From journalist to iOS developer: How LinkedIn’s editor builds with Claude Code | Daniel Roth

[00:00] So you have actually named your Claude's and then you give them instructions to listen to each other. Yes, they have to talk to each other. One is called the Builder app is called Bob, Bob the Builder. And he's got instructions to stop constantly. And you have to run everything by Ray, who's the review agent. Ray's job is senior software engineer who is obsessed with security. He reviews code milestones, guards security architecture. And then the third agent is me. [00:30] thing in racing, you can't do it. And you are doing all of this as someone who has not spent their career as a software engineer. For a while, I thought I'm like a mediocre PM. And then I was like, no, maybe I'm more like an architect. And now I realize like an architect actually knows real details, [00:44] A PM is like super rigid and it keeps the entire app in their head and they're able to really prioritize. Well, I'm a bad prioritizer. All I am is a really picky customer. So I think that is like the role of the vibe coder is what do I care about deeply? I'm like walking through this house and I'm telling the architect, no, I want this room blue. I know you don't think it's a good idea. I'm telling you, this is what I want. [01:07] Welcome back to How I AI. I'm Claire Vo, product leader and AI obsessive here on a mission to help you build better [01:14] these new tools. [01:15] Today I have Dan Roth, who's the editor of LinkedIn and started his career as a business writer and editor. [01:22] but has somehow become a software engineer vibe coding iOS apps all the way to the App Store. He's going to show us his dueling cloud code setup that lets Bob and Ray build high quality production grade software. Let's get to it.

[01:37] 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. [01:49] But there's a catch. [01:50] These tools only work well when they have deep access to company systems. [01:55] 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 need secure authentication, access controls, audit logs, the whole suite of enterprise features. [02:16] Building all that from scratch? It's a massive lift. That's where WorkOS comes in. WorkOS gives you drop-in APIs for enterprise features, so your app can become enterprise-ready and scale up market faster. Think of it like Stripe for enterprise features. OpenAI, Perplexity, and Cursor are already using WorkOS to move faster and meet enterprise demands. [02:46] today. [02:47] Dan, welcome to How I AI. What I like about having people [02:53] like me, maybe that have a couple years of experience under their belt is... [02:57] We've seen... [02:59] technology shift over time and we've seen market shift over time and we've seen our own career shift over time and what I love about [03:05] Your story is...

[03:07] You've seen a shift like this. [03:09] in an industry that you've been in? [03:11] And you've seen how disruptive and scary it can feel. [03:14] And now you're seeing this again and you're really leaning into it. So tell us how you came from... [03:19] your background, which is non-technical, into... [03:22] Now we're going to see some power cloud code tips and iOS apps kind of vibe coded all the way to the app store. I was a longtime business writer. I was at Fortune, Wired, Forbes. [03:34] And I remember being at Fortune during the introduction of blogging. And all of the sudden, [03:41] Everyone had access to something that I thought was [03:44] something that was unique to writers. We were able to talk to the world [03:50] in a way that no one else could. And that was kind of like a monopoly almost on this ability to get [03:55] ideas out into the world. [03:57] And then WordPress came around and Tumblr, and suddenly everyone could talk to everyone, and you discover this explosion of ideas. [04:05] And, [04:05] I have, and it was scary at the time, and then it was, you realize, oh, [04:09] actually you want to embrace this more ideas the better and so you as a writer changed and as an editor changed how I thought about who I could go after and open up like suddenly I realized there were way more people. [04:22] that could be sharing ideas and reporting that I ever thought were possible. [04:26] a couple years ago when generative AI started making its way into coding, and it became clear that any of us could build anything. [04:35] I had the exact same idea, but it went from being...

[04:37] this, I was on the opposite side of it. It was like, oh my god, I've had all these ideas of stuff I wanted to launch, and in the past I would have had to go convinced [04:45] an engineer or a PM to go team up with me on something. And I was just [04:50] trying to influence what got built. [04:52] And then I could suddenly start building. [04:54] So it has become an obsession of mine. [04:57] building to the point now where when I'm with friends and family they're like please stop talking about the stuff that you're building you know we don't want to hear about it anymore and and I just have to like ratchet it back but on the weekends it is like that is what I love spending my time doing so like while the Super Bowl was going on I will be on my laptop building a [05:14] either like working on some new feature for the apps that I have out there. [05:18] Well, what's really funny is you are not alone. We just had Guillermo, the CEO of Vercel on, and he calls that request for prioritization, like petitioning the government, where anytime you had something, you had to go to the government, which were unfortunately run by product managers and say, please, oh, please. [05:35] government, would you pass this resolution to shit my button in production? And then we're also hearing from everybody, whether technical or not, that... [05:44] This is really fun to build, and it's kind of... [05:47] New hobby, new space for learning. And unfortunately, maybe or fortunately, where they're spending money. [05:54] Too much time? Yeah. No. Well, we're going to benefit from your obsession now, and you're going to show us how... [06:00] you as somebody who has a non-technical background has used [06:04] cloud code and some other tools to build real production apps. So what do you do? What's your special sauce? Sure. So first, I should just tell you, I started this with a course I took on cursor. So it started with how to use cursor. And I can share that link with you. It's a free course.

[06:18] how to build with cursor, how to build apps. And I watched that. And so I started with cursor. [06:22] And then over time, I stopped using cursor because I didn't really care [06:26] where the files were kept. I wasn't going in and editing anything. I didn't actually need that. I just needed to tell people what I was doing. I needed to tell... [06:34] Claude what I was doing so quad code was the big unlock for me and I'll show you what how I build um [06:40] So if you can see my screen here, I'm going to show you one. One thing I do is I keep I use Claude and I ratchet back and forth between the $20 a month plan and the $100 a month plan, depending on where I am in my building. So right now I'm in the $100 a month plan. [06:53] I keep a clawed window up that has all of my-- I keep everything in projects. So this is my Commutely project, if you can see this. [07:01] And I keep one running feature here, which is commutely feature idea and tracker. [07:07] So this is as people talk to me about what they wish the app did. And this is an app for being able to basically never run for the New York City train. Again, you can know if I keep missing the train. I'm like, I'm going to build an app that is just for me. [07:19] that is basically like, is the train almost here? Can I walk or do I have to run? That is what it's designed to do. It was... [07:25] that perfect product market fit because I was the entire product. We call this personalized, the rise of personalized software right now. [07:32] It's amazing. It's the best. And then suddenly you discover other people care about this also. And it's like, well, I have a community. [07:39] So this is from my community of train runners. They give me lots of feedback, and I've been keeping a... [07:45] uh i keep i keep one clawed chat available here that is just all the feature ideas

[07:51] And I've given it a prompt to basically rank it in terms of time it'll think to build. [07:55] and the growth that it will think that this feature should have for the app. [08:01] and so the i'll read you the the prompt at the top which is basically [08:05] Let's use this as a running idea of ideas for Commutely as I log them, keep track of them and offer guidance, time estimate to build and estimated back and forth hours. [08:14] potential impact score on two one to three scales, customer happiness and growth impact. [08:19] And then I've given it a bunch of ideas and just keep feeding it new ideas. And it has this table here. [08:25] So these are, if you can see the commutely features ranked by build time. [08:29] And so what I do is when I have free time, I go into this [08:32] chat and i find a feature that i'm like i've got a couple hours i can go and build something [08:37] and I'll look for it. So the things on my list to do are Siri integration, standalone widget, [08:41] I've already built this SEO friendly blog. [08:43] location awareness, but I thought maybe for this, it would be fun to build something I've been trying to do, which I built the scheduled automatic updates. [08:51] which is... [08:51] I know that every day at 7.30 a.m. I usually leave my house. I just want Commutely to tell me [08:57] where the trains are. So I built that, but no one's using it. And so I need to be able to build, I now have to think about discovery. [09:03] By the way, this is the other part of this I've learned is [09:06] like, [09:07] The building is one thing, the marketing. [09:09] is a total other part of it. So now I've gone from being [09:13] a [09:14] quasi-crappy PM to now being a quasi-crappy PMM. [09:18] as I learn how to basically do marketing for my app, too. Here's a funny thing that I'm thinking as you say that is I know I'm a true product founder and that I will literally build.

[09:29] everything on this list before I can will myself to do anything that is like even remotely called marketing. And so if you can get over your, what we say in the industry, you know, if you can climb Cringe Mountain and just become a marketer, you will be very happy with the distribution of your app. So, [09:48] I've already worked with... [09:50] card code on [09:52] coming up with a retention plan. [09:54] And I save everything as .md, as Markdown file. So I've got it within my Commutely project, [10:00] There are just there's a document folder and then there's a list of Markdown files. [10:04] And I just every time I'm working with community, every time we're working with Claude, I'm saying, [10:09] Write it into a file, log everything, log everything. And I do that for two reasons. One is the context window. Claude, it's constantly forgetting what it's working on. [10:17] And then I'm forgetting what I'm working on because they only do this on weekends. [10:20] So on Saturday, I'll pick it up and I'll be like, what? Wait, what am I building? I can't remember. And how far did I get? So everything gets logged. That is one tip I try to give anyone that is in my shoes also. So we make these MD files. So this is retention plan. [10:35] and it's come up with a general plan, but now I need to go build it. [10:39] So I keep two tabs. I use Terminal. [10:43] And I keep two tabs open. One is for building and one is for reviewing. Now I've given Claude two personalities. [10:50] which I can bring up by using. One is called the Builder app is called Bob. [10:55] Bob the Builder. And so I bring up Bob. [10:58] And this is my builder app and he's got instructions.

[11:01] Tell me your instructions. [11:04] on how you work, so this is just to show you [11:07] what Bob is trying to do, [11:09] And quick question for folks that don't know how to do this. First of all, I have never seen somebody customize their clod theme to let them know what version flavor of clod they have running. I've seen a lot of people that run multiple clods and multiple flavors. Yeah. So I've never seen that. Pro tip, you can do that. Second is, how do you have you built these as aliases that have different settings? How do you build actually how do you technically make Bob if you could just give us a high level? [11:35] This is not going to be super satisfying because what I did was I go into Claude and I say, I don't want to have to tell you every single time what you are. So this is your requirement is Bob. And let me pull up what Bob is here. So... [11:48] Well, here, this is what I've taught Bob to do. This is basically my prompt on what I want Bob to do. So this is Bob telling me, Bob's idea, everything has to plan first. I've learned over time, like, you don't build until it's done planning. And I've heard guests of yours say the same thing. Like, [12:02] Plan, plan, plan first. [12:04] And then everything has to be built in modules. I don't want like tons of spaghetti code. I learned that with my first project, the code gets unwieldy. So I say you're a lean builder, whatever that means. [12:14] and then document everything. We talked about that. [12:17] This is the important part, is I say to Claude, I say to Bob, [12:21] You have to stop constantly, and you have to run everything by Ray, who's the review agent. So let me get over to Ray. So this is Ray. I love this so much while you pull this over. So you have actually named Ray.

[12:35] Your clods. Yes. And then you give them instructions to listen to each other. Yes. They have to talk to each other. So... [12:43] Ray's job is a senior software engineer who is obsessed with security. [12:48] and with making sure that we don't leave any of our design guidance. So I've got a whole design document also. [12:56] and then make sure so here's what ray does right what i do i review bob's plans before he builds [13:01] He reviews code milestones, guards security architecture, [13:04] And what he cares about, and this is what was in my prompt, is member trust. [13:08] security. [13:09] architecture integrity and quality. [13:12] And I say, and because Claude is always rubber stamping everything, [13:16] I'm sure you're [13:17] Viewers see this all the time. If everything's genius, you're always perfect. I have to tell it. [13:22] you have to say no to things like you. And then I break the tie. So the third agent is me. [13:27] I am the person who breaks the tide that often happens between Bob wanting to do something and Ray saying you can't do it. [13:34] Well, can I suggest two other agents? One is Amy, the PM that says, sorry, Bob and Ray, that hasn't been prioritized yet. [13:41] And then there's Joe, the AE that sells it anyway, whether or not it's been built. And then you have the whole team ready to go. Okay. So Ray and Bob work together. So how does Bob invoke Ray? [13:55] So Bob has to, so let's do this. Say, I'm going to say we... [13:59] We're going to build [14:00] The retention plan. [14:03] Thank you.

[14:05] All right, so I use the app. [14:06] It finds its retention plan, MD, [14:09] And then I just say, because Bob knows what his role is, I say, get started. [14:13] So he should now go into plant Bob. I shouldn't even use, I shouldn't personify these people. So it now goes into AI. I think it's very, it's, [14:22] You know, it's just the way we work. [14:24] Really? I feel so creepy about it. I hate it. I hate it. I hate when I do it. [14:28] So it's starting to read this Markdown file that I showed you earlier of what this retention plan is. I came up with this weeks ago. [14:34] reviewed it. I thought it was pretty good. And now we got to start building it. This is amazing. I think this is so fun. [14:40] So once it's done here, it will spit out something that I have to then copy and paste into Ray. [14:45] Now, what I've done in the past is I haven't built Raid. I've just said, run this past a security agent. [14:50] That works, but what I don't like about it is I can't see what the security agent is saying. [14:54] So, [14:55] what what the builder agent will often just say is security passed it or security wants me to change one thing but because i'm trying to learn this it also [15:03] I want to know what it's stumbling on. [15:06] I think that's an underappreciated workflow, which is, you know, earlier when you said I got out a cursor because I'm not looking at files and I'm not editing things. The software engineer in me just started like my ulcer starts to just flare. I am an aggressive code reader. [15:23] But you are taking this. And I even think some of these like micro frictions that aren't necessarily like, yeah, could you spin up a Ray subagent and do all sorts of stuff? But I do think. [15:33] putting a little bit of friction in the process where you're actually forced to like copy and paste, put it over, read what Ray says. Exactly. Does help with learning. And so I don't want people to, especially people that are moving from...

[15:44] non-technical into more technical tasks to make it so efficient that you're not actually learning the process because then, like you, you can set up even more powerful systems. Couldn't agree with that more. [15:55] That has been and I'm not doing this just to build. I'm doing this to learn. But what I figured out early is that [16:01] I'm not going to learn how to code. [16:02] Like just being realistic, like I tried to do that. I got I didn't find it that interesting. And I'm like, I'm a total beginner. [16:09] And I'm like, well, it's actually building code. I just want to understand why it's building, what it's doing. [16:13] And the problems that I find that I can solve uniquely [16:17] as a human, [16:18] are things of like should we prioritize this or not or [16:21] you're this seems like it's going to be really expensive like is this worth doing is this going to break my budget my budget for commutely is zero except what i'm paying for claude and so i don't i have to tell it all the time like that seems expensive i don't want to do this that's all right so here this is it's now done here [16:38] Let's come up with this... [16:40] That's pretty long. Implementation plan. [16:42] Mm-hmm. [16:43] So normally I would sit here and read this whole thing. [16:45] But I told it, build it. Everything that Bob does has to be done in a branch. That's one lesson I've learned. I used to [16:51] ship everything to Maine. And I learned the pain of that early on. I yelled at a friend recently. I was like, make a branch, dude. Like, you're stressing me out. Oh, my God. But what I didn't realize this, and I found this out from real engineers later, is it's not... [17:08] when I merged the branch of my other app [17:11] I merged a branch into Maine and it didn't work. [17:13] For some reason, it didn't merge perfectly. It took me weeks to be able to

[17:17] figure out why it was emerging. So I didn't [17:20] This was a lesson to me is it doesn't always just work seamlessly. You probably know that well. [17:24] Yeah. Okay. All right. So here I'm copying the plan here. Normally I would read this whole plan, but I'm not going to this time because I'm just going to build this into a branch and then work on it later. So Ray is now ready for this. I paste it in. [17:37] There we go. [17:39] And now Ray is going to get to work. And so what Ray is doing here is the sort of... [17:45] Is this architecturally correct? Is it secure? Are there any, you know, as we say, there be dragons, like, is there anything in there that you need to be worried about that Bob mixed? And I really like this. We haven't actually seen somebody do a persona to persona handoff. What we have seen is a lot of people will maybe use like an Opus 4-5 or an Anthropic model to build the plan. [18:06] And then they'll actually hand it to like a codex model. [18:09] to review it, Codex is like a little [18:12] a little mean senior staff engineer. Totally. And so it is kind of nice to have that handoff. And what I say is like dueling agents. [18:21] to just get very similar to when you're working in a team. I think you can appreciate this, right? You write code, [18:27] Or you write up, in my experience in product, like you write a product idea and then you bring somebody else into it and they're like, oh, but you forgot we have to have this compliance thing or don't you remember that... [18:37] when we did the data analysis on this, customers hated that piece. Or design says, actually, this is really technically hard to implement in our design system. And so I do think just taking some...

[18:48] um taking some flows from your organizational process and then figuring out how to make them agentic is a really natural way for people who especially have been managers yep to start building out their own little ai productivity stack it's such a great call that manager that idea of being a manager for this you are managing these agents yep so like one of the things i find a lot with commutely is it depends on this app is really built around live activity [19:14] on iOS. [19:15] That is where you are tracking your train. Your phone is locked. You just go and look at it. Live activity, it turns out, to have all kinds of limitations. [19:23] And [19:24] Claude will forget those limitations all the time. [19:27] And so it will suggest things like, oh, you should just do this. And I'm like, we know we've learned this already. Don't you remember like two weeks ago we tried to build it. It turns out that like it can't actually ping the MTA's API when it's when when the the app is not on the screen. And so I it's like being a manager of I've read this somewhere else. This is not my thing, but someone once said that. [19:48] managing AI is almost like managing a really smart but hungover intern. And I feel that way all the time. It's like, you're a genius, but you don't have it this morning. Just remember, we've gone over this already. [20:01] Well, and AI is very similar to how I've positioned the benefits of what we call early career talent. Yeah. Which is like, [20:08] Very capable, very excited. [20:11] to an experience to know they shouldn't do something. So occasionally you get greatness. Right. [20:15] But we should use a branch and a PR just in case. That's exactly it. As an AI founder, you're used to sprinting towards product market fit, your next round, or that first enterprise contract. But speed isn't enough for AI startups. Buyers expect security, compliance, and transparency.

[20:35] from day one. That's why serious AI startups use Vanta. With deep integrations and automated workflows built for fast-moving AI teams, Vanta gets you audit-ready fast and keeps you secure with continuous monitoring as your models, infra, and customers evolve. AI innovators like Langchain, Rider, and Cursor scaled faster and closed bigger deals by getting security right early with Vanta. [21:05] a special offer of $1,000 off Banta at vanta.com slash how I AI. [21:12] Great. So now Bob has raised some edge case concerns, which I think are really useful. Ray has raised the edge case concerns. Yep. Ray has. And then says Bob's plan is solid. So then do you pass this back to Bob? Yep. [21:26] Yeah, exactly. So now I copy and paste this right back. [21:30] Uh, it's got the green light, and then Bob's gonna go build. [21:33] Now, the next step in this is that I will then take this and put it into Xcode. [21:36] and do a new build and then test it out in the simulator, see if it works, test it on my phone. And then I usually ship it to Apple right then. So I've been trying to do weekly updates to Apple. I will say the hardest part, [21:49] of building my two apps has been the app store [21:52] I had no idea. [21:54] navigating the app store is a whole separate. I've got, I have so many chats where I'm like, what does Apple want from me here? And just getting Claude to teach me how to use the app store has been a real thing.

[22:05] I feel like that's almost the last friction left in being a builder. [22:09] is navigating the App Store. I have a couple related requests for startups. We have all the coding agents we need. They're going to get better. We're fine. We are spoiled for choice. We need AI for App Store submissions. [22:21] We need AI for SAP Ariba submitting procurement requests and POs. And we still need that perfect AI CRM. So all the builders out there, if you could give us these very boring but very high value problem solved, you have a lot of customers waiting out there. [22:40] You know, one that I might build, actually, to solve, again, this idea of solving for your own problems is App Store designs. So the right now, the way that I do, you know, when you when you [22:50] when you do something in the App Store, you have to show [22:53] what your app looks like. [22:54] And I've been using Canva for it, but it's really [22:57] canvas ai i don't love if i'm like i'm not getting what i need so i might try to build an app that just takes people's screenshots and turns it into something for the app store i love it okay so ready to leave the plan bob is asking some design questions exactly so this is great so this is i i've written about this in the past but like for a while i thought oh i'm i'm like a [23:18] a mediocre PM. And then I was like, no, maybe I'm more like an architect. And now I realize like an architect actually knows real details. A PM is like super rigid and like has understands that keeps the entire app in their head. And they're able to really prioritize. Well, I'm a bad prioritizer. All I am is a really picky customer. So I think that is like the role of the vibe coder is.

[23:40] what do i care about deeply i'm like walking through this house and i'm telling the architect no i want this room blue i know you don't think it's a good idea i'm telling you this is what i wanted so the picky customer [23:50] is I think the role that is at least my role. That's how I think about my role. [23:54] So in this case, Bob is saying there's some UX decision I have to decide. [23:58] I like this concept of a picky customer because I was going to say what I feel like is QA that's just looking at little edges and saying, no, that's wrong and that button isn't quite doing. So I like elevating this to no, no, no, no. I'm not doing quality assurance. Yeah. I am going through and being my own pickiest customer. You know, I'm I'm sniffing my champagne before I drink it, as we say. And so that's a really fun thing. [24:25] Fun way to think about your role when you're building for yourself. [24:28] Yeah, and it also does like my other app, which is a podcast clipping app. [24:31] the [24:33] There was all this, it took a little while for the video to be made of the podcast clip, and there was some kind of error. There was a message just saying... [24:40] your video is being created. [24:41] And I'm like, actually, I want this to have a better voice. I want this to be funny. I want it to say like, oh, my God, you clipped a great part of the podcast. And so as the picky customer, I could say, this is the voice of this thing. Make it funny. [24:52] and wrote some copy for that so that's that's how i i think about it more than qa [24:57] Because you want to bring your personality into it. [24:59] All right. So in this case, it's asking me some options. It's giving me some options. I could pick my own option just for the sake of time. I'm going to just say, let's keep the MTA blue.

[25:10] All right, I'm just going to start building. [25:12] Great. [25:13] And you're doing this all on the weekend. So are you doing, I have to ask, are you running multiple bobs and multiple rays? Do you single do it? What's your own, what is your own capacity? [25:24] for a gentake management. Bob is allowed to spin off sub-Bob's. [25:29] So that is the one thing. My prompt says you are allowed to have agents that you manage. You're responsible for these agents. I'm holding you accountable. And your subagents can't create their own subagents. So that's my rule on how to do this. Got it. So Bob can spawn, but he's ultimately the directly responsible individual. Exactly. Got it. Ray cannot spawn. [25:49] Ray is Ray. There's only one gatekeeper, and that gatekeeper is Ray, and there shall be no more. Exactly. That's very principal engineer energy. It's like one guy. [26:00] And you go to him and you're like, can we do this? And only he can say yes or no. And he neither manages nor can be managed. That is your right. Totally. Well, Claire, like one of the things that I have, I'm able to do this because I've now worked inside of a tech company for 15 years. And so I've watched how, so a lot of this is based on people I've worked with. And exactly to your point, the principal engineer, like I've watched my PM partners be like, we should really run this past Sanjay. [26:30] Just find out whether this is going to work or not or where we're going to make a mistake. And so that is exactly what Ray is based on. [26:36] Every ray that you've ever worked with is now like, is this? Am I ray? Am I ray? Okay, so we're watching Cloud Code generate code as it does. And then, you know, maybe we won't show this part, but you're just going to take this into Xcode.

[26:51] make sure it compiles, test it, and... [26:55] And, you know, spend the rest of your life getting it to the app store. Exactly. So let me just show you quickly, if I can, what this would look like. [27:02] is you go into Xcode, [27:04] I've actually come to really like working inside Xcode, but I think I'm probably only using like 5% of it. I try putting Claude into Xcode. They're like, they just built this new part of... [27:13] where you can actually use Cloud Code in Xcode. I have not found it to be... [27:19] worthwhile. It kept running out of memory, so I just quit using it. Um, [27:23] But you go into Xcode, you... [27:26] What do you do? [27:27] Command-Shift-K, you do a clean of this. [27:30] Look at you, expert software engineer. I should say, I don't know what I'm doing. [27:35] So let's just make that clear. I have learned these things. I'm basically the bot. I'm like, Claude has told me what to do. You're the agentic browser. Exactly. That's exactly it. Tell me how to do this. I'm doing it. I'm just like, someone's pulling my strings. [27:48] And then you go to build. [27:49] which is what? Control B. [27:50] It's going to run this thing. When it's done, it'll pop up the... [27:55] the simulator, I can test it out. The simulator is, I find, like, [28:00] 80% close. [28:01] But you really like there's so many edge cases you don't even realize until you get it onto your phone. [28:06] I test it. [28:07] on my phone, [28:08] And then I quickly shipped it to Apple. [28:10] get it in test flight, test it for like an hour, and then I just ship it to the App Store. [28:14] And then you have all this extra time so you can make it to your train on time. Exactly. That's exactly it. [28:21] This is an awesome flow. Just to recap for folks. So what we saw is sort of dueling Claude codes. One's a builder, one's sort of like an architect reviewer type. You build your, you have a standing prioritization roadmap chat in the Claude web or desktop app where you're always putting in ideas, reprioritizing them against like a simple three point framework.

[28:46] On the weekends, you pluck one of those, you make a PRD, you give Bob the PRD, and [28:52] Bob... [28:53] invokes plan mode and cloud code. [28:55] It builds a plan. You copy and paste that over to Ray. [28:58] Ray either green lights it or gives feedback. You give it back to Bob. [29:01] Bob? [29:02] builds, love it. And then you used keyboard commands you don't even know in Xcode and you ship it to the app store. [29:13] That is 100% right. [29:15] And you are doing all of this as someone who has not spent their career as a software engineer. [29:21] I've been around a lot of software engineers. I've watched them work, but no, I have never done any of this myself. [29:26] This is a flood we really haven't seen. I think it's a useful, really repeatable one that others can use. And... [29:33] I, you know, if anybody in San Francisco used public transport anymore, then I would definitely request a regional option for us. But in the meantime, if you could build a commutely.com. [29:46] that tells me like when I need to yell at my kids at what level to get out of the door to school on time. Yeah. That would be. Yeah. Apparently. Exactly. That's what we need. I'm going to, I'm going to replicate your flow and build that next. Nice. [30:01] All right, so here it is. Commutely is now opening on this. Oh, no, I don't have Metro app. [30:06] I can never remember the command. Uh... I'm gonna have to suggest, for anybody who can never remember the command... Yeah. You should watch our episode with John Lindquist, who shows us how to set up terminal aliases. You can just ask Claude to set up a terminal alias.

[30:22] that will then run these like regular things that you need to run. So if you wanted to type in "metro" and have the terminal run it, [30:30] You could create a terminal alias using CloudCode to just make a quick chart. That's so much better. I have it like in a notes file somewhere, which I can then never find. So that's much handier. Let's go back to CloudCode. I've just, I got to have you do this. We'll do it live. This can be a live HowA.ai. [30:43] and say, "Can you make me an alias for the Metro command?" [30:49] so it's easier to run in the future? [30:51] By the way, I've really tried to not say, can you or please? This is part of how I'm like making sure that I don't personify this thing. This is how I stop the robots from taking over. This is one of two things. This will go to our last question, which is how do you talk to the bots? I am so Southern. I'm like, would you pretty please... [31:09] do this. Please, sir. Yes, ma'am. The other thing is actually, quick parenting tip, I always find I ask my kids, like, [31:18] Would you do you want to unload the dishwasher? [31:21] And they're like, no, I don't want to unload that dishwasher. And so that's another thing is you don't want your AI to say no. Okay, so now anytime you type in Metro, it'll restart the bundler. Amazing. Thank you. You're so welcome. [31:34] How I AI, live. Wow. Just learned something new. I love that. [31:38] Okay, so let's see if it's running now. So let's open the simulator. Look in. There it is. So this is exactly what I wanted to build. This was a hidden feature. [31:47] on commutely is that you could set it up to go off at certain times. Bob and Ray just worked together to build this thing. And now every day, 7:00 a.m. weekdays, I can get this.

[31:56] But now if I go to my morning commute, [31:59] It's going to show me these trains are ready. I get this. If I go to the lock screen, [32:03] It'll show up here, so... [32:05] If you were at 14th Street, your next train's coming in five minutes. You got to start running. [32:10] I love it. Okay, download this app on the App Store. Give Dan... [32:14] all the feedback so he can give it to Claude, Bob, and... [32:18] Ray. All right, Dan, let's hop to some lightning round questions and then I will get you back to your day job. So we get to the end of the week and on the weekend you can start playing with some more Cloud Code. [32:28] The first question I have for you is, are there any sort of non-coding workflows or tips or tricks that you think are really useful that people can pick up in like five minutes that you think are going to make their life better? We've talked this entire episode about something I just do on weekends, but most of my time was actually spent at work. I run a 400-person team. I've got a context switch all day long. [32:48] I rely on Copilot constantly to do that because it has access to all my files [32:54] and my entire team. So my command that I start the day with, or I end the day with, usually, is what did I drop the ball on? [33:02] And I'll show you that. [33:04] What did I drop the ball on? And then I usually, and then for the point of this show, I'm going to say anonymize. [33:10] Any names or project names as this will be seen by... [33:19] Yeah. [33:19] people I don't work with. [33:21] Perfect. [33:23] Yeah. [33:23] Okay. [33:25] It's going to go through Outlook, it's going to go through Teams, it's going to go through any updated files.

[33:29] It knows who I report to. It knows who reports to me. And it keeps track of things that I'm constantly clicking on during the day. So it'll find, it'll go through all my emails and find. [33:39] places where I'm not responding or teams where I'm not responding. [33:43] And what's great is it's not just places where I've been app mentioned. [33:45] It's stuff that it knows that I am actually interested in. [33:48] So projects that I've been like kind of like following over time. [33:53] What I think is really useful about this is we've seen a lot of people do their morning daily digest, but we haven't seen anybody do their daily. [34:01] evening nightly nudge, which is [34:03] Hey, you got through your whole day and you forgot X, Y, and Z. And how many of us, especially managers, want to start the morning with nothing to do and having wrapped it up all in the evening? So I think just even take AI out of it, moving that practice from upfront in your morning to in the afternoon when you can actually do something about the stuff that hit your plate during the day is a really great idea. That's exactly it. For me, this is my... [34:27] 30 minutes before I leave. [34:29] I ask this, I do this prompt and then I can go through here. So here's an inbound escalation from a longtime creator. Someone's unhappy with me. I didn't reply. I have a draft reply that I never sent. [34:40] I'm meeting follow up. This is my life. And this is it. This is like when you get at some point, you start managing so many different projects. You're like, I know I'm dropping the ball. Just tell me what I am dropping the ball on. So this is my savior. This is like what I count on. [34:53] AI to be able to do to make me better at my job so that I can spend the weekends building money losing apps like Commutely.

[35:00] Yeah, you can vibe code code. You cannot vibe code gross margin. That's true. That is true. All right. And then my last question, I ask everybody, but when AI is not giving you what you want, you've said you don't want to personify AI. [35:13] AI, which I do. So we are on opposite sides of this very interesting thing. [35:18] Then what is your tactic? Do you... [35:21] Do you like kill Bob and his spawns? Like, do you? Yeah. Are you an all caps person? What's your prompting strategy? I mean, there are times where so I'm usually really just straightforward. I just I'm like, this is what you're doing. I try not to say please or thank you, because, again, I just don't want to at some point when we get to AGI, they're going to be running the show. And I just I'm fighting until we get to that point. I'm holding on to my humanity. And then but I usually just I usually spend a lot of time saying we've gone over this already. [35:51] You've talked about this. Go search your memory. [35:54] to go find the time where we've done this. And it is, it's a lot of parenting. I have, like you, I have three boys, and I rely on a lot of the things where I'm like, we've talked about this, remember? And, you know, and your kids are like, you know that they are, they want to do the right thing. [36:09] And so it's just a lot of like helping them get there. There's something that we say that I learned from a former manager and that we say a lot at LinkedIn, which is assume best intentions. And that is how that's, by the way, a big change from how newsrooms work, which is my last life, which was you assume worst intentions all the time. At tech companies, you assume best intentions. I've now taken that to my family and I've taken it also seriously.

[36:31] to building with AI. So I assume the AI has best intentions, but has to be reminded about how we work. So I don't yell. I'm pretty clear. And I try to give it a little bit of grace. [36:41] Perfect. Well, Dan, this was awesome. I think it's a great overview for technical, non-technical. [36:47] busy, [36:49] busier alike. So thank you for sharing your flows with us and our audience. Where can we find you and how can we be helpful? So I'm on LinkedIn, not surprisingly. Find me. You can follow me on LinkedIn. It's Daniel Roth at LinkedIn. And I've got, I keep a running newsletter called Forward Deployed Editor, which tracks how I'm learning how to AI. And it talks, it's really designed for people who are non-technical to be able to get [37:13] to be able to build cool things. And so I try to talk about what I'm failing. It's mostly what I'm failing at, what I'm learning, what didn't work, how to avoid... [37:21] making the same mistakes I've made. And so if you can follow that, that'd be great. Otherwise, I'm always constantly posting on LinkedIn, great content that creators are posting around the world. So hope you'll follow me there. [37:32] Great. Well, thanks for joining How I AI. Thanks for having me. [37:44] 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. See you next time.