2:42 on over to lennysnewsletter.com and click product pass. With that, I bring you Zevi
2:47 Arnovitz after a short word from our sponsors. This episode is brought to you by 10Web,
2:53 the company that pioneered AI website building before ChatGPT. In the last three years, over two
2:59 million websites have been generated with 10Web's vibe coding platform. 10Web's vibe coding platform
3:04 is a powerful way to build websites. Think of it as lovable for WordPress, front end and backend.
3:10 Users can build any website at any complexity, e-commerce, portfolios, information websites,
3:17 blogs, and it comes with the WordPress admin panel and thousands of ready to use plugins.
3:21 10Web also offers website generation as an API as a service for SaaS companies, marketplaces,
3:27 hosting providers, MSPs and agencies. SaaS companies can embed it via API so that users
3:33 can launch AI generated sites directly inside of their platform, connected to their own data.
3:38 Agencies and MSPs can get a white label dashboard to manage clients and resell under
3:44 their brand. Hosting providers can self-host the API builder on their own infrastructure.
3:49 Check it out at 10web.io/lenny and use code Lenny for exclusive free credits and 30% off
3:56 API or white labeled solutions. That's the number 10web.io/lenny, vibe coding platform as an API.
4:06 Today's episode is brought to you by DX, the developer intelligence platform designed by
4:11 leading researchers. To thrive in the AI era, organizations need to adapt quickly, but many
4:17 organization leaders struggle to answer pressing questions like, which tools are working? How are
4:22 they being used? What's actually driving value? DX provides the data and insights that leaders
4:27 need to navigate this shift. With DX, companies like Dropbox, Booking.com, Adyen, and Intercom
4:33 get a deep understanding of how AI is providing value to their developers and what impact AI is
4:39 having on engineering productivity. To learn more, visit DX's website at getdx.com/lenny,
4:46 that's getdx.com/lenny. Zevi, thank you so much for being here and welcome to the podcast.
4:56 Thanks for having me, Lenny. I'm a huge fan of the show and
4:59 tons of people that I've admired most and learned the most from. I've been on here,
5:03 so it's a crazy moment for me. I'm really excited for this.
5:06 I really appreciate that. I want to start by reading actually a note
5:09 I got about you from Tal Raviv, who is a previous podcast guest,
5:14 many times newsletter collaborator. One of the most AI forward product managers that
5:18 I know I've learned a ton from him. So here's what he said about you when he introduced us.
5:23 Zevi is the most hands-on vibe coding PM I know, and I've personally learned so much from him. His
5:28 engineers at Meta ask him to teach them how to do what he does. Every time we get coffee,
5:33 I repeatedly get this feeling of everyone needs to be hearing this.
5:37 That's so nice. And so that's the goal. That's the goal of this conversation is to help more people hear what you
5:41 figured out. We're going to get very hands-on. We're going to do a lot of show versus tell,
5:46 showing people what you've figured out about how to be a PM, a non-technical PM building stuff. I
5:52 want to give people a little bit of background on you because I think this is going to inspire
5:55 a lot of listeners to feel like they can also do what we're about to show you. This is going
6:00 to look very advanced, but just give people a little bit of sense of just your background.
6:05 I'm very non-technical. I have zero technical background. Did music in high school. A lot of
6:10 Israelis do technology units in the Army. I was not in a tech unit. And basically a year ago,
6:18 I was traveling with my wife for three months in Asia and we were in Japan and
6:23 that was around when Sonnet 3.5 came out. And I remember watching a YouTube video.
6:29 I think it was either Greg Isenberg or Riley Brown and they were basically building apps using,
6:37 it was either Bolt or Lovable, just using AI. And it was like a crazy moment for me because
6:42 I was watching this and it basically felt like someone came up to me and said, "Hey Zevi, there's
6:48 this cool new technology you should check out. You should really give it a try. Oh, and by the way,
6:52 you have superpowers now." And the second I got home from Japan, I didn't even unpack my bags,
6:58 ran to my computer, opened Bolt, opened an account, and for the past year I've been building.
7:03 And the last thing I'll say on that is we talked about this a bit before we started recording,
7:07 but I was prepping with Claude for the episode and I was trying to clarify what my goal is for
7:15 this episode. And Claude said, "If people walk away thinking how amazing you are,
7:20 you failed. And if people walk away and open their computer and start building,
7:23 you've succeeded." So I really hope that we can inspire some people to do the same.
7:27 I love that so much. I feel like that should be the goal for my podcast. If you're like,
7:31 "I love that guest." It's less of a win. If it's just like, "Oh, I'm so inspired
7:35 to do the thing that they figured out, that is the real win." I love, Claude is the best.
7:41 I agree. Okay. So let's dive in and give people, let's start with kind of a high level overview of
7:47 how you operate and you use AI in your job. What are the core tools and just what's kind of like
7:53 the frame of reference for the workflow that you figured out and how you operate?
7:56 This all started where I was a project's power user. I love projects, GPT projects.
8:03 ChatGPT projects? Yeah, exactly. GPT projects and Claude projects, which are basically a shared folder of chats which
8:10 share both custom instructions and shared knowledge base. And I think it was around
8:15 when GPT started using memory where I thought it was interesting, but it really annoyed me
8:23 because I do a bunch of different things. I'm a terrible runner, I'm a PM, I was a student,
8:31 psychology student, so I had all these different facets of life. And what happened was
8:37 the memory feature was mixing stuff up. So like I talked to GPT about running
8:41 and it would say, "Oh yeah, after this 5K, you're going to crush all your next product reviews." And
8:47 it's like, okay, I understand that you have that in your memory, but it's just not relevant. And
8:52 projects basically allows you to compartmentalize and have things within the right context. So
9:01 tracking back to the story I told when we came back from Japan, I started building this app.
9:05 The first thing I noticed was that these products were built in a way where, and when I say these
9:11 products, I mean Bolt and Lovable, were built in a way where they were super eager to write code.
9:16 So their system prompt was you're a coding agent. So when you'd write something, they'd
9:21 straight away start coding. So at the beginning of a project, this was super fun and exciting
9:25 because they just go and start building your app. But later on when things got more complex, this
9:30 created much more problems because planning is really important when you're implementing
9:35 something technical and let's say you're implementing payments or something that's
9:40 going to be a change to your database. If the coding agent is just like, "All right,
9:45 I got it." And just starts writing code, this always results in terrible things,
9:49 some really gnarly bugs that I had. And to mitigate this, what I did was I created
9:54 sort of a CTO. So again, I'm not technical. I have been in product for a while, but I know
10:02 zero stuff about code. So basically what I did was I created a CTO with the custom prompt of it being
10:11 the complete technical owner of the project. So I told it, "I own the problem. I own how we want the
10:17 users to feel. You're the complete owner of how this is going to be built. I want you to challenge
10:22 me. I don't want you to be a people pleaser." All these things that kind of mitigate the
10:26 regular ChatGPT-isms. I always think about this where for some reason, the easiest way for me to
10:32 think about AI is to imagine it as people. And I think ChatGPT would probably be the worst CTO
10:39 because it's such a people pleaser and it's so sycophantic where ... Just a short story I had
10:46 a few weeks ago, I was trying to learn about Bun JavaScript, which was acquired by Anthropic
10:52 and I was trying to understand what they do. So I was talking to GPT and this wasn't within my
10:57 co-founder CTO project and I asked it if it's similar to a different framework that I have
11:04 in my app called Zustand, which nothing to do at all with what Bun JavaScript
11:10 does. And basically GPT goes, "Oh yeah, it's exactly the same." And then it started talking
11:16 about what it meant and I was like, "Wait, no, these are not the same at all." And it
11:20 said the most terrifying and hilarious thing. He goes, "Oh, I'm sorry. I thought you were
11:24 just making this up and I was riffing with you." And I was like, "Oh no, no,
11:28 no, this is terrible." So basically if regular ChatGPT was a CTO, that would be the CTO who goes
11:34 along with your dumbest ideas. So creating the project allowed me to mitigate that.
11:40 So this is, just to be super clear, you have a ChatGPT project that you've given a prompt
11:45 to be your CTO of your product and being a non-technical person,
11:51 this is kind of like the thing you talk to when, and we'll get to what you're actually
11:55 using to build when you have questions about architecture and decisions that are technical.
12:00 Yeah. So now I'll show my full workflow and I don't involve GPT anymore,
12:05 but I definitely would recommend, even though the technology has gone ... So when I started this,
12:11 there was no plan mode or ask mode. It was just build on these products on Lovable and Bolt,
12:17 and they've progressed a ton. A lot of what I had as workflows have become ingrained
12:22 in these products, which is really interesting. I would still recommend start with a project for,
12:27 first of all, the reason that I said, and also it kind of puts you in a place where you're in
12:31 a chatbot and not writing code. So you take the time to converse and to learn, which I think is
12:37 critical. And the second thing is if you're non-technical like me, code is terrifying.
12:44 It's the scariest thing in the world to look at, and I look at it as kind of like exposure therapy.
12:49 I think if you see this where I'm working like in Claude or in Cursor, you might be excited to
12:56 start using those, but I would really recommend starting slow with a GPT project, beautiful UI,
13:03 super simple, then maybe graduate to like a Bolt or a Lovable, and then go to Cursor in light mode,
13:09 slowly, slowly, gradually ease in until you open a terminal,
13:13 go full dark mode, go full dev. So I would really recommend doing this gradually.
13:18 That is awesome advice. And so just to be clear,
13:22 these days you're using Cursor with Claude Code powering it. And what I love about that is that
13:28 you've never written code. The way you put it, you're afraid of even looking at code.
13:32 Yeah, 100%. You can do exposure therapy, and I love that Cursor is useful to you. And what
13:39 you're telling us is that graduating from a ChatGPT project that is kind of
13:43 your technical co-founder kind of taught you enough to feel more comfortable going straight
13:48 to cursor. You said that you actually went to Bolt and Lovable kind of in the interim
13:53 and then you went just straight to Cursor. What's the reason to just go straight to Cursor? Is it
13:57 just Cursor can do everything and once you get the hang of it, it's actually the most powerful tool?
14:02 Yeah, I think I graduated from each tool when I kind of outgrew it. So Bolt was awesome until I
14:08 was trying to connect payments to my app and I kind of started losing it and then
14:12 I graduated to Cursor and I've actually fallen in love with Claude. So I'm using Claude Code,
14:16 but that also runs within Cursor, and I think this is Tal who told me this.
14:22 I'm not sure who he's quoting, but code is just words at the end of the day. So it's
14:27 just files on your computer. So basically you can be working on the same project and carry
14:31 it from app to app. And especially now, I can work with multiple models and apps
14:36 on my project. So start slow, but definitely there's a lot of places you can graduate to.
14:42 Awesome. Okay. Should we dive into screen share showing how you operate?
14:47 Awesome. I pulled up cursor. Can you see it? Mm-hmm. Perfect. So within my code base, what you can see here on the left, these are all my code files.
14:57 Here on the right is Cursor. So this is basically like having AI, which has access
15:02 to all the code. And here in the middle, I have Claude Code running. And what you can see here,
15:06 I'm going to close cursor for a second. What you can see here are all my /commands.
15:10 Basically what /commands are, they are reusable prompts that I save within the code base that
15:16 I can run by writing / and then the name of the file. So here you can see Create Issue,
15:22 which is the first command that I'm going to use. And basically what this tells Claude,
15:26 it says the user is meant development and thought of a bug or a feature and improvement,
15:30 capture it fast so they can keep working. And then it basically says, this is the
15:34 format that I want you to capture the linear issue in, and it explains a bunch of things
15:40 what exactly Claude needs to do to get there. So the way I invoke this is basically I'll do
15:47 /create issue and this injects this prompt into Claude. So it says, "I'm ready to help
15:54 you to capture this issue, what's on your mind." So basically when I'll do this is if I'm working
15:58 on a big project and I suddenly come across a bug or have an idea that I don't want to
16:03 work on right now, but I want to work on later, I'll do this really quick and Claude's main goal
16:08 is to quickly capture what I'm thinking about. So quickly to run through my full workflow. So
16:14 basically it starts with creating an issue. So this is the create issue /command, which
16:19 basically tells Claude that I'm mid-development and it should quickly capture what I'm thinking
16:24 about and create an issue within linear. Then later on, when I want to pick this up,
16:29 I have the exploration phase. Exploration phase is basically telling Claude,
16:33 we're going to only explore what we want to solve here. It could either pull from linear
16:37 or I can just speak freely to it. And what it will do is it will analyze and understand the
16:43 issue and just ask clarifying questions. The next phase after we've done finished
16:47 exploration phase is we're going to create a plan. So you can see create plan. This basically has
16:53 a template that I love for creating plans, and the output of this at the end of the day will be
16:59 a markdown file with our plan that we can end up building along with code. After creating the plan,
17:04 we have execute plan. After execution, we have review and then we have peer review,
17:10 which is really cool and we'll get into later on, and at the end, we update the docs.
17:14 So this is updating documentation and everything so that agents can write better code later on. So
17:19 I think what we'll do is we're going to build a feature live for my app, which I think is really
17:23 cool. But first what I'd like to do is show you the app so you have some context. So this
17:28 is StudyMate. It's a platform for students, which allows them to upload study materials and create
17:36 interactive tests based on their own materials. So here we can go to the top. Let's upload a PDF.
17:46 We can decide what pages we want to be quizzed on. We can decide the number of questions,
17:52 the difficulty level. And basically what happens behind the scenes is we send the information the
17:59 user uploaded along with the system prompt and any other augmentations the users decided to
18:05 Gemini and we create a quiz. These are challenging questions that are meant to assess comprehension.
18:12 You even have some hints and once we do a few of these, we can submit ... I got them right?
18:21 Terrible results. Yeah, lucky. And so just to be really clear about this, this is like a side business that you have, an app that
18:27 you built that's making money. That's like a thing you vibe coded having no technical experience.
18:32 Yeah, this is my weekend project. Yeah. This is what I do.
18:34 Amazing. On weekends. Yeah. So you get basically deep explanations into why each
18:41 question was wrong or each question was right. And at the moment, StudyMate only
18:45 has multiple choice questions. And I was doing some competitor research over the last weekend
18:51 and I saw competitors who had true or false questions and also fill in the blank questions,
18:56 which I loved. So I think that'd be really cool if we could build that live. How's that sound?
19:00 I love it. Crossing your fingers, this all work. I just want to highlight the stuff
19:05 you shared right before this in cursor. So this is a huge deal, what you describe here. This is
19:10 essentially what you've figured out is a way as a person that has no idea how to write any code,
19:16 how to build a product in Cursor as a product manager using this series of /commands that
19:22 you've concocted that you're going to be sharing with listeners. They can download all these and
19:27 just use them directly. They don't have to figure out all these prompts that you've figured out.
19:31 Yeah, 100%. Basically what happened was I formulated the backbone of this
19:36 with the CTO, and it was basically within the system prompt of the CTO
19:40 project that I had within GPT. So it said, step one, we do this. Step two,
19:44 we do this. And now I'll keep building. And if I see something that happens over and over again,
19:51 I'll just create a /command and then it will be automated within the workflow.
19:54 Amazing. So just to summarize the /command. So one is create an issue in Linear, which
20:00 I love. Linear is awesome. Shout out Linear. That's also from the product pass.
20:04 From the product pass. Oh my God, what a value? Okay. So step one is create the issue in linear.
20:09 So it's a command. So this prompt /command you've created, just create issue. Then it's explore,
20:16 which is explore the idea, help me ideate on what this could be. And this is Claude helping
20:21 you think through the feature and product. And then it's actually create the plan.
20:27 And so it's like the AI helping you build the plan to build the product. Then it's actually execute,
20:33 which is just build the thing. And then there's this review,
20:37 peer review step, which is awesome that you'll share. And then there's document,
20:41 update documentation based on the new feature that we're adding. Sweet.
20:44 Yeah. Cool. So let's go ahead and start building. So I'm going to use Wispr Flow
20:52 to dictate and basically this starts with /create issue. So this basically sends that prompt. And I
21:01 love this because I usually do this during when I'm building something else. So basically it
21:07 tells Claude that I'm mid building something and I don't have a lot of time to waste time on this.
21:12 So just ask some brief questions so that you have enough to capture within linear.
21:16 So I want to add fill in the blank questions to StudyMate. I want this to be 30% of tests to be
21:25 generated as fill in the blank questions. I want there to be six potential answers
21:30 for two blank spots, and of course there's only going to be two correct answers. So one correct
21:36 answer and two incorrect answers for each spot and I want the interface to be drag and drop.
21:43 So that's just basically a quick think of how I want this to work.
21:49 So it's going to ask me a few questions. Quizzes are 100% multiple choice, question structure,
21:56 single sentence passage to blanks and priority. So one and two are correct, and this is
22:05 not high priority. It's a nice to have feature. So now basically what Claude is going to do is
22:13 it's going to use MCP, which is basically a technology that was created by Anthropic,
22:20 which gives AI the ability to use tools. So this is connected to my linear. So what it's
22:25 going to do now is it's going to use everything we've said and create an issue within Linear.
22:30 And by the way, as this is loading, I just love the way, the way you described this,
22:34 especially doing voice mode, it's like exactly how you would talk to an engineer describing a
22:39 feature, "Here's what I want." And then they ask you questions, here's the clarification.
22:43 Yeah. So at first when I was doing this with the CTO, I would do it with ChatGPT voice mode,
22:50 and that was crazy. That literally felt like ideating with a person. It would push back,
22:55 ask questions, and maybe one day the coding tools will get there too, but that was exactly ... It
23:02 really felt like sitting with my CTO. Great. So created STU88. So if we open up Linear now, we
23:09 should be able to see ... Let's see where STU88. There it is. Fill in the blank questions with drag
23:17 and drop interface. So it has a TLDR, it has the current state. It did a little bit of research on
23:22 the code base, I think, expected outcomes, some context. So yeah, so this is basically ready for
23:28 me to pick up when I'm interested in building. So now let's say a few days go by, I finished the
23:34 current project I'm working on, I can pick it up. So when I pick it up, I do /exploration phase,
23:39 which is what we said. And then instead of pressing enter, I'll press tab and I'll show
23:44 you this. So basically, exploration phase, what it does is it will take an argument. This is
23:51 basically a placeholder within the prompt, which allows me to enter something that is
23:57 extra context for the AI. So I can say here, Linear STU88, which is referencing the ticket.
24:07 And now what it's going to do is it's going to go, it's going to fetch the Linear ticket.
24:12 And what's the idea? What's the goal of the exploration
24:14 phase? This ideate on the idea. Is that the- Exactly. Okay. So it's both for the CTO to deeply understand the problem that we're
24:22 trying to solve and also understand the current state of the code base,
24:26 what files need to be affected, and how is the best way to implement this technically.
24:31 And usually what happens is right now, Claude is just basically reading a bunch of files,
24:35 understanding the basic structure of the code, and then it's going to come back with
24:39 a bunch of clarifying questions that will decide how we end up implementing this.
24:44 So it feels like it's talking to your engineering manager.
24:48 Exactly, exactly. 100% this is how I think about it. And you said that you're a CTO, so you used to use ChatGPT prompt
24:56 to have a CTO in there. Now the CTO's living inside here in Cursor?
25:00 Yeah, because of the way the tools have developed and they've become so good at both exploration and
25:07 code execution. So now it's just a habit that I call it a CTO, but it's basically all in one.
25:13 The same agent will both do the exploration and write the plan and end up executing the code.
25:19 Got it. So it's basically it's Claude Code. Is there a prompt
25:21 you gave it to act like that? To act like the right kind of CTO?
25:26 Yeah, so within the Claude.md, which is basically the system prompt that's loaded
25:33 within Claude's context in every conversation, I have some basic stuff like this is our workflow,
25:39 this is how we work. Within exploration phase, I want you to challenge my thinking,
25:43 all kinds of stuff like that that can be loaded within the Claude.md file.
25:47 Cool. One last question before we move on here, just because I'm thinking about it as this happens, the Linear issue that you generated,
25:55 how often is it actually great and ready? How often do you have to edit it? What's the quality
26:00 of the Linear ticket that it generates? Because a lot of people are probably wondering just like
26:05 all these terrible linear issues are being created by AI. Are they actually any good?
26:08 It's completely different because I'm a company of one. So a lot of the context is within here
26:15 and there's no need for me to talk to other teams and understand. It's basically very accessible,
26:20 and also I can easily see when Claude understood something wrong.
26:26 I don't want to say that I would create Linear issues at work like this, but definitely if you're
26:31 building your own side project, they're pretty quality. And also, it just kicks off when I want
26:38 to start working on it. I wouldn't say it's ready to be built. It's ready to start being explored.
26:43 Got it. So it's just the beginning of an idea. Actually, let's come back after we go through this
26:47 flow of how you would approach this if you were at say Meta or another, maybe a smaller company,
26:52 how this workflow might work at a larger company that isn't just your own startup.
26:56 Yeah. Interesting. Let's come back to that. Cool. All right. So this is Claude coming back. I have a comprehensive understanding of the code
27:05 base. I thoroughly analyzed StudyMate live codebase and understand the current system,
27:11 feature quest and key areas that it's identified. Usually I'd spend a lot of time going over this
27:17 because this is super, super important, but just for the sake of development right now,
27:21 we're going to brush through this. Now Claude basically comes back after it's
27:26 gone through the code base and understood the way it currently works. It's basically telling
27:30 me what the current understanding is. So it's talking about how the app is set up at the moment,
27:36 how the data is structured, what it understood from the feature quest, and what it has identified
27:43 as key areas, and then it asks me some questions. So it's asking about the scope, it's asking about
27:48 the data model, the UX/UI of the feature, how it should be validated, how it should be graded,
27:54 what changes need to be happened to the AI system prompt and all kinds of questions
27:59 about the app. I've prepared answers to all these questions beforehand because I don't think we all
28:04 want to sit through this. So I'm just going to paste that in and we'll see what Claude says.
28:08 Awesome. I love it. And I love just scanning those questions I was asking. It's like such smart,
28:13 sophisticated, important questions instead of just, "Cool, here I go, I'm going to build it."
28:18 Yeah, and I think this is the big difference between just vibe coding and going along with the
28:23 vibes and really building serious apps. I spend a lot, a lot of time going back and forth and
28:29 understanding. Also, a very cool /command that I haven't showed yet is learning opportunity, which
28:36 basically when something is really difficult for me to understand, I'll do /learning opportunity
28:42 and then talk about what I want to learn. And this basically primes Claude and says,
28:47 "I am a technical PM in the making. I have mid-level engineering knowledge.
28:51 I understand architecture and basically I want you to explain what we're currently working on
28:58 using the 80/20 rule." So this is a great way to learn. I would definitely take this and every time
29:02 you kind of see something that you don't fully understand, I would definitely use this to learn.
29:08 Great. So Claude basically comes back and says how it understands the current data model and how it's
29:16 going to implement. Yeah, so it's ready to create the plan. So basically what I'm going to do now
29:21 is I'm going to go and do /create plan and while Claude is doing this, I'm going to show really
29:29 quick what this looks like. So basically, these plans are from a template that I found on Twitter.
29:36 I forgot who it was, but it was just a template that really resonated with me. And
29:41 it's basically saying, based on our exchange, create a markdown file that will be the plan,
29:47 include clear, minimal, concise steps, track the status. So this basically has like status trackers
29:53 on each task that Claude updates as it's going through and it will have a TLDR, some critical
29:58 decisions that we've made and the plan itself. So Claude has finished writing the plan,
30:03 so we'll be able to look and see exactly what the plan is. So it has a TLDR, it has the critical
30:10 decisions we've made and the tasks broken down. And this is a perfect plan and it's also a really
30:16 good way to write this because a lot of times, I'll use different models to execute certain
30:21 stuff. So Cursor has an amazing model called Composer, which is superfast. So a lot of things
30:27 that are not that complex, I'll use Composer. Gemini 3 that just came out is unbelievable
30:34 at UI. So a lot of times, I'll split the plan into backend and front end,
30:38 and then I'll have Gemini just read the plan and do the front end. So having this as a markdown
30:44 file is really good. And also going forward, it's really good to have within the app so that
30:48 later on, if an agent is writing code in a certain area, I can see what's already been done there.
30:54 So what we're going to do now is we're going to execute the plan. So now I think we're going to
31:00 do this with Cursor just because Composer is so freaking fast. So what we can do is basically
31:06 just say execute and then we can tag the file. And Composer is ridiculously fast. So that's it. It's
31:15 off. It basically understands what the plan is and it's going to go ahead and start writing the code.
31:20 Let me ask you a question while this is happening. Awesome. I have many questions, so this is a good time to ask a few of them.
31:26 You said that Lovable and Bolt and other apps in that space are just not enough to
31:32 build really serious apps and you have to move to Cursor to do that. Tell us more about that.
31:37 Just what's the limitation you ran into with those products and why you switched to Cursor?
31:42 I started using Cursor and Claude Code a few months ago and I haven't looked back, but at that
31:50 time, these teams have been moving like crazy. So I don't want to say I wouldn't trust them. I
31:56 don't know what the current state is. But for me, it was basically the issue of I felt that Bolt was
32:02 being very opinionated on how I should do things. And I felt like my knowledge has gotten to a point
32:08 where I can graduate and be more in control. By the way, I think that the main difference
32:13 between all these tools is basically the harness. So the models are all the same models. I'll run
32:18 Claude within Cursor, I'll run it within Claude Code, and it's also the models that Claude is also
32:23 the model that is underlying Bolt and Lovable, but basically, Bolt and Lovable will add a bunch
32:29 of levels in the middle that will take all kind of guesswork and hard decisions out for the user.
32:37 So the user doesn't have to make these hard decisions. So it's also very easy to build,
32:41 but the flip side of that is that you have less control. And basically Claude Code is
32:44 just taking Claude and shoving it straight in your code system and giving it full tools and
32:49 to do whatever it wants, but also with that comes a lot of decisions that you need to make. So I
32:55 don't know if you can't build really amazing production apps using Bolt or Lovable now,
33:01 but I think basically if you want the most cutting edge abilities of the models and you want to
33:06 be able to make all the decisions on your own, it's probably best to be on one of these tools.
33:13 What I'm feeling and hearing is that planning work that you did,
33:16 that's the stuff that Lovable, Bolt, and would you put Replit in that bucket too?
33:20 Yeah, for sure. Lovable, Bolt, Replit, Base44. v0. Yeah, v0, all same bucket.
33:27 So essentially, they're doing that planning for you. And as you said,
33:32 they're very opinionated. They try to make it easy. So it's just like,
33:35 "Here's how to do it. Here's the way we think is best for people." And what you're saying is
33:40 once you're trying to get a little more serious about it or want to go in a different direction,
33:44 you don't have the power to change how they plan. So Cursor lets you do that.
33:49 Yeah, I don't want this to come out like I'm badmouthing them. Base44, let's say.
33:53 No, absolutely. Yeah. Base44 does an amazing job at basically taking all the complex guesswork out of
33:58 building product and just allows you to just go with the vibes and build,
34:03 but it will do sign in with Google for you and it will do a database,
34:07 but then you don't have decisions on what database am I using. Do I need sign in with Google this way
34:12 or another way? It would just do it out of the box. So that's basically the trade-off there.
34:16 Awesome. Shout out Maor, the founder of Base44. Yeah. Maor Shlomo. Yeah. He's amazing.
34:24 Okay. I just love how this is like the way you're like flinging, what's the word? Slinging models
34:32 like Gemini 3 for frontend. I love that you've never written any code and you're just like,
34:37 "Cool, use Gemini for this and Claude for this. And I'm just working on Cursor,
34:41 talking to this CTO, helping you build stuff and build significant product."
34:48 Yeah. We just live in the craziest of times where basically the world changes once a week, it feels
34:56 like. And there is just no boundaries. You can use all of these just on your regular MacBook
35:03 or regular laptop. And I have these moments, I call them time machine moments, which is
35:10 basically this week, for instance, I was prepping for the podcast using Claude with a project.
35:17 I was building, I was fully localizing StudyMate from Hebrew to English, which I did in two days,
35:22 which would probably take a dev team weeks. And I was building a personal site, which went from
35:28 no domain, no nothing, to live on a domain within an hour and a half. And I was doing all three of
35:33 these in parallel. And there was a point where basically all three of the agents were running,
35:39 so I didn't have anything to do. I just had to let them think,
35:42 and these are the time machine moments where I feel like I was in the future and I just stick
35:46 my head out of the time machine and whoever's next to me, at the moment it was my wife,
35:51 I'll just say, "We live in the future." And she'll be like, "Huh, what?" And I'll be like, "No, no,
35:55 don't worry about it." But it's just basically so crazy that all these things are just an API away.
36:01 You can use anything. So I think it's an awesome time to be curious and optimistic and hardworking.
36:08 These are my favorite kinds of podcast guests. People that are living in the future, figuring
36:13 out all these things and then are just kind of come back, as you said, poke your head out of the
36:17 rocket ship and just like, "Hey, here's this thing that I figured out. Here's where we're going."
36:21 Yeah, best time to be alive. So awesome. So it looks like it's finished.
36:27 So now what we're going to do is we're going to run the app locally and we'll be able to see
36:32 what Composer ended up building and we're going to see if anything else is needed
36:38 on our end to maybe do some manual review. Does that sound good?
36:42 Sounds great. And I love, that was like, I don't know, a few minutes
36:45 where if it was a human engineer, it'd be like days, maybe a week for work.
36:50 For sure. Yeah, for sure. No, Composer like the one thing is it's just so,
36:55 so blazing fast, keeps you in flow. So yeah, full features take minutes.
37:00 And it probably costs a couple bucks in AI credits. I don't even look. I used to be so stingy about paying for products and now I'm just basically,
37:10 I look at it all as tuition, as stuff that I'm paying for
37:14 learning. So I don't know how much it costs, but it's definitely worth it.
37:18 That explains why they're the fastest growing products in history.
37:21 100%. Your marketing website sets the tone for your brand and is the one touchpoint that
37:27 every single one of your customers sees. In today's age, if you're still having
37:31 a hard time making small changes and simple updates to it, you are doing something wrong.
37:35 That is why so many companies from early stage startups to Fortune 500s,
37:40 including companies like DoorDash, Zapier, Perplexity, and ElevenLabs turn to Framer,
37:44 the website builder that turns your .com from a formality into a tool for growth. Framer works
37:50 like your team's favorite design tool and comes with real-time collaboration, a robust CMS with
37:56 everything you need for great SEO and advanced analytics that includes integrated AB testing.
38:01 Changes to your Framer site go live to the web in seconds with a single click and without any
38:06 help from engineering. Whether you want to launch a new site, test a few landing pages
38:10 or migrate your full.com, Framer has programs for startups, scale-ups, and large enterprises to make
38:16 going from idea to live site as easy and fast as possible. Learn how to turn your website into a
38:23 growth engine from a framer expert or get started building for free today at framer.com/lenny,
38:29 that's framer.com/lenny. Rules and restrictions may apply.
38:33 So now we have this feature, which basically we built and I can ask it to make some changes
38:39 because it's running locally and once it's ready, I'll be able to ship it to
38:43 users. So now the next phase after I've QA'd it and basically tested it manually,
38:49 I'll have Claude review its own work. So what I'll do is I'll reopen Claude Code.
38:56 I love this because this is one of the things that comes up a lot in this podcast is writing
38:59 code is now so easy. The main challenge people have is reviewing the code that AI has written.
39:04 100%. And what you're doing here is you're having Claude review its own code.
39:08 Yeah, so this is another thing where it's very difficult for me to catch mistakes.
39:13 So my review process has gone through a bunch of iterations to really be as good as possible
39:19 and to catch as many things as possible. So I'll always manually QA at first to make sure
39:25 if I can see any mistakes that Claude made. And then what I'll do is basically /review.
39:32 And this tells Claude to start reviewing its own code. But what's even cooler and something that
39:39 I'm really proud of is I will usually do multiple reviews and I'll have Codex, which is ChatGPT's
39:47 competitor to Claude Code, as well as cursor open, and I will have each of them review the code. And
39:55 then what I do is I have a /command called peer review, which is really interesting. And basically
40:02 what it does is it's going to take Claude, which is usually the agent who I'm working with.
40:07 And just to put this in a mental model, this is basically my dev lead that I'm working with.
40:16 The /command is basically saying, "You're the dead lead on this project. Other team leads within the
40:22 company have looked at your code and reviewed it and found these issues." Don't take what
40:27 they said at face value. The reason is you have more context than them and you led this project.
40:33 You need to either explain why the stuff they found are not real issues and wrong or fix them
40:40 yourself. And it's really cool because the way I look at these things is I look at the models,
40:45 I try to imagine them as people and I can really tell you how each one of these
40:51 would be as a real human because they have- Each model. Yeah. Each model has such distinct characteristics. So let's say Claude, she would
41:00 be the perfect CTO. She's very communicative. She's very smart. She doesn't just go with the
41:07 flow and do whatever you tell her. She's very opinionated, but also super collaborative, which
41:12 is I think why I'm always drawn to Claude because I need to do so much learning and it's your dream,
41:20 a very communicative, but very opinionated dev lead, but then there's also Codex.
41:27 So I use Codex 5.1 Max, whatever. I don't know, they're not the best at naming models,
41:33 but GPT's model. I always imagine it as like the best coder within the company who comes
41:40 to the office with a hoodie and sandals and sits in a dark room. And you basically only
41:46 bother him when you have the worst bugs and you say, "Listen, we have this bug and it will just
41:50 close the door for two hours and come out and say, I fixed it." And you're like, "Wait, what? Are you
41:55 going to tell us what happened or whatever?" And he's like, "Don't worry about it. I fixed
41:57 it." It's like really not communicative, but it solves all the worst problems. And let's
42:03 say Gemini is like a crazy scientist who's super artsy, super talented at designing,
42:10 but if you sit next to it and watch it work, it's terrifying. You would fire that person
42:14 instantly. This might be just my experience, but when I'm using Gemini within antigravity,
42:19 which is Google's new competitor to Cursor, when it's writing code, you can
42:25 see the steps it's taking and it's terrifying. You'll say, "I want you to redesign the top of
42:30 the dashboard." And you're looking at its thought process and it will say, "Oh, first things first,
42:35 I'll delete the dashboard." And then it'll be like, "Nope, that was a mistake. I'll bring
42:39 it back." And then it will say, "Oh, can I edit the database?" And you're like, "No,
42:44 do not edit the database. You're just doing a redesign." And then it will end up designing
42:47 something beautiful. So the way there is a rollercoaster and very scary, but at the end
42:53 of the day, Gemini is very good at design. So I think that using all these models
42:59 and basically playing to their strengths and mitigating their weaknesses by using
43:04 other models is a game changer for me. So I'll do peer review a bunch of times and I'll have
43:10 other models review other models code and kind of have them fight it out basically. Sometimes
43:18 Claude Code will get really sassy and be like, "This has been raised for the third time. And
43:22 for the third time I'm telling you, this is not an issue. This is by design." So it's
43:26 just a really cool thing that I've added and I haven't seen many people doing it.
43:31 That is such an incredible rant/way to understand what's going on. Okay,
43:38 awesome. So we just ran the review. So show us what we saw there and let's
43:42 actually try this peer review. I'm really excited to see what you learned there.
43:45 Yeah. So basically Claude has reviewed its code and it's found a bunch of bugs, a critical bug
43:51 it found in the prompt, some high bugs, some medium bugs, and now what I'll do is I'll do
43:57 the same thing with the other models. So Codex has a built-in code review that you can do, or I just
44:05 like to say review all the code in this branch. Of course, branch is referring to the GitHub
44:13 branch that we're working on. We're not working on the live code base. And then I'll do this with
44:18 Composer say with, let's do it with Composer One. So I'll do /review here as well. And basically
44:27 these are both going to run and do a in-depth review similar to what Claude does. But again,
44:32 because of the differences between the models, they're all going to catch different things and
44:36 they're all going to look differently, and this is a really cool way to work.
44:40 It's basically if you had other team leads within the company review the code. Here,
44:44 you can see how fast Composer is. I think GPT probably will take a bunch of time. Like I said,
44:49 it's in its own dark room right now reviewing code and we'll come back in a few minutes.
44:55 Okay, cool. So we can let these run in. We don't actually have to
44:57 go through the whole process, but is the idea once you get these results,
45:00 you run peer review and you copy and paste kind of these results. Is that the idea?
45:04 Exactly. I'll copy and paste the results. I'll do peer review and then I'll say dev lead one
45:08 and then paste from one of the models. And then I'll say dev lead two and paste from the other
45:12 model and basically have them fight it out until I feel like we have no more issues.
45:17 Incredible. For me, this is super important because I'm not technical and
45:21 I'm not a developer. And I'll also use /learning opportunity a bunch
45:25 during this to learn about stuff that I don't understand or don't fully grasp.
45:31 Incredible. What a clever solution to solving this code review problem where it's like,
45:35 I don't know what you ... I don't know how to recode, so what am I going to even ... Yeah.
45:39 Yeah. Okay. Incredible. Let's wrap up this workflow. Is there anything else that's
45:45 important in this workflow? And again, all this stuff is going to be available
45:48 where people can just plug this stuff into their Cursor account and use it themselves.
45:52 100%. The one thing I'll say is that I think just like working in general with AI and even just like
46:01 working on any product, doing constant postmortems is critical. So a lot of
46:08 times we'll find all these kind of bugs or maybe Claude will fail to execute something
46:13 correctly. And at the beginning when I started vibe coding, I would basically
46:17 just keep running at it like running at the wall and until it worked. And once it worked,
46:21 I was like, "All right, awesome. This works. Let's keep going." But I've learned over time
46:25 that updating documentation and tooling is one of the biggest hacks for productivity.
46:31 So when Claude will fail to do something or I'll see this really bad bug that shows that Claude
46:37 really didn't understand something, I'll ask it, "What in your system prompt or tooling made you
46:42 make this mistake?" And Claude will kind of like go introspective and think of what made it create
46:48 that mistake. And then I'll say, "Okay, great. Let's update your tooling and documentation so
46:53 that this mistake never occurs again." And I do this every time I'm either building
46:57 an internal tool or anything. And I think this is just like working.
47:03 If you end up doing a bunch of mistakes and then end up releasing the feature to users,
47:08 so you're like, "All right, it's a big success." But going back and even when you've succeeded,
47:13 looking and understanding what you did and what you could have done better is critical.
47:17 And also using AI, this is probably one of the biggest unlocks. Going back to your prompts,
47:22 understanding what was not good enough, iterating on them and then seeing how AI's responses get
47:28 better, I think that's probably one of the most important things and one of the things that
47:33 divides between people who are okay with using AI and the people who actually know how to use it.
47:38 That is such good advice. So what I'm hearing is when the models do
47:43 something dumb, make a mistake, you ask it to reflect on what the mistake it made was,
47:48 and then you update the /command prompts with that knowledge so that in the future,
47:54 it's not making that same mistake, and it just keeps getting better.
47:56 Exactly. These things just keep getting smarter and smarter. So you're building up this
47:58 really incredible prompt that just gets better and better.
48:01 Exactly. Not always the /commands. It will sometimes update
48:05 different documentation or its tooling, but basically it's understanding what
48:09 the root cause of the mistake that the AI made and fixing it.
48:15 Awesome. So the models are getting smarter and then there's also the other parts of
48:20 your workflow can get smarter as you find flaws in the way it does stuff.
48:25 100%. Yep. Amazing. Okay. Is there anything else there before I move in a couple other directions?
48:31 I think that's it. I think we covered pretty much everything. Basically, just to wrap this up,
48:35 what I do is I do a bunch of code review and then update the documentation so that everything
48:39 is documented. So the next time I try to build a feature in this area, there won't be any mistakes.
48:45 And then I'll do a bunch of testing. I'll do some user testing as well before I release this to
48:50 general availability. Obviously we're not going to release this. This was just a show, but hopefully
48:54 maybe by the time the podcast comes out, I'll have done this correctly and release the feature.
48:59 It's incredible that this was not possible, I don't know, two years ago, maybe a year ago,
49:04 you are a product manager shipping a product without knowing how to write code,
49:11 barely knowing how to review code. You said you're afraid of looking at code. As a product manager,
49:15 you're building a product in Cursor using all of these different AI models. You're
49:21 making money with this product. We're so used to this now, but it's insane what is now possible.
49:29 It's the best time to be live. 100%. I think that I understand the fear,
49:35 but AI just makes it so much possible. Just a quick side note here, my brother, who I'm
49:39 building one of the apps with is an entrepreneur. He has a beautiful business that helps old people
49:45 and seniors understand to use technology and AI better. And he's basically doing the same
49:52 kind of learning as me, and he's replaced all of the tools he was paying for. I think
49:56 he was paying for Zapier and Airtable, and he's basically built a full-fledged CRM system and
50:03 automation system for his business completely alone. So for the people who are curious,
50:10 optimistic, hardworking, this is the best time to be a builder.
50:14 And what I love about this conversation we're having here is it feels like the
50:18 biggest barrier for a lot of people is like, how do I get started? What exactly do I do?
50:22 I open up cursor. It looks very intimidating. I don't know how to write code. I don't know
50:27 how to build stuff. I don't know about databases. And so you're going to be
50:30 sharing all these /commands and basically this whole workflow with the audience.
50:34 Yeah. Okay. And like I said, just start at GPT. Start on GPT, tell it what your idea is,
50:40 tell it to explain to you what are even the first steps of thinking,
50:43 what are the decisions you need to make? And just be inquisitive, learn.
50:48 Don't rush things. It's very important to just dive in and really spend the time to learn.
50:55 And you share this. One of your /commands is learning opportunity, and it's how you learn
50:59 a lot of these things. Just teach me this thing and how this database issue works.
51:04 Exactly. Okay. There's a couple directions I want to make sure we touch on. One is coming back to
51:08 a question I asked earlier about how this might work at a larger company. Say it's not like Meta,
51:12 but just like, I don't know, a thousand person company, 500 people. How much of this can you
51:17 plug and play into a workflow as a PM at a larger company? What would be your advice for
51:22 someone that may want to start trying to ship code, at least showing people what's possible?
51:28 I think that first making your code base AI native is a really important step, and I think this needs
51:34 to be done by technical people. So basically my codebase has a ton of just plain text in it. So it
51:43 will have a bunch of markdown files that explain to agents how to work in certain areas of the code
51:48 base and high level structure so that the agents navigate through the code base easier.
51:54 And I think that if this is set up in a really good way, I still don't think
52:00 PMs should be shipping heavy database chain migrations or any big project,
52:06 but contained UI projects, especially if you just build it, create the PR and send
52:13 it to a dev to do the final finishes. I think that's definitely something that's
52:18 possible. And I think we're going to see that a lot in the next coming years. I
52:20 think basically everyone's going to become a builder, so it should be really interesting.
52:25 Okay. So your advice here is as a PM, maybe don't go right to Cursor, start building, shipping,
52:31 trying to ship features to production, especially complicated features. Do you think we'll get
52:35 there? Do you think in a couple years, PMs will be doing this and it'll feel less scary and crazy?
52:42 If there are PMs. Yeah, I think titles are going to collapse and responsibilities are
52:49 going to collapse and everyone's just going to be building. I definitely think that the models,
52:55 the context window is getting bigger, the models are getting smarter and I definitely see how PMs
53:02 or any other background can be writing. At the moment, I wouldn't wait for that. I would use this
53:07 as a collaborative learning opportunity to work with your dev team. It's going to be difficult.
53:14 A lot of developers are very, very skeptic about the current state,
53:18 and I think that it's going to be a lot of sales work on your end to convince,
53:22 but if you're able to convince, and I think teams that are really sold on this and want
53:27 to take the time to work on their workflow about how can our team become more AI native,
53:33 I think that these teams are going to probably be a few years in the future and they're going
53:38 to look back at the few weeks they spent setting this up as the best time they spent.
53:43 Let me ask you another question around just the job of a PM. One of the biggest fears people have
53:48 with these AI tools for PMs for every function I imagine is just you start to rely on these things,
53:56 your skills start to atrophy, you're producing all this slop that looks great,
54:01 cool, amazing strategy doc. No, it's actually not at all good. Are these Linear
54:05 tickets or just products that are half-baked? What's your take on these two parts of just like,
54:10 how has this impacted your craft as a PM? Do you feel like this is weakening your
54:16 skills because you're so reliant on these tools and just how do you keep the quality
54:21 of this stuff up and not just like, "Eh, it's just a bunch of AI generated slop."
54:25 I have a very strong disagree to this and I've heard it a bunch. I remember when I started using
54:32 Tal Raviv has this whole course on building a PM Copilot using projects, which is probably one of
54:40 the best courses that you can take. And when I started working with my own Copilot, I remember
54:46 people at work looking and saying like, "Oh, so you're basically outsourcing your thinking." And
54:51 to me, that's just the worst way to look at it. And I think for some reason, these people usually
54:59 have a high correlation with the kind of person who doesn't like to show their presentation when
55:03 it's only 10% done or doesn't want to ask for help a lot. I think that there's a misconception with a
55:10 lot of PMs that the job is always having the right answers and being the smartest person in the room.
55:16 And at least how I was trained and how I believe the role of the PM is, it's the exact opposite.
55:22 It's basically harnessing anything that can get us as quick as possible to delivering the right
55:29 solution to users. And I just think this is like that really smart person that has context
55:34 or your mentor or whatever, but is just always available and doesn't judge you and can really
55:40 help you. So if you're using it to just create your outputs and then putting them out there,
55:46 yeah, that's AI slot, but it's also human error. I think it's really important that you own your
55:52 own outputs. If you put anything out there or show something in a product review and you say, "Oh,
55:58 sorry, that was built by AI." That's your mistake. I think if you use these intentionally and really
56:06 take the time to understand how to use AI in the correct way, it's one of the biggest game
56:10 changers that will make you much better as a PM. And another thing here is that, especially for
56:17 more junior PMs, it allows you to play at such a higher level than you would normally. I think
56:23 that at Wix, I wasn't thinking of what's the marketing strategy of the company and how will
56:29 the onboarding be completely revamped within the whole product. But on my side product,
56:35 I can just do whatever decisions I want and think of the strategy and marketing and the messaging.
56:39 And this is basically just getting me reps, which is one of the most important things
56:44 at the beginning of your career. So I understand the fear that how do you outsource certain stuff
56:51 and you're not owning 100% of everything, but I think the upside is so much more valuable. And I
56:58 think the only way that AI makes you worse at your job is if you're using it wrong.
57:03 Is there anything that you've learned about reducing the sloppiness of the output,
57:08 just like a tip for keeping the quality high of the stuff that it produces?
57:13 Similar to people, setting up AI for success, for the task at hand. So if I just brought in
57:23 a junior to write a deck or something and I didn't give it any guideline, I just said, "Give
57:30 a strategy deck." He would probably just go online and find top strategy deck and just reproduce
57:36 that, which is basically what AI is doing. It's basically just fed all of the internet.
57:40 So instead of that, guiding it and giving it context on what your style of writing is and
57:48 what you're trying to solve and all these different things, I think that's probably
57:51 one of the biggest unlocks. So that's just a quick tip. And also Cursor has a /command called deslop,
57:58 which is basically going back over the code. I don't know if this is integrated into the
58:03 product yet, but it's on Twitter. Their founders have been talking about this,
58:07 so that's definitely something I would run after just to make sure that no slop is left behind.
58:12 That is so funny, deslop. Okay. One more question,
58:17 which may lead to something else, but kind of going in a whole different direction.
58:21 You used AI to help you actually interview for the job that you got at Meta. Talk about how
58:28 you did that, because a lot of people right now are struggling to find a job reading about all
58:32 these people using AI to help them interview. You actually did it. What did you use? What worked?
58:37 I feel like the analogy here is I have 12 nieces and nephews and you can see how people who have
58:44 grown up in a different world, how their mind is formed differently. So if you ask me, how do you
58:50 answer a phone, I'll do this. But a child now, when you say, "How do you answer the phone?"
58:55 They'll do this. They'll do the iPhone answer. And I feel like people who are growing up now in their
59:04 professional lives were the same just with AI. So every time I'm faced with a new challenge
59:08 or problem, I think AI first how to solve it. So Meta reached out and said they'd
59:14 like me to interview. Straight away, I opened up a project within Claude. I started looking
59:19 online for all the best information out there, things that I resonated with. I took a ton of
59:24 frameworks and stuff from Ben Erez who has written a guest post for you, who I think
59:30 is one of the best minds out there right now. And basically I created a project which was my
59:35 coach, which I would come and consult what to do at each phase. I would mock interview with,
59:42 and this was amazing. Also, I created a game in Base44, which helped me ... I
59:48 was really struggling with segmentation within the product questions, so thinking
59:51 of the correct segments. So I basically just created a quiz game, which creates questions
59:56 and different segmentations and I have to choose. So this was like, I spun this up. It's a web app
60:02 that I would play sometimes when I was on the bus to work. So basically, I think Ben talks
60:08 about this a bunch, so I don't just go read Ben's stuff, but just creating a project and feeding it
60:14 with all the best information on the internet and then mocking a bunch. I will say that the biggest
60:19 game changer for me was doing human mocks. So cold outreaching to people on LinkedIn and
60:26 having them do actual mocks for me, I think that at the end of the day, especially for the Meta PM
60:32 prep, which is super competitive and difficult, I think there's no way to get around that.
60:38 That is so cool they use that post. I wasn't aware. We're going to link to it. And in that
60:42 post, Ben shares all these prompts you can feed ChatGPT to help you prepare for interviews,
60:48 do mocks online. It's a really important point to say that those take you to a point, but it's
60:53 actually better to use humans. I actually have a post coming out soon in collaboration with Noam
60:59 Segal about how everyone is using AI to interview. And one of the most interesting ways I've heard
61:05 people and that we've found in this research was that people use it to get feedback. They record
61:08 the interview and then it gives them feedback. Here's where you could have done better.
61:12 Here's what you missed because the feedback loop is so missing. No one ever tells you,
61:16 here's what you did badly in this interview. No one tells you that, and AI can do that.
61:21 So I'll add two things to that. One, which is exactly this. So I'll mock with AI. Also,
61:27 I did something really cool where there's a question bank online free by Louis Lynn,
61:33 which basically is an always updating bank of questions that people are asked in real
61:37 interviews. And I basically used Comet, which is the Perplexity's browser. And I had the
61:44 agent run all kinds of analyses on what the most asked questions are. And that's how I knew how
61:49 to prioritize what questions I would mock. And then at the end of these mocks, I would
61:56 tell Claude within the project, "You're my coach and I don't want you to make me feel good. I want
62:02 you to make me as ready as possible for these interviews. So give me feedback, like you said."
62:07 And the other thing that I did was really cool was some questions where I didn't have time to
62:11 mock. I would ask Claude to play the candidate, and then it would just give me a really good
62:16 answer. And I could also learn from that, like learning from someone who does a perfect answer.
62:20 Oh, man. I really love the way you phrased it, that people kind of in your generation,
62:24 the default is, "I have something I need to do. Let's go to AI immediately and help
62:30 me prepare for this thing, help me figure it out." Yeah. And this comes back to this quote that I always think about, which I think everyone is always
62:36 hearing, but it's such an important quote that it's not that you will be replaced by AI at
62:42 least for a long time. It's you'll be replaced by someone who's better at using AI than you.
62:47 I agree. And that's what these conversations are for to help people keep up with all that and to
62:51 learn some of these skills. And again, see where the future is going and start to learn
62:56 how to get there yourself. Okay. Zevi, before we get to our very exciting lightning round,
63:01 I'm going to take us to a recurring segment on this podcast I call Failure Corner.
63:05 And why I love this segment is people come on this, just even this conversation,
63:09 it's like all these amazing things you figured out, everything is going
63:12 so well. People rarely hear the things that don't go well, and those are often the most
63:17 interesting and impactful stories. So the question is just, what's the story
63:22 of a time you failed in your career and what did you learn from that experience?
63:26 Yeah, I love this. I love this. I love Failure Corner, big fan. So I'll tell a story about
63:34 when I started at Wix. So basically I started within Wix as a student program and straight
63:38 out of the student program, you get put into a certain team. So I was in the editor, which is
63:45 the core product of Wix. And the other PMs were just the best PMs almost at Wix.
63:51 There's four other people had much more experience than me and they were ridiculously good. And I
63:56 remember coming in and thinking like, my first product review, I'm going to blow these people's
64:00 socks off. They're not going to believe how good of a PM I am. And I basically didn't
64:05 really share what I was thinking. I would work tons of hours alone and I was like,
64:11 "I'm going to kill this product review. They're going to be so impressed." And I ended up failing
64:16 miserably. My product review was not good. It wasn't the format they expected. They
64:21 had a ton of questions that I missed and I felt awful when it was over. I was like,
64:26 "Ah, you're such an idiot." And I saw that everyone was like, "All right, cool. Yeah,
64:29 just come back in two weeks and we'll keep getting at this." And I understood in that moment that
64:36 they had zero expectation of me being a 10X PM, but the expectation of me was being a 10X learner.
64:42 And the second I understood that, my whole mindset shifted. And I think this is probably the best tip
64:48 that I give now to junior PMs is basically be the best learner you can be at the beginning. No one
64:55 expects you to know all the answers and no one expects you to be good. So basically what I did
64:59 was I took each person on the PM team, there was four other PMs and I assessed what their
65:05 strength is and used them as a mentor for that. So Neri who's still my mentor till today,
65:11 he has the best product sense of anyone I've met. Oya is super,
65:14 she's like a methodology expert. She just thinks in frameworks. Yahra, who is the head of product,
65:21 basically can look at a product and then instantly understand the third and fourth order effects
65:25 of them, the system thinking. So every time I had an issue with one of these areas, I would
65:29 come to one of them and consult them, and this does two things. First of all, I learned a ton.
65:35 And the second thing is that when the next time, the next product review,
65:39 my success felt to them like their success because it wasn't this kid who's trying
65:44 to show us up how cool he is. It was like our mentee kind of making us all proud. And it was
65:51 such a great shift for me. And basically at the end of the day, I really excelled through this.
65:57 That is an awesome story. And this idea of learning is such a good thread throughout
66:02 this whole conversation that AI is good at getting stuff done, but it's also really
66:06 good at helping you learn how to do the thing and to be this partner, this thought partner,
66:11 the way you talked about the interview process you went through and this learning opportunity
66:16 /command. So awesome. Great story. Zevi, okay. Before we get to our very exciting lightning
66:22 round, is there anything else that you wanted to share? Anything you want to leave listeners with?
66:25 Yeah. So kind of to tie back into the first thing I said where if people walk away thinking,
66:33 "Zevi's so cool." Then I've failed here. I think that it's just the best time to be alive,
66:40 I think. It's the best time to be a junior contrary to what a lot of people are saying how
66:46 there's no more junior roles out there and people get out of school and you can't find a role.
66:52 Yeah, that's true. But also when else in history could you get out of school and
66:55 just build a startup on your own with a couple of friends completely bootstrapped. And I see
67:02 more and more people towards the end of my time at Wix, I was interviewing and I saw
67:09 more and more people building their own stuff with AI. And I think contrary to what a lot of
67:15 people think, it's the best time to be a junior. It's the best time to be a learner. And I think
67:19 if any listener is listening to this and you're a curious person, you're a hardworking person,
67:26 I want to say kind, I'm not sure, but if you're a kind person and a good communicator, you have such
67:31 an unfair advantage and you can give more value to companies than most people who have 20 years of
67:37 experience. So I really hope people get inspired by this and start killing it with their projects.
67:44 Amazing. So many ways to be inspired from this conversation. Zevi, with that,
67:47 we've reached our very exciting lightning round. I've got five questions for you. Are you ready?
67:52 Yep, let's do it. What are two or three books that you find yourself recommending most to other people?
67:58 So I'll take one from each kind of genre. So in fiction, I love The Fountainhead by Ayn Rand,
68:06 one of my favorite books. Really makes you think, really makes you feel. Business books,
68:12 I'm a big fan of Shoe Dog, the Nike story, one of my favorite books.
68:15 I just finished reading that. So funny. Amazing. This is great. It was great.
68:18 Yeah. I love Shoe Dog. And then more on the psychology side Mindset by Carol Dweck,
68:25 who coined the term growth mindset. It's just such an amazing book. It
68:30 kind of sounds like a self-help book, but then you understand that it's completely
68:34 psychological and is based on research and that book completely changed my life.
68:39 Really, I was always with a fixed mindset, and then after reading that, I kind of understood
68:44 that it was something holding me back. And since then, I've been really,
68:47 really trying to cultivate a growth mindset. So I really recommend everyone reading that.
68:51 Again, connects to that thread of the way you described it, being a 10X learner versus a 10X
68:56 doer. Okay. Next question. Favorite recent movie or TV show you have really enjoyed?
69:02 Yeah, actually, my wife is really into film, so we watch a lot of TV. It's probably our favorite
69:08 together time. I just finished watching The Pitt,
69:11 which was amazing. It was really good. And my first recommendation to everyone
69:16 is if you haven't seen Severance run to see Severance, one of my favorite shows.
69:21 Is there a favorite product that you have recently discovered that you really love?
69:24 This is a good question. I'm always trying new products. I'll always have three or four browsers
69:30 installed on my computer and all this different kind of stuff, and I recently discovered a Loom
69:36 alternative. I was kind of disappointed with Loom. They were taking so much money and the product,
69:43 I don't know, I just didn't love it. And there's an open source alternative called Cap,
69:47 which is just really well-crafted. You can see that the person was really sweating the
69:53 details and it's just a really, really great alternative. So I've been using that recently.
69:58 There's also a product called Supercut that I love that's also a Loom alternative.
70:02 Shout out. Okay. Two more questions. Do you have a favorite life motto that you
70:06 find yourself coming back to in work or in life? Yeah. I'm kind of between two right now. One, which has become a Twitter meme basically,
70:14 which is you can just do things. I feel like that is basically going always in my
70:19 head every time I do something that I'm just shocked at the speed and ability to
70:24 do things now so you can just do things, and the second one I stole from my brother. His
70:30 motto is nobody knows what the fuck they're doing. And I just love that. And I think it
70:34 kind of makes you take life more lightly. So yeah, nobody knows what the they're doing.
70:39 I think people see these companies on the outside and it feels like everything they've got all
70:43 figured out. And if you're ever on the inside of a company that's doing really well, you're like,
70:47 how is this staying on the rails? How is this still a thing that is working? Doesn't make any
70:51 sense. It's all about to fall apart. Yeah. Okay. Last question. You've had a long entrepreneurial
70:59 thread throughout your career. There's a couple other real world businesses you've
71:04 started in the past. You did a thermal clothing business and then like a hummus
71:08 delivery thing. So maybe pick one of those and just tell the story of what that's about.
71:13 Yeah, I'd love to. Really fun that you asked about this. So I'll tell the thermal clothing because
71:19 I think it's really cool. So in high school, I was selling thermal clothes in 10th grade
71:24 for one of my sister's friends or something, and basically it was just packs of thermal
71:30 clothing, shirt and pants. I grew up in Jerusalem, so it's a bit chillier there.
71:34 So it was perfect for the weather. And in 10th grade, when I was selling them, they were like 20,
71:40 $25 a piece and I was making like $4 a sale, and if you look in the food chain, I was like
71:47 sixth or seventh down the line. So this was like crazy margins. So during the summer I thought
71:52 about it like I should just go straight to the importer. So throughout the summer I called the
71:57 importer and at first he was really, really mad. He was like, no, you have to work for me for years
72:02 to get to this state. And I said, listen, man, I'm finishing school soon. This is not going to be
72:06 my career. Either do it or not. And we basically negotiated throughout the whole summer. And this
72:13 was also like how I did things before ChatGPT. So he would throw out something, he'd say, "Oh,
72:20 the import tax has gone up." And I'll just search Google, like Import Tax Israel and start reading.
72:25 And I'll be on the phone with him and I'll be like, "Hey, I would just basically stall." And
72:29 then I'd somehow come back with a challenge. And I ended up getting a really great price,
72:36 like 12 and a half dollars a piece. So I was making 100% profit and I spread throughout a
72:42 bunch of different schools. Each school, I had the coolest people in school selling for me. And then
72:49 a really fun thing that I did was we had a really awesome basketball team and our basketball team
72:55 would basically be 30 points up within the first half and it kind of got boring for the crowd.
73:01 So I wrote a song, like a basketball chant about Thermal Clothes that
73:05 basically has my number within it. And the end of it was if you join in now,
73:11 we'll give you a discount. And it was with drums and everything. And still when I go to Jerusalem,
73:16 I know some people who I don't even know my number by heart because they know it
73:20 by the tune. And sometimes when I walk in Jerusalem, people stop me and say like,
73:24 "Hey, it's Thermal Zevi." So that was just a really cool experience as a kid.
73:29 This explains so much just the marketing genius of that move. Oh man. Okay. Zevi,
73:36 this was incredible. Two final questions. Where can folks find you if they want to reach
73:40 out and maybe follow up on some of the stuff? We'll link to the scripts and prompts and all
73:44 that in the show notes so you don't have to read that, and then how can listeners be useful to you?
73:50 Awesome. So I've been helped throughout my whole career a ton, so I love helping any
73:56 way I can. So reach out on LinkedIn or on X. I'd really love to help whoever I can. How can
74:03 listeners be useful to me? So if you're a student, try StudyMate, tell me what you think. If you're
74:09 in Israel and you are not using dictation yet, try Dibur2text. Tell me what you think.
74:14 Amazing. I just love how much you're giving away and how useful that's going to be to so
74:18 many people. So again, we'll link to that in the show notes. Zevi, you're awesome. Thank
74:22 you so much for being here. Thank you so much for sharing so much. This is going to help, I think,
74:25 a lot of people and I think it's going to help people get over the hump on. Okay,
74:28 I see all these people doing cool stuff. Here's how I can actually do this stuff. So
74:33 thank you so much for being here and for sharing so much.
74:35 Thank you for having me. And if you build something cool
74:38 with some stuff that I learned here, hit me up, send me. I'd love to see.
74:43 Amazing. Zevi, thank you so much for being here. Thank you. Bye everyone. Thank you so much for listening. If you found this valuable, you can subscribe to the
74:51 show on Apple Podcast, Spotify, or your favorite podcast app. Also, please consider giving us a
74:57 rating or leaving a review as that really helps other listeners find the podcast. You can find
75:02 all past episodes or learn more about the show at lennyspodcast.com. See you in the next episode.
$
How a Meta PM ships products without ever writing code | Zevi Arnovitz
[product development and MVP][AI agents and automation][developer tools and coding][productivity and workflows]
// chapters
// description
Zevi Arnovitz is a product manager at Meta with no technical background who has figured out how to build and ship real products using AI. His engineering team at Meta asks him to teach them how he does what he does. In this episode, Zevi breaks down his complete AI workflow that allows non-technical people to build sophisticated products with Cursor.
*We discuss:*
1. The complete AI workflow that lets non-technical people build real products in Cursor
2. How to use multiple AI models for differ