good for you. I won't rattle off all the benefits, but perhaps I'll share them with Claire for the show notes.

Starting point is 00:11:57 And I did start sharing it with my network, even when it was small and just on Replit. And I would get text messages of like, what's a Superman? How do I do a reverse lunge? What's a reverse push up? And I was like, I've got to like not be the single point of failure here. But then I got kind of stuck in the, what person do I make? Is it all of me? I really didn't like that idea.

Starting point is 00:12:20 And I thought we all have animals. And so I've created anthropomorphic animal videos for, I think there's two that don't have videos yet. But they are all obviously AI generated. And I've really kind of gone ham on these. This is my favorite part. And we're going to see some pretty amazing ones. But can you walk us through how you generated this? because it isn't just make me a polar bear doing body weight lunges.

Starting point is 00:12:46 It's much more complex than that. So I want you to walk us through step by step how you eventually got to being able to productionize these high quality videos. Thank you. Yes. It did require a lot of trial and error. And it's still not, it's still not fully seamless. But I started in Sora and fully prompting to describe the animal I wanted and the exercise

Starting point is 00:13:11 I wanted to do, but found that oftentimes it would get good but not great results. And the prompting was really limited in terms of tightening things up or fine-tuning. And I found that just to be maddening. I ended up, and I can, I'll show you the process if you're interested, creating the animals in Gemini. I came to learn that the starting position for the animals was really key. Gemini wasn't doing the videos, but I was making the animals there. And my husband does a lot of work in AI, and he introduced me to Higgs Field. And so there's a ton of models in Higgs field.

Starting point is 00:13:58 And one of their capabilities is to merge, mesh, intertwine, a still image with a motion video to have what's in the image doing what's in the video. And I've played around with a couple of the different models somewhat intentionally, somewhat unintentionally. I found that Kling is the model that works best for these videos. Fun fact, Hicksfield was down a couple weekends ago, and I was fiending for more video creation. So I went and downloaded Kling separately, and it didn't make videos that were as good as Kling in Higgsfield. So I'm a Higgs field loyalist.

Starting point is 00:14:44 I make the animal in Gemini. I film myself doing the exercise. And then I mash up the anthropomorphic animal with Bryce exercising to create the videos. So technically you are. In every video. As some say, you can imagine me in a mascot so you're doing these because it's not that far off. Okay. So let's walk through that because you talked a lot about Jeb and I.

Starting point is 00:15:15 I'm presuming you're using nano banana here. I want to see it and I want to make a video. Let's do it. First of all, do you have an animal you want to make? Oh, I was not prepared for this. I can pick any animal. We're going to try and make crunches or bicycle crunches because those are on my hit list. So, but think about what would work or I can, or we can workshop one together.

Starting point is 00:15:42 I have, you already have a cat here. So I have a little leopard lamp over, over here. So we could do a leopard. Let's do a leopard. Okay. So I really don't reinvent the wheel. Like I said, copy and paste. I'll take what I had.

Starting point is 00:15:57 Create an anthropomorphic leopard. In a gym setting, wearing exercise gear, leopard, its hands would be behind its head, elbows out to the side, head resting down on the mat. The head should be to the left and the feet should be to the right. The knees be positioned above hips and feet forward. In a tabletop. I have to pause here as my friend Bryce writes this very precise prompt about accurate positioning on your crunches. I have to call out that she has a secret power here, which is she used to teach bar. And so being able to prompt somebody knees over here.

Starting point is 00:17:01 hips, shoulder width apart, hands behind your head. You knew that all those skills would come into cromping an AI image gen model to make a leopard doing crunches. It's really true. As I often tell people, like you never know what lateral moves in your career are going to end up being tools that pay off in dividends later. And I am quite good at. physical exercise queuing. And now I use it a lot. Okay, let's see what this gives us. And I know a lot of your guests like to speak. For me, some of the precision, I'm visual, so I like writing it out, but I have found that we want to leave no room for interpretation. And I'll often ask myself, can I be any more literal in what I'm describing? Okay. And we're using

Starting point is 00:18:00 nanobanana here in Gemini. In Gemini. And it's creating your image. I have to call back to one of the earlier things you said, which is you originally your MVP, one, was using Sora. And Sora is being sunset. So I'm glad you have a different flow here because you would have been deprecated out of RIP.

Starting point is 00:18:23 I know. RIP. Yeah, I think it's going to be interesting. You know, one of the challenges of of building stuff in these day and age with all these new products is sometimes they end being experiments that go away. And then you're like, wait, I was building my very important animal videos off of this. That's a really disappointing. So I'm glad you got to this new, new flow. And then Gemini is going to take a couple of minutes to load and we will just wait for it

Starting point is 00:18:52 to show up. And then we'll go to the next step. This episode is brought to you by MetaView. because who says hiring has to be fair? Every founder, hiring manager, and recruiter I speak with feels the same pressure. Hire the right people as fast as possible. But recruiting is brutally time-consuming, alignment is hard, and the competition for great talent keeps getting tougher.

Starting point is 00:19:14 That's why teams like Riot Games, Brex, GitLab, and Replit, plus 5,000 other organizations use MetaVue, the agenic recruiting platform giving high-performance teams an unfair advantage in hiring. It works by giving you a suite of AI agents that behave like recruiting coworkers, finding candidates based on your exact criteria, taking interview notes, reviewing every inbound application, gathering insights across your hiring process, and helping you identify the

Starting point is 00:19:42 best candidates in your pipeline. Don't let your competitors out hire you. MetaView customers close roles 30% faster. Get started with MetaView today and get your first 100 candidates source for free at Metaview.AI slash how I.A.I.A. Okay, so it loaded. Let's pop it open. Let's pop it open. See how good it did. So it's kind of flawed. It didn't do a great job.

Starting point is 00:20:11 It didn't listen to the hands behind its head. It didn't listen to the head down. It got one leg in the proper position, but it got one leg not in the proper position. We're going to try it again. We are creating an anthropomorphic leopard in a gym setting. The leopard should be wearing exercise clothes.

Starting point is 00:20:30 And sometimes, and this is probably me not knowing anything and summoning the AI gods, copying and pasting works when we're on a win and starting over sometimes work when you have an L. So I'm just restarting the karma and writing it all over again. This is to match the video because it doesn't do a good job interpreting anything. Both knees should be above hips, knees should be bent, feet forward and tabletop position, both feet off the ground. They should know their characters in the image. Sometimes, I guess, excited and adds friends for the character, and we just don't need that.

Starting point is 00:21:03 We don't want that. Okay. So just we prompted it once. You copied and pasted your kind of original prompt made a couple edits, did not give you what you wanted. You say, don't copy and paste. That's just welcoming more of the same. Instead, started over, rephrase. We added a couple more literal things together in terms of like saying both feet off the ground or

Starting point is 00:21:25 both hands behind your head or left and right and just being very precise. And then you're using Gemini to create this image. We'll see if it does a little bit better. We'll see if Gemini does a little bit better. It's really fascinating. Sometimes we'll get things on the first try. Sometimes it'll take a while. Yesterday we made a cougar. And what it got quickly was the cougar. What it didn't get, and I wanted it to do burpees. I wanted the cougar to be all the way forward on the mat. And I wrote that a couple of different times. The cougar should be standing all the way to the front edge, left side of the yoga mat.

Starting point is 00:22:05 It gave it weights the next time. I didn't want weights, but it kept it in the middle. And so what I then did was I took a image of myself and showed it a different version because we just kind of got stuck. But we eventually got the cougar a little bit further forward. Okay, let's see. Okay. Oh, yay. There's your leopard. It's head's not down, but I think we can work with us.

Starting point is 00:22:32 Okay, can we pop it up and just show the improvement we got? All right. So both legs up. Tail still looks awkward, but, you know, it's a tail. It has a tail. It hands are behind its head like we want for crunches. It's in exercise gear. There's no other friends. We love it. Okay. So what is your next step? Here's another actual hiccup about Higgs field. Sometimes the downloads work well and download what you want, and sometimes it downloads something totally random. Like it might give us a different animal than the one that we created, which is fascinating.

Starting point is 00:23:09 So we'll see if it gave us the right one. It did. I saved the animals by name. I save in a starting positions folder so I can pull them for recall. I give the animal and I give the position that they're in. so it's a little bit easier. And then do you want to try and turn this into a video clear? Yes.

Starting point is 00:23:27 Okay. So then we go to Higgsfield. And Higgsfield has, it's like an embarrassment of riches in terms of how many options you have and what you can do. It can be a little bit overwhelming. But in this case, I use motion control. I use Kling 3. It's under the video option right here. So Kling 3 motion control.

Starting point is 00:23:49 I add the motion. So in this case, we're going to pull my video, and this is going to be crunches. We're going to do crunches cut because it's shorter. Fortunately, all of these exercises are not in my living room, and that's what you would see if we didn't have this magic tool. And then we start, find the position that we want. And this was our leopard in the supine position. It lets you choose the scene control. So in this case, we're choosing the image.

Starting point is 00:24:20 Still loading our video. Or still loading our image, excuse me. So just to call out for folks, a couple of things that I notice if you're not watching on the YouTube. So Bryce took a video of herself doing these crunches with her legs in the tabletop position. Very good form. Excellent work, my friend. And a couple of things I notice is I see now why you prompted for the head to be at the left, because you don't want the video to be mirror image of the image.

Starting point is 00:24:45 of the image. And so you put these two image and video side by side. They're roughly the same shape of character. You're using this Kling 3.0 motion control model. And then you're saying the image is what's going to control the scene versus the video is going to control the scene. Because you don't want the videos in your living room. You want the videos in 24-hour fitness Animal Edition. Correct.

Starting point is 00:25:11 Okay, great. Exactly. And then you click generate. And you click generate. And it does require patience. They tend to take quite some time. You can tend to do, I can maybe do three or four before it gets overwhelmed. So I might cue some up if I have my videos and my images ready.

Starting point is 00:25:28 But it is, you know, go for a walk. Do some of your daily hundreds, get a set in. And it will eventually get you your video. Amazing. So we'll let this process and we'll come back and see what we got. Do you want to see some of the past ones while it's working? Yeah, let's do it while it's loading. Okay. So there have been a lot of friends that we've made.

Starting point is 00:25:50 We have animals and we have mythological creatures for making sure we're getting good coverage. There's a goblin. There's a cat. There's a fox. Flamingo. Some of them, I'm able to get on the first try. Some of them take a while. And some of them are just like real, real tricky. I'll show you one that I think you demonstrates like how A.S. can do you wrong. So I wanted to demonstrate swimmers, which is a great postural exercise for us people with desk jobs. Oh, excuse me, Superman's.

Starting point is 00:26:26 So it's laying down, it's lifting all of its limbs up off of the ground. It's using your posture, muscle, it's using your glutes, basically your whole back chain. This is what I wanted. This is our genie doing some supermans. But your hands have to be like that when he's superman. No, you got a lot of choice.

Starting point is 00:26:43 This was just his style. But as you can see, we got real close the first time. I was pretty happy with this, except the feet stayed up. And we don't want people to think that they've got to do this unreasonable exercise the whole time. And sometimes I'll have to get in there and give it some more encouragement, some more literal guidance. It's so bad. The genie's legs should start on the floor and lift up at the same time as the arms instead of saying elevated the whole time. What?

Starting point is 00:27:14 I don't even know if I can describe what I'm seeing on screen right now. You just really go to the, we'll make sure this is bookmarked in the YouTube so you can see this. I mean, the genie is floating. There is some body part, maybe a foot, maybe something else, just on the ground. And it's doing nosedives into the yoga mat. And so, you know, oh, he's only got one leg. It must be his foot. You can see it kind of floating behind him. Yeah. Very odd. Very odd. Not approachable for us actual humans. No, not at all. Was there one that you did that surprised you how effective it were like an animal you thought it wouldn't really work out and it ended up being pretty high quality?

Starting point is 00:28:06 Oh, a million percent. This was my kids' recommendation. They wanted me to make a turtle. And I was like a turtle feels like not the animal at the gym, first of all, but like the shell would be a bit prohibitive. But like, look at our friend doing these cross-body step-impresses. He's so friendly. I mean, turtled art historically known as ninjas. So I'm not surprised that it That's true. That's true. This is maybe its origination, even doing curtsy lunges. Look at this little friend doing Kurtziger. He's got a nice little demeanor. He looks approachable and friendly.

Starting point is 00:28:47 Oh, Bryce, you know that I do ballet. Can you make me turtle ballet? That's for our next installment. Okay, perfect. So let's see if this video is back up and loaded. And again, I can see here, it's taking you one, two, three tries. You're trying to reprompt. Sometimes AI goes real sideways.

Starting point is 00:29:08 And we're all of these, kind of this combination of image and video. They were all the combination of image and video. Yeah. And to your point before, there were times where I tried to get it to perhaps I had an animal in a straight-arm plank position and I wanted it to do donkey kicks or something that started in quadruped. And it couldn't even adjust the starting position from a mostly the same to the knees down or bare plank hovers where your toes are tucked and you're lifting your knee slas. slightly off of the floor. It even had a hard time interpreting those small changes. And so I tend to get really precise on the starting images as much as possible. And that's been a big unlock in terms of generating the right video that I want. Amazing. Okay. You ready to see your leopard? I am ready to see

Starting point is 00:30:00 my leopard. Show it to me. Let's see how we did. Hey. Hey. Hey. You're doing cringes. You're doing crickies. I thought it was weird elf before that everyone thought was a human and kept asking me who the human was. And so now we've got a leopard. This is fantastic. I love this so much. And it looks great. I mean, things that you can call out, I even think it shows the reflection of the leopard in the mirror back there. So it's pretty funny. Pretty smart. You would never be able to do this before. This is one of those things that I tell people. Like, imagine being able to, in the past, like you would have to, I don't know, hire an animator. I don't even know what you would do. It would just be videos low-res videos of you in your living room.

Starting point is 00:30:43 Really. And the horror. Yeah. In the corner. And so now you have this like high production value, fun, leopard, doing crunches in appropriate form. Even looks like it's struggling a little bit, a little wobble to the to the crunch. It looks very natural. 10 out of 10.

Starting point is 00:31:03 You can do crunches now too. You got your inspo. I love it. Got your form. Okay. So just to catch people up where we are so far, we have built. a full end app in Replit without knowing what we're talking about, decided to add in custom videos of these exercises by combining a nanobanana image of reference image of an anthropomorphized

Starting point is 00:31:25 animal and my friend doing an exercise. So it's just like a video from your iPhone doing an exercise. You're combining those in Higgs field using the Kling model and waiting about five minutes. and then you get your video. So you have these two things together. This looks like a web app, but people don't want to pull up web apps when they're doing their exercise. So your next step was getting this to the app store.

Starting point is 00:31:53 And I will tell you, Bryce was asking me for advice on how to do this. And I was like, girl, I am not a mobile developer. Never have been, never will be. Not my thing. Don't do consumer enterprise till I die. And so I was like, I can't help you. I can't help you.

Starting point is 00:32:07 Otherwise I would. And I think you heard that a lot. from friends, right? A couple months ago when you first started this, like you were asking around how to get this into the app store and what was their response? I started building this in October and once I realized that I wanted to keep using it every day and to your point, not only do people not want this as a web app, you certainly don't want it to be Daily 100.replit.com, because nobody's going to go there. It was like, okay, well, the Holy Grail is getting this to being a published app in the app store and the, like, broad consensus

Starting point is 00:32:39 back in the fall was at some point, like, yes, you can do a lot of this in Replit, you can do a lot of this on your own. At some point, you're going to have to have someone technical unblock you and level up to get this in the app store. And a friend's husband who's technical, I engaged him to basically write me a fairly intensive doc that I could shop around if I wanted to hire a contractor. But as I went through the holidays, as the new models came out in February, and I started getting ready to advance the project, it was wild to me because the same tech. folks that I was asking, Claire included, it was sort of like, actually with the current models, like you can probably do this yourself. And so I did. Beginner's mindset went into Clod and was basically how do I prepare a Replit app for App Store submission and kept it really broad and gave it the context that I am not technical. I can use Claude code.

Starting point is 00:33:39 where it was starting, some of what was involved, and what do we do next. And it gave me, I think it was like five pretty meaty items that we were going to have to go through, including moving, letting go of my replica comfort blanket and moving off of it, and ultimately got it ready for App Store publishing. And so what I would do is I would use Claude, original Claude, as like my friend in I don't know, in the cockpit of like, what are we doing? How are we going to approach this? And it would tell me when to go into Claude code. Claude code would write me code. I would bring that back into Claude and say, this is what you told me to have it do. Here's what it did. It would confirm or give me thoughts on it. And then it would tell me to put it into the terminal directly, which was a fascinating and at first terrifying experience. But that was ultimately what I would do. I had bought. between Claude, Claude and Terminal and really continue.

Starting point is 00:34:45 And in fact, I hit my limit like 51 minutes before it reset one day and then I got 90% another day. But I was able to stay within my limits generally and did start to outwork it because on a couple of occasions it would say, you've done a lot today. You can come back tomorrow. I'm like, absolutely not. we're going on to the next one. And so I was able to go, I took about 25 or 30 hours in one weekend and just cranked through it.

Starting point is 00:35:16 But ultimately got it into the app store on the second try. Yeah. So just for folks, and I love this workflow again, because it's like beginner's mindset, right? You were just like, plain all clod, OG Claude is very accessible to me and not scary. So I'm going to ask OG Claude to give me a plan. And again, like, let's go back to plan mode. need a plan, give me a step by step. And I love the honesty of like, I'm not technical. So like, let's not pretend I am. Give me the step by step. I'm going to work with Claude Code. And then you

Starting point is 00:35:47 would give those steps to Claude Code. So you almost had like a product manager or a technical architect in Claude. Then you had like your software engineer in Claude code. And then they both said, you know, we don't have the ultimate permissions here. So you need to step in and do these specific things in the terminal. And then you went to, I asked you the day, I was like, are you in test flight? And you're like, yeah, it was in test flight. And so now it's in the app store. You got it approved. It's ready to go. It's ready to go. Yep. I got, I had some pretty low hanging fruit from my first submission. That was mostly user error. Yeah. But yeah, we're, we're live and in the app store. What was the user feedback or the feedback? Do you remember? Yes. So there were three things.

Starting point is 00:36:31 One, and, and of course, I just took it all. I copied it and pasted it from Apple's feedback into Claude. And he's like, we did not achieve full publishing. Here's what it said. The first one was like, oh, it looks like you check the wrong box on parental. You're like childproofing something. And so it's like, this is the box to check. I probably went back to it and was like, you need to clarify further where that is and what to do.

Starting point is 00:36:56 The second one was definitely user error because it does use your phone number to log in. and because it needs to be compatible with iPad, I needed to add sign-in with Apple, which I had done, but I never tested it. And so that was my bad. It didn't work. And so I needed to troubleshoot that and make sure that sign with Apple worked.

Starting point is 00:37:18 And then you need to have a way to delete it. So I needed a button where you could delete your app. And so I added a button to be able to delete your account. And she's not lying, folks, it's right here on the app. app store. She truly beat me. This makes me very mad. I am a little bit of competitive. I'm a competitive vibe goater. This is super impressive. So again, for folks who never thought they could do this. And you know, we've had people on the show who are like pseudo-technical, like product backgrounds. And it's just, what I love about this moment is really people are unconstrained by

Starting point is 00:37:58 execution and they can take a good idea that adds value to them and build it and make it real and not just make it real, make it production ready, which I think is super impressive. So, Bryce, before we get you out of here, I'm going to ask you a couple lightning round questions and then we'll get you going. So in your day job, you think a lot about talent, teams, and leadership. And I'm just curious, your thoughts reflecting on this exercise, which has brought you much closer to the builder side of things. What are things that are top of mind for you about how to hire and how to be hireable in this moment? Yeah, it's really, it's really interesting. I've personally always gravitated towards an appreciated environment where the best idea wins, right? It's not only certain

Starting point is 00:38:51 people have the best ideas or certain functions can have the best ideas. But I think in this day and age, The attitude that different skills and different ideas are going to come from everywhere, and it's table stakes to cross-pollinate and have both like the humility and the curiosity to work with others in ways that you haven't before. I think people that get, dare I say, territorial or constrained by what they used to do or what other people used to do, are going to struggle with relevance and playing nicely in the sandbox and instead trying to zoom out and consider people can contribute in ways that they haven't before and being both ready for that from other people and keen to do that and bring that attitude to other places as well I think is is necessary it requires there's a lot of adaptation in fact I

Starting point is 00:39:58 I feel like there's an opportunity for me to adapt because for a lot of the things where my job or my function is changing, it's still a nice to have. I think there's other functions where it's table stakes. And I have friends who especially do technical recruiting who have seen that when there's resistance to seeing technical problems in a new way is where folks really struggle. So for an engineer to come in to a technical interview and focus only on finding a working solution fastest, it misses the point. Because the robots can find a working solution faster than they can. And if they're not recognizing, hey, in this equation, the human role has shifted, I need to step back and consider my role as well as the full suite of tools and understand that my role as a technical expert is broader and different than it was six months a year ago.

Starting point is 00:41:05 That gap, I think, is only going to be greater and more challenging. And so that willingness to almost be open to outcome and unattached to what was and recognize that what got me here won't necessarily get me there. But also that at least for now, there's still a lot of opportunity, I think, to preserve humanity and maximize impact when you're willing to see things differently than you did before. I love that. And I think that's a real challenge that needs to be put out to everybody in this moment is your roles are fundamental. fundamentally changing and the skills you need are changing. And that's okay. I think there's still value to bring into an organization to a team. But the sooner you face that things are different now, the better. Bryce, my second question is, I know you read or listen a lot to books. In this moment in AI, has there been a book that you've read recently or one that you just have in your pocket

Starting point is 00:42:01 from, you know, the before times that you think is really relevant for folks right now as we're navigating this different sort of moment in our careers? If you haven't read what got you here won't get you there or how women rise, which is kind of the sister book to that, it's a good reminder. Not everything is in the title, but it's really the premise that, like, yes, you should trade on your strengths and the things that have been positively reinforced to date. And also definition of insanity is doing the same thing and expecting different results. And so your willingness to believe in yourself and scale to the next altitude is really your. your opportunity. I did listen to a whole new mind. It's the book by Dan Pink, which actually came out in

Starting point is 00:42:48 2014, and I think is really ahead of its time, but talks about the benefits of and and thinking of both left brain and right brain thinking. And again, this is, it's old now. And the way he's talking about automation and acceleration and abundance is interesting and right. And I think it's only more true. But I really think, especially as computers can do more left brain thinking, there's an opportunity and a lot of inspiration for seizing and maximizing humanity with right brain thinking that they talk about. That's pretty powerful. I love that. Willing to those books in the show notes, but a lot of good recommendations here. And then my last question, I ask everybody

Starting point is 00:43:36 on the show, which is when AI is not listening, when you are getting that weird genie foot floating below your Superman genie, what is your kind of like prompting technique? Do you yell? Do you bribe? I am a true Dale Carnegie enthusiast, and I feel like I've built a lot of my career on how to win friends and influence people. And I would be lying if I didn't acknowledge that it is sometimes cathartic to. put down my Dale Carnegie and not win friends and influence people with the robots and just be angry. So sometimes I do raise my typing. However, and I will say I have been inspired and somewhat compelled by some of your guests that have talked about karma with the robots,

Starting point is 00:44:25 that I have strengthened some of my perspective and opinions on my role and how to humanize or not. And so I do try and be more measured and decent and prepare myself for continued robot evolution. So I try to be decent and firm when needed and also keep my position of power. I love that. And then, you know, two other things that we saw is you just try to be hyper literal and the screenshot is your friend. The screenshot, yes, try new things, right? It's like add more details. If it didn't get it right, how can I be literally.

Starting point is 00:45:05 how can I be any more precise about what I want? That might work. Reset. I'm an 80s baby. So refresh or rewrite if I need to. And then try something new. Like maybe I'll draw the progress circle and take a physical picture or capture a screenshot of my starting position and like just see if that prompts the robots any differently. I love it. Well, Bryce, this has been really, really just a fun episode, I think very accessible for folks. Now where can we find you and how can we be helpful? Certainly. Yeah. Yes, I run a firm called Great Team Partners. We take a team building approach to startup scaling. We work with mostly C through Series B companies on how to grow strategically and with talent density. You can find me on LinkedIn. You can find me on GitHub at BRKBot. And you can, of course, find me on the Leaders Board of Daily Hundreds in the App Store. Thanks for coming.

Starting point is 00:46:01 This was super fun. Thanks so much, Claire. Thanks so much for watching. If you enjoyed this show, please like and subscribe here on YouTube or even better, leave us a comment with your thoughts. 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 how IAIIPod.com.

Starting point is 00:46:30 See you next time.

How I AI - Building an iPhone app with zero technical skills | Bryce Rattner Keithley

There aren't comments yet for this episode. Click on any sentence in the transcript to leave a comment.