Skip to content
Lenny's PodcastLenny's Podcast

Meta PM Zevi Arnovitz: How a non-coder ships real features

Through staged Cursor workflows and multi-model peer review on Claude; Codex and Gemini help a non-technical PM turn Linear tickets into shipped features.

Lenny RachitskyhostZevi Arnovitzguest
Jan 18, 20261h 15mWatch on YouTube ↗

EVERY SPOKEN WORD

  1. 0:00 – 4:48

    Introduction to Zevi Arnovitz

    1. LR

      You are a product manager shipping product without knowing how to write code, barely knowing how to review code.

    2. ZA

      I have zero technical background. Did music in high school when Sonnet 3.5 came out. I remember watching a YouTube video building apps using Bolt or Lovable. It basically felt like someone came up to me and said, "You have superpowers now."

    3. LR

      These days, you're using Cursor with Claude Code.

    4. ZA

      If you're non-technical like me, code is terrifying, but AI just makes so much possible. In the next coming years, I think everyone's gonna become a builder. Titles are gonna collapse, and responsibilities are gonna collapse.

    5. LR

      The main challenge people have is reviewing the code that AI has written.

    6. ZA

      It's very difficult for me to catch mistakes. What I'll do is basically slash review. This tells Claude to start reviewing its own code, but what's even cooler is I have Codex as well as Cursor open. I will have each of them review the code.

    7. LR

      This comes back to this quote I think everyone's always hearing: "It's not that you will be replaced by AI. You'll be replaced by someone who's better at using AI than you."

    8. ZA

      It's the best time to be a junior, contrary to what a lot of people are saying, how there's no more junior roles out there. Yeah, that's true, but also, when else in history could you get out of school and just build a startup on your own?

    9. LR

      [upbeat music] Today, my guest is Zevi Arnovitz. Zevi's a PM at Meta. Prior to that, he was a PM at Wix, and this is a truly remarkable conversation that every non-technical product person needs to hear. Zevi is super young and has no technical background, but as a smart, young, ambitious person, has learned how to use Cursor and Claude Code to build significant and real products completely on his own, and he's created his own very clever and effective workflow that everyone listening can copy. To make that copying even easier, at the top of the show notes of this episode, you can download all of the prompts and slash commands and start doing all of this yourself. Zevi shows you how to work with Cursor to quickly add your ideas to Linear, to explore your idea with AI, how to develop your plan, how to then build the thing, and then have different LLMs review your code and update your documentation, and then use all of this as a learning opportunity to develop your own sense of how things work. I haven't stopped thinking about this conversation since we had it, and everyone needs to pay attention to what AI is unlocking for non-technical people. A huge thank you to Tal Raviv for encouraging me to meet Zevi. If you enjoy this podcast, don't forget to subscribe and follow it in your favorite podcasting app or YouTube. It helps tremendously. And if you become an annual subscriber of my newsletter, you get 19 premium products for free for an entire year, including Lovable, Replit, Bolt, Gamma, n8n, Linear, Devon, PostHog, Superhuman, Descript, Wispr Flow, Perplexity, Warp, Granola, Magic Pattern, Drake House, ChatPR, dmobbin, and Stripe Atlas. Head on over to lennysnewsletter.com and click Product Pass. With that, I bring you Zevi Arnovitz after a short word from our sponsors. This episode is brought to you by 10Web, the company that pioneered AI website building before ChatGPT. In the last three years, over two million websites have been generated with 10Web's vibe coding platform. 10Web's vibe coding platform is a powerful way to build websites. Think of it as Lovable for WordPress, front-end and back-end. Users can build any website at any complexity: e-commerce, portfolios, information websites, blogs, and it comes with a WordPress admin panel and thousands of ready-to-use plugins. 10Web also offers website generation as an API as a service for SaaS companies, marketplaces, hosting providers, MSPs, and agencies. SaaS companies can embed it via API, so that users can launch AI-generated sites directly inside of their platform, connected to their own data. Agencies and MSPs can get a white label dashboard to manage clients and resell under their brand. Hosting providers can self-host the API builder on their own infrastructure. Check it out at 10web.io/lenny, and use code LENNY for exclusive free credits and 30% off API or white label solutions. That's the number 10W-E-B.io/lenny. Vibe coding platform as an API. Today's episode is brought to you by DX, the developer intelligence platform designed by leading researchers. To thrive in the AI era, organizations need to adapt quickly, but many organization leaders struggle to answer pressing questions like: Which tools are working? How are they being used? What's actually driving value? DX provides the data and insights that leaders need to navigate this shift. With DX, companies like Dropbox, Booking.com, Adyen, and Intercom get a deep understanding of how AI is providing value to their developers and what impact AI is having on engineering productivity. To learn more, visit DX's website at getdx.com/lenny. That's getdx.com/lenny.

  2. 4:48 – 7:41

    Zevi’s background and journey into AI

    1. LR

      [upbeat music] Zevi, thank you so much for being here, and welcome to the podcast.

    2. ZA

      Thanks for having me, Lenny. I'm a huge fan of the show, and tons of people that I've admired most and learned the most from have been on here, so it's a crazy moment for me. I'm really excited for this.

    3. LR

      Hmm. I really appreciate that. I wanna start by reading actually a, a note I got about you from Tal Raviv, who is a previous podcast guest, many-time newsletter collaborator, one of the most AI-forward product managers that I know. I've learned a ton from him. So here's what he said about you when he, he introduced us: "Zevi's the most hands-on vibe coding PM I know, and I've personally learned so much from him. His engineers at Meta ask him to teach them how to do what he does. Every time we get coffee, I repeatedly get this feeling of, 'Everyone needs to be hearing this.'"

    4. ZA

      [chuckles] That's so nice.

    5. LR

      And so that's the goal. That's the goal of this conversation, is to help more people hear what you figured out. We're gonna get very hands-on. Uh, we're gonna do a lot of show versus tell, showing people what you've figured out about how to be a PM, uh, a non-technical PM building stuff. I'm gonna give people a little bit of background on you because I think this is gonna inspire a lot of listeners to feel like they can also do what we're about to show you. Uh, it is gonna look very advanced, but-... just give people a little bit of sense of just your background.

    6. ZA

      I'm very non-technical. I have zero technical background. Uh, did music in high school. Uh, a lot of Israelis, uh, do technology units in the army. I was not in a tech unit. And basically, a year ago, I was traveling with my wife, uh, for three months in, in Asia, and we were in Japan, and that was around when Sonnet 3.5 came out. And I remember watching a YouTube video, uh, I think it was either Greg Isenberg or Riley Brown, and they were basically building, uh, apps using... It was either Bolt or Lovable, just using AI. And it was, like, a crazy moment for me, 'cause I was watching this, and it basically felt like someone came up to me and said, "Hey, Zevi, there's this cool new technology you should check out. Um, you should really give it a try. Oh, and by the way, you have superpowers now." And the second I got home from Japan, I didn't even unpack my bags, ran to my computer, uh, opened Bolt, opened an account, and for the past year I've been building. And the last thing I'll say on that is, we talked about this a bit before we started recording, but I was prepping with Claude for the episode, and I was trying to clarify what my goal is for this episode. And Claude said, "If people walk away thinking how amazing you are, you've failed, and if people walk away and open their computer and start building, you've succeeded." So I really hope that, uh, we can inspire some people to do the same.

    7. LR

      Uh, I love that so much. Uh, I feel like that should be the goal for my podcast. If you're like, "I love that guest," uh, it's less of a, a win. If it's just like, "I'm so inspired to do the thing that they figured out," that is, uh, the real win. Uh, I love... Claude is the best. [chuckles]

  3. 7:41 – 14:41

    Overview of Zevi’s AI workflow

    1. ZA

      I agree.

    2. LR

      Okay, so let's, let's, uh, dive in and give people... With- Let's start with kind of a high-level overview of how you operate and use AI in your job. What are the core tools, and just what's kind of like the frame of reference for the workflow that you've figured out and how you operate?

    3. ZA

      This all started where I was a, uh, projects power user. I love projects, um, GPT projects-

    4. LR

      ChatGPT projects.

    5. ZA

      Yeah, exactly. GPT projects and Claude projects-

    6. LR

      Mm-hmm

    7. ZA

      ... which are basically a shared folder of chats, which share both custom instructions and a shared knowledge base. And I think it was around when GPT started using memory, where I thought it was interesting, but it, it really annoyed me, 'cause I do a bunch of different things. Like, I'm a terrible runner, uh, I'm a PM. I was a student, a psychology student, so I had all these different facets of life, and what happened was, uh, the memory feature was mixing stuff up. So, like, I talked to GPT about running, and it would be- and it would say, "Oh yeah, after this 5K, you're gonna crush all your next product reviews." And it's like, uh, I mean, okay, I understand that you have that in your memory, but it's just not relevant. And projects basically allows you to compartmentalise and, and have things within the, the right context. So tracking back to the story I told, when we came back from Japan, I started building this app. Uh, the first thing I noticed was that these products were built in a way where... And these- When I say these products, I mean Bolt and Lovable, were built in a way where they were super eager to write code. So their system prompt was, "You're a coding agent." So when you'd write something, they'd straight away start coding. So at the beginning of a project, this was super fun and exciting, 'cause they'd just go and start building your app. But later on, when things got more complex, this, uh, created much more problems, 'cause planning is really important [chuckles] when you're implementing something, uh, technical. And let's say you're implementing payments or something that's gonna be, uh, a change to your database, if the coding agent is just like: "All right, I got it," and just starts writing code, this always results in terrible things, uh, some really gnarly bugs that I had. And to mitigate this, what I did was I created sort of a CTO. Um, so again, I'm not technical. I have been in product for a while, but I know zero th- uh, zero stuff about code. So basically what I did was I created a CTO with the custom prompt of it, uh, being the complete technical owner of the project. So I told it: "I own the problem, I own how we want the users to feel. You're the complete owner, um, of how this is gonna be built. I want you to challenge me. I don't want you to be a people pleaser," all these things that kind of mitigate the regular ChatGPT-isms. Uh, I, I always think about this, where, uh, for some reason, the easiest way for me to think about AI is to imagine it as people, and I think ChatGPT would probably be the worst CTO because it's such a people pleaser, and it's so sycophantic, where... I mean, just a short story, I had, uh, a few weeks ago, I was trying to learn about Bun JavaScript, which is, uh, was acquired by Anthropic, and I was trying to understand what they do. So I was talking to GPT, and this wasn't within my, uh, co-founder, uh, CTO project, and I asked it if it's similar to a different framework that I have in my app called Zustand, which nothing to do at all with what Bun JavaScript does. And basically, GPT goes, "Oh yeah, it's exactly the same." And then it started [chuckles] talking about what it, what it meant, and I was like: "Wait, no, these are not the same at all." And it said, like, the most terrifying and hilarious thing. It goes, "Oh, I'm sorry, I thought you were just making this up, and I was riffing with you."

    8. LR

      [chuckles]

    9. ZA

      And I was like: "Oh, no, no, no. This is terrible."

    10. LR

      Great.

    11. ZA

      So basically, if regular ChatGPT was a CTO, that would be the CTO who, like, goes along with your dumbest ideas. So creating the, the project allowed me to mitigate that.

    12. LR

      So this is, um... Just to, just to be super clear, you have a ChatGPT project that you've given a prompt to be your CTO of your, of your product, and, and being a non-technical person, this is kind of like the thing you talk to when you don't- when, uh... And we'll get to what you're actually using to build, when you have questions about architecture and decisions that are technical.

    13. ZA

      Yeah, so now I'll show, I'll show my full workflow, and I don't involve GPT anymore, but I definitely would recommend, even though the technology has gone-... So when I started this, there was no plan mode or ask mode. It was just build on these products, on, on Lovable and Bolt, and they've progressed a ton. A lot of what I had as workflows have become ingrained in these products, which is really interesting. I would still recommend start with a project, for, first of all, the reason that I said, and also it kind of puts you in a place where you're in a chatbot and not writing code. So you take the time to converse and to learn, which I think is critical. And the second thing is, if you're non-technical like me, code is terrifying. It's the scariest thing in the world to look at, and I look at it as kind of like exposure therapy. I think if you see this where I'm working, like, in, uh, Claude or in Cursor, you might be excited to start using those. But I would really recommend starting slow, uh, with a GPT project. Um, beautiful UI, super simple, then maybe graduate to like a Bolt or a Lovable, and then go to Cursor in light mode. [chuckles] Slowly, slowly, gradually ease in until you, like, open a terminal, uh, you know, go full dark mode, go full dev. Um, so I would really recommend doing this gradually.

    14. LR

      That is awesome advice. And so just to be, uh, to be clear, these days, you're using Cursor with Claude Code powering it, and what I love about that is that you're not- you've never written code. [chuckles] You- the way you put it, you're afraid of even looking at code. You have-

    15. ZA

      Yeah, one hundred percent.

    16. LR

      You have to do exposure therapy. And I love that Cursor is, is useful to you. And what you're telling us is that graduating from a ChatGPT project that is kind of your technical co-founder, kind of taught you enough to feel more comfortable going straight to Cursor. You, you said that you actually went to Boulder and Lovable, kind of an interim, uh, and then you went to just straight to Cursor. What's the reason to just go straight to Cursor? Just Cur- is it just 'cause Cursor can do everything, and once you get the hang of it, it's actually the most powerful tool?

    17. ZA

      Yeah. I think I graduated from each tool when I kind of outgrew it. So Bolt was awesome until I was trying to connect payments to my app, uh, and it kind of started losing it, and then I graduated to Cursor. And I've actually fallen in love with Claude. Uh, so I'm using Claude Code, but that also runs within Cursor, and I think this is Tal, uh, who told me this, I'm not sure who he's quoting: Uh, "But code is just words at the end of the day." Um, so it's just files on your computer. So basically, you can be working on the same project and carry it from app to app, and especially now, I can work on m- with multiple models and apps on my project. So s- start slow, but, uh, definitely there's, there's a lot

  4. 14:41 – 17:18

    Screenshare: Exploring Zevi’s workflow in detail

    1. ZA

      of places you can graduate to.

    2. LR

      Awesome. Okay, shall we dive into, uh, screenshare, showing how you operate?

    3. ZA

      Awesome. I've pulled up Cursor. Can you see it?

    4. LR

      Mm-hmm.

    5. ZA

      Perfect. So within my code base, what you can see here on the left, these are all my code files. Uh, here on the right is Cursor. Uh, so this is basically like having AI, which has access to all the code, and here in the middle, I have Claude Code running. And what you can see here... I'm gonna close Cursor for a second. What you can see here are all my slash commands. Basically, what slash commands are, they are reusable prompts that I save within the code base that I can run by writing slash and then the name of the file. So here you can see Create Issue, which is the first command that I'm gonna use. And basically, what this tells Claude, it says, "The user is mid-development and thought of a bug or a feature and improvement. Capture it fast so they can keep working." And then it basically says: "This is the format that I want you to capture the, the, uh, Linear issue in," and it explains a bunch of things, what exactly Claude needs to do to get there. So the way I invoke this is basically I'll do slash create issue, and this injects this prompt into Claude. So it says, uh, "I'm ready to help you to capture this issue. What's on your mind?" So basically, when I'll do this is if I'm working on a big project and I suddenly come across a bug or have an idea that I don't wanna work on right now, but I wanna work on later, I'll do this really quick, and Claude's main goal is to quickly capture what I'm thinking about. So quickly, to run through my full workflow. So basically, it starts with creating an issue. So this is, uh, the create issue slash command, which basically tells Claude that I'm mid-development, and it should quickly capture what I'm thinking about and create an issue within Linear. Then later on, uh, when I wanna pick this up, I have the exploration phase. Exploration phase is basically telling Claude: We're gonna only explore what we wanna solve here. It could either pull from Linear, or I can just speak freely to it, and what it will do is it will analyze and understand the issue and just ask clarifying questions. The next phase, after we've done- finished exploration phase, is we're gonna create a plan. So you can see Create Plan. This basically has a template that I love for creating a plans, and the output of this, at the end of the day, will be a markdown file with our plan that we can end up building along with code. After creating the plan, we have Execute Plan. After execution, we have review, and then we have peer review, which is really cool, and we'll get into later on. Um, and at the end, we update the docs. So this is updating documentation and everything so that agents can write better code later

  5. 17:18 – 30:52

    Building a feature live: StudyMate app

    1. ZA

      on. So I think what we'll do is we're gonna build a feature live for my app, which I think is really cool. But first, what I'd like to do is, is show you the app so you have some context. So this is StudyMate. It's a platform for students, which allows them to upload, um, study materials and create, uh, interactive tests based on their own materials. So here we can go to the top. Uh, let's upload a PDF. We can decide what pages we wanna be quizzed on. We can decide the number of questions, the difficulty level, and basically, what happens behind the scenes is we send the information the user uploaded, along with the system prompt and any other, um, augmentations the users decided, to, uh, Gemini, and we create a quiz. These are, uh, challenging questions that are meant to assess comprehension. You even have some hints, and once we do a few of these, we can submit.... I got them right. [chuckles]

    2. LR

      [chuckles] Terrible results.

    3. ZA

      Yeah. Yeah, lucky.

    4. LR

      And so, and so just to be really clear about this, this is like a side business that you have, a, an app that you built-

    5. ZA

      100%, yeah

    6. LR

      ... that's making money, that's just, like, a thing you vibe coded, [chuckles] having no technical experience.

    7. ZA

      Yeah, this is my weekend project. Yeah, this is what I do-

    8. LR

      Awesome

    9. ZA

      ... uh, on weekends.

    10. LR

      Amazing.

    11. ZA

      Um, yeah, so you get basically deep explanations into why each, uh, question was wrong or each question was right. And at the moment, StudyMate only has multiple-choice questions. And I was doing some competitor research over- over the last weekend, and I saw competitors who had true or false questions, and also fill-in-the-blank questions, which I loved. So I think that'd be really cool if we could, uh, build that live. Uh, how's that sound?

    12. LR

      I love it. I'm crossing, crossing my fingers this will work. [chuckles] Uh, I just want- I, I just want to highlight the stuff you shared right before this in Cursor. So this is a huge deal, what you described here. This is essentially what you've figured out, is a way, as a non- a person that has no idea how to write any code, how to build a product in Cursor as a product manager, using this series of slash commands that you've concocted, that you're gonna be sharing with listeners. They can download all these and just use them directly. They don't have to figure out all these prompts that you've, you've figured out.

    13. ZA

      Yeah, 100%. Basically, what happened was I formulated the backbone of this, uh, with the CTO, and it was basically within the system prompt of the CTO project that I had within GPT. Uh, so it said, "Step one, we do this. Step two, we do this." And now I'll keep building, and if I see something that happens over and over again, I'll just create a slash command, and then it will be automated within the workflow.

    14. LR

      Amazing. So just to summarize the slash commands: so one is create an issue in Linear, which, uh, I love. Linear is awesome. Uh, shout out Linear.

    15. ZA

      That's also from, uh, yeah, the product packs. [chuckles]

    16. LR

      From the product packs. [chuckles] Oh, my God, what value!

    17. ZA

      [chuckles]

    18. LR

      Uh, okay, so step one is create the issue in Linear. So it's a command- so this prompt slash slash command you've created, just create issue. Then it's explore, which is, uh, explore the idea, help me ideate on what this could be, and this is Claude helping you think through the feature and product.

    19. ZA

      Yeah.

    20. LR

      Then it's actually create the plan, and so it's like the AI helping you build the plan to build the product.

    21. ZA

      Mm-hmm.

    22. LR

      Then it's actually execute, which is just build the thing.

    23. ZA

      Yeah.

    24. LR

      And then there's this review, peer review step, which is awesome, that, uh, you'll share.

    25. ZA

      Yeah.

    26. LR

      And then there's document, update documentation based on this-

    27. ZA

      Exactly

    28. LR

      ... new feature that we're adding. Sweet.

    29. ZA

      Yeah. Cool. So let's, uh, go ahead and start building. So I'm gonna use Wispr Flow, uh, to dictate, and basically, this starts with slash create issue. Um, so this basically sends that prompt, and I love this because I usually do this, uh, during when I'm building something else. So basically, it tells Claude that I'm mid-building something, and I don't have a lot of time to, to, to waste time on this, so just ask some brief questions so that you have enough to capture within Linear. So I wanna add fill-in-the-blank questions to StudyMate. Uh, I want this to be 30% of tests to be generated as fill-in-the-blank questions. I want there to be six potential answers, uh, for two blank spots, and of course, there's only gonna be two correct answers, so one correct answer and two incorrect answers for each spot, and I want the interface to be drag and drop. So that's just basically, uh, a quick think of, of, of how I want this to work. So it's gonna ask me a few questions. Quizzes are 100% multiple choice. Question structure, single-sentence passage with two blanks, um, and priority, so one and two are correct. And this is, uh, not high priority, uh, it's a nice-to-have feature. So now, basically, what Claude is gonna do, is it's gonna use MCP, which is basically, uh, uh, technology that was created by Anthropic, which gives AI the ability to use tools. So this is connected to my Linear. So what it's gonna do now, is it's gonna use everything we've said and create an issue within Linear.

    30. LR

      And by the way, as, as this is loading, I just love the way, the way you describe this, especially doing voice mode, it's like exactly how you would talk to an engineer: describing a feature, "Here's what I want," and then they ask you questions, "Here's the clarification."

  6. 30:52 – 38:32

    Executing the plan with Cursor

    1. ZA

      see what's already been done there. Um, so what we're gonna do now is we're gonna execute the plan. So now I think we're gonna do this with Cursor just 'cause, uh, Composer is so freaking fast. So what we can do is basically just say, "Execute," and then we can tag the file. And Composer is ridiculously fast, so that's it. It's off. It, uh, basically understands what the plan is, and it's gonna go ahead and start writing the code.

    2. LR

      Let me ask you a question while this is happening.

    3. ZA

      Awesome.

    4. LR

      And I have many questions, so this is a good time to ask a few of them. You said that Lovable and Bolt are- and other, you know, other apps in that space are, are just not enough to build really serious apps, and you had to move to Cursor to do that. What- tell us more about that. Just, like, how far... What, what kind of limitation you ran into with those products and why you switched to Cursor?

    5. ZA

      I started using Cursor and Claude Code a few months ago, and I haven't looked back. But at that time, these teams had been moving like crazy, so I don't wanna say I wouldn't trust them. I don't know what the current state is, but for me, it was basically the issue of I felt that Cla- that Bolt was being very opinionated on how I should do things, and I felt like my knowledge has gotten to a point where I can graduate and be more in control. By the way, I think that the main difference between all these tools is basically the harness. So the models are all the same models. You know, I- I'll run Claude within Cursor, I'll run it within Claude Code, and it's also the models that... Claude is also the model that is underlying Bolt and Lovable. But basically, Bolt and Lovable will add a bunch of levels in the middle that will take all kind of guesswork and, and, and hard decisions out for the user. So the user doesn't make- have to make these hard decisions, so it's also very easy to build. But the flip side of that is that you have less control, and basically, Claude Code is just taking Claude and shoving it straight in your code system and giving it full tools and to do whatever it wants. But also with that comes a lot of decisions that you need to make. So I don't know if, if you can't build really amazing production apps using, using Bolt or Lovable now, but I think basically, if you want the most cutting-edge abilities of the models, and you wanna be able to make all the decisions y- uh, on your own, it's probably best to be on one of these tools.

    6. LR

      What I'm feeling and hearing is that planning work that you did, that's the stuff that Lovable, Bolt, and would you put Replit in that bucket, too?

    7. ZA

      Yeah, for sure.

    8. LR

      Okay.

    9. ZA

      Lovable, Bolt, Replit, Base44.

    10. LR

      v0.

    11. ZA

      Um, yeah, v0-

    12. LR

      Yes

    13. ZA

      ... all same bucket.

    14. LR

      So essentially, they're kind of- they're doing that planning for you, and as you said, they're very opinionated. They, they try to make it easy, so it's just like, "Here's how to do it. We're not gonna..." Like, "Here's the way we wanna... we think is best for people." And what you're saying is once you're trying to get a little more serious about it or have- wanna go in a different direction, you don't have the power to change the, how they plan, so Cursor lets you do that.

    15. ZA

      Yeah. I don't want this to come out like I'm bad-mouthing them.

    16. LR

      No, absolutely.

    17. ZA

      Base44, let's say... Yeah.

    18. LR

      Yeah.

    19. ZA

      Base44 does an amazing job at basically taking all the complex guesswork out of building product and just allows you to just, you know, go with the vibes and build. But it will do sign-in with Google for you, and it will do a database, but then you don't have decisions on, uh, what database am I using? Do I need sign-in with Google this way or the, or another way? It would just do it out of the box. So, so that's basically the trade-off there.

    20. LR

      Awesome. Shout out, M- uh, Maor, the, uh, founder of Base44-

    21. ZA

      Yeah, Maor Shlomo

    22. LR

      ... on the podcast. Yep. Love that guy.

    23. ZA

      Yeah, yeah. He's amazing.

    24. LR

      Okay. Uh, I just love how this is, like, the way you're, like, s- uh, flinging, what's the word? Slinging, slinging models, like Gemini 3 for front end. Like, I love that you have... You've never written any code, and you're just like, "Cool, we use Gemini for this and Claude for this, and I'm just working on Cursor, talking to this, uh, [chuckles] CTO, helping you build stuff, and build, like, significant product."

    25. ZA

      Yeah, I mean, we just live in the craziest of times, where basically there- the world changes once a week, uh, it feels like, and there is just no boundaries. You can, you can use all of these just on your, like, regular MacBook or, or regular laptop, and I have these moments, um, I call them time machine moments, which is basically... This week, for instance, I was prepping for the podcast using Claude with a project. I was building- I was fully localizing, uh, StudyMate from Hebrew to English, which I did in two days, which would probably take a dev team weeks. And I was building a personal site, which ca- went from no domain, no nothing, to live, uh, on a domain within an hour and a half, and I was doing all three of these in parallel. And there was a point where basically all three of the agents were running, so I didn't have anything to do. I just had to let them think. And these are, like, the time machine moments where I feel like I was in the future, and I just stick my head out of the time machine, and whoever's next to me, like, at the moment it was my wife, I'll just say, "We, we live in the future." And she'll be like: "Huh, what?" [chuckles] And I'll be like: "No, no, don't worry about it." But it's just basically so crazy that all these things are just, you know, an API away. You can, you can use anything, so I think it's an awesome time to be curious and, uh, optimistic and hardworking.

    26. LR

      These are my favorite kinds of podcast guests, people that are living in the future, figuring out all these things, and then are just kind of come back, p- as you said, poke your head out of the, [chuckles] the rocket ship and just like: "Hey, here's this thing that I figured out. Here's where we're going."

    27. ZA

      Yeah. Best time to be alive.

    28. LR

      [chuckles] Agree.

    29. ZA

      Um, so awesome. So it looks like it's finished. Um, so now what we're gonna do is we're gonna run the app locally, and we'll be able to see, uh, what, uh, Composer ended up building, and we're gonna see if anything else is needed, um, on our end to maybe do some, uh, manual review. Does that sound good?

    30. LR

      ... Sounds great, and I love- that was, like, I don't know, a few minutes? Where if it was a human engineer, it'd be, like, days, maybe a week-

  7. 38:32 – 40:40

    Using multiple AI models for code review

    1. LR

      may apply.

    2. ZA

      So now we have, uh, this feature, which basically we built. Um, and I can ask it to make some changes, because it's running locally. Um, and once it's ready, I'll be able to ship it to users. So now, the next phase, after I've, uh, QA'd it and basically tested it manually, I'll have Claude review its own work. Um, so what I'll do is I'll, uh, reopen Claude Code.

    3. LR

      I love this, 'cause this is one of the things that comes up a lot on this podcast, is writing code is now so easy, the main challenge people have is reviewing the code that AI has written.

    4. ZA

      100%.

    5. LR

      And what you're doing here is you're having Claude review its own code.

    6. ZA

      Yeah, so this is another thing where it's very difficult for me to catch mistakes, so my review process has gone through a bunch of iterations to really be, uh, as good as possible and to catch as many things as possible. So I'll always manual q- manually QA it first, uh, to make sure if I can see any mistakes that Claude made, and then what I'll do is basically slash review, and this, uh, tells Claude to start reviewing its own code. But what's even cooler, and something that I'm really proud of, is I will usually do multiple reviews, and I'll have Codex, which is ChatGPT's competitor to Claude Code, as well as Cursor open, and I will have each of them review the code. And then what, what I do is I have a slash command called peer review, which is really interesting, and basically what it does is it's gonna take Claude, which is usually the agent who I'm work- working with, and just to put this in a mental model, this is basically my, uh, my dev lead that I'm working with. I will take, uh... The, the slash command is basically saying, "You're the dev lead on this project. Other team leads within the company have looked at your code and reviewed it and found these issues. Don't take what they're- what they said at face value. The reason is, you have more context than them, and you led this project. You need to either, um, explain why the stuff they found are not real issues and wrong, or fix them yourself."

  8. 40:40 – 43:37

    Personifying AI models

    1. ZA

      And it's really cool, because the way I look at these things is I look at the models, I try to imagine them as people, and I can, I can really tell you how each one of these, uh, would be as, as a real human. Um, because they have-

    2. LR

      Each model.

    3. ZA

      Yeah, each model has such distinct, uh, characteristics. So let's say Claude, she would be the perfect CTO. Like, she's very communicative, she's very smart, um, she, she doesn't just go with the flow and do whatever you tell her. She's very, um, opinionated, but also super collaborative, which is, I think, why I'm always drawn to Claude. Um, because I, I need to do so much learning, and, and, like, it's, it's your dream of very communicative, but very, um, opinionated, uh, dev lead. But then there's also Codex. So I use Codex, um, 5.1 max, whatever, I don't know, they're not the best at naming [chuckles] uh, models, but GPT's model, I always imagine it as, like, a... The best coder within the company, who comes to the office, like, with, a, a hoodie and sandals, and sits in a dark room, and you basically only bother him when you have the worst bugs. And you say, "Listen, we have this bug," and he will just close the door for two hours and come out and say, "I fixed it." And you're like, "Wait, what? Uh, d- are you gonna tell us what happened or whatever?" And he's like, "Don't worry about it, I fixed it."

    4. LR

      [chuckles]

    5. ZA

      It's, like, r- r- really not communicative, but it solves all the worst problems. And let's say Gemini is, like, a crazy scientist who's super artsy, uh, super talented at designing, but if you sit next to it and watch it work, it's terrifying. Like, you would fire that person instantly. This might be just my experience, but when I'm using Gemini within Antigravity, which is, uh, Google's new competitor to Cursor, when it's writing code, you can see the steps it's taking, and it's terrifying. Like, you'll say, "Uh, I want you to redesign the top of the dashboard," and, and you're looking at its thought process, and it will say, "Oh, first things first, I'll delete the dashboard," and then it'll be like, "Nope, that was a mistake." [chuckles] "I'll bring it back." And then it will say, "Oh, can I edit the database?" And, uh, you're like-... no, do not edit the database. You're just doing a redesign, and then it will end up designing something beautiful. Um, so the, like, the way there is like a rollercoaster and very scary, but at the end of the day, Gemini is very good at design. So I think that using all these models, um, and basically playing to their strengths and mitigating their weaknesses by using other models, is, is a game changer for me. So I'll do peer review a bunch of times, and, and I'll have other models review other models' code and kind of have them, like, fight it out, uh, basically. Like, sometimes, uh, Claude Code will get really sassy and be like, "This has been raised for the third time, and for the third time, I'm telling you, this is not an issue. This is by design." So it's just a really cool, cool, uh, thing that I've added, and I haven't seen many people doing it.

    6. LR

      That is [chuckles] such an incredible rant slash- [laughing] ... way to understand what's

  9. 43:37 – 45:40

    Peer review process

    1. LR

      going on. Okay, awesome. So we just ran the review. So show us what we saw there, and let's actually try this peer review. I'm really excited to see what, what you learned there.

    2. ZA

      Yeah. So basically, Claude has reviewed its code, and it's found a bunch of bugs: a critical bug it found in the prompt, uh, some high bugs, some medium bugs. And now what I'll do is I'll do the same thing with the other models. So Codex has a built-in code review that you can do, or I just like to say, "Review, uh, all the code in this branch." Of course, branch is referring to the GitHub branch that we're working on. Uh, we're not working on the live code base. And then I'll do this with Composer, say, with... We can do- let's do it with, with Composer 1. So I'll do, uh, /review here as well. And basically, these are both gonna run and do a in-depth review, similar to what Claude does. But again, because of the differences between the models, uh, they're all gonna catch different things, and they're all gonna look differently. And this is a really cool way to work. It's basically if you had other team leads within the company, uh, review the code. Here, you can see how fast Composer is. I think GPT probably will take a bunch of time. Like I said, it's in its own dark room right now, reviewing code, and will come back [chuckles] in a few minutes. Uh-

    3. LR

      Okay, cool.

    4. ZA

      Yeah.

    5. LR

      So we can, we can let these run, and we don't actually have to go through the whole process, but is the idea once you get these results, you run peer review, and you, you copy and paste kind of these results? Is that the idea?

    6. ZA

      Exactly. I'll copy and paste-

    7. LR

      Okay, cool

    8. ZA

      ... the results, I'll do peer review, and then I'll say, "Dev lead 1," and then paste from one of the models, and then I'll say, "Dev lead 2," and paste from the other model, and basically have them, uh, fight it out until I feel like we have no more issues. Um-

    9. LR

      Incredible

    10. ZA

      ... for me, this is super important because I'm not a, I'm not technical-

    11. LR

      Yeah

    12. ZA

      ... and I'm not a developer. And I'll also use slash learning opportunity a bunch during this to learn about stuff that I don't understand or, or don't fully grasp.

    13. LR

      Incredible. What a, what a clever solution to [chuckles] solving this code review problem where it's like, I don't know what you... I don't, I don't know how to recode, so what am I gonna even... Yeah.

    14. ZA

      Yeah.

  10. 45:40 – 51:05

    The importance of postmortems

    1. LR

      Okay, incredible. Let's, uh, let's wrap up this, kind of this workflow. Is there anything else that's important in this workflow? And again, all this stuff is gonna be available. People can just plug this stuff into their Cursor account and, and use it themselves.

    2. ZA

      A hundred percent. Um, the one thing I'll say is that I think just like working in general with AI, and even just like, uh, working on any product, doing constant postmortems is critical. So a lot of times, we'll find all these kind of bugs, or maybe Claude will fail to execute something correctly. And at the beginning when I started vibe coding, I would basically just keep running at it, like running at the wall, and until it worked, and once it worked, I was like: "All right. Awesome. This works. Let's keep going." But I've learned over time that updating documentation and tooling is one of the biggest hacks for productivity. So when Claude will fail to do something, or I'll see this really bad bug that, that shows that Claude really didn't understand something, I'll ask it: "What in your system prompt or tooling made you make this mistake?" And Claude will kind of like go introspective and think of what made it do- create that mistake, and then I'll say: "Okay, great. Let's update your tooling and documentation so that this mistake never occurs again." And I do this every time I'm either building, uh, an internal tool or anything, and I think this is just like working, you know. Uh, if you've... You end up doing a bunch of mistakes and then end up releasing the feature to users, so you're like: "All right, it's a big success." But going back, and even when you've succeeded, um, looking and understanding what you did and what you could have done better is critical. And also, using AI, this is probably one of the biggest unlocks. Going back to your prompts, understanding what was not good enough, iterating on them, and then seeing how AI's responses get better, I think that's probably one of the most important things and one of the things that divides between people who are, like, okay with using AI and the people who actually know how to use it.

    3. LR

      That is such good advice. So what I'm hearing is, when you run in- when the models do something dumb, make a mistake, you ask it to reflect on what the mistake it made was, and then you update the slash command prompts, uh, with that knowledge, so that in the future, it's not making that same mistake.

    4. ZA

      Exactly.

    5. LR

      And it just keeps getting better. These things just keep getting smarter and smarter, so you're building up this really incredible prompt that just gets better and better.

    6. ZA

      Exactly. Um, not always the slash commands. It will sometimes update, uh, different documentation or its tooling-

    7. LR

      I see

    8. ZA

      ... but basically, it's, it's understanding what the root cause of the, of the, uh, mistake that the AI, AI made and fixing it.

    9. LR

      Awesome. So it's not... So, like, the models are getting smarter, and then there's also the other parts of your workflow can get smarter as you, as you find flaws in the way it does stuff.

    10. ZA

      A hundred percent. Yep.

    11. LR

      Amazing. Okay, um, is there anything else there before I move in a couple other directions?

    12. ZA

      I think that's it. I think we covered pretty much everything.

    13. LR

      Okay.

    14. ZA

      Basically, just to wrap this up-

    15. LR

      Yeah

    16. ZA

      ... what I do is I do a bunch of code review and then update the documentation so that everything is documented, so the next time I try to build a feature in this area, there won't be any mistakes. Um-... um, and then I'll do a bunch of testing. I'll do some user testing as well before I release this to general availability. Obviously, we're not gonna release this. This was just a show. Uh, but hopefully, maybe by the time the podcast comes out, I'll, I'll have done this correctly and, and released the feature.

    17. LR

      It's incredible that this was not possible, like, I don't know, two years ago, maybe a year ago? Like, you are a product manager shipping [chuckles] a product without knowing how to write code, barely knowing how to review code. You said you're afraid of looking at code. As a product manager, you're building a product in Cursor using, uh, all of these different AI models. You're making money with this product. Uh, this is like- we're so used to this now, but it's insane what is now possible.

    18. ZA

      It's the best time to be alive, 100%. Um, I think that... I, I understand the fear, but AI just makes so much possible. Just a quick, uh, side note here. My brother, who I'm building one of the apps with, is an entrepreneur. He has a beautiful business that helps old people, um, and seniors understand to use technology and, uh, AI better, and he's basically doing the same kind of learning as me, and he's replaced all of the tools he was paying for. I think he was paying for Zapier and Airtable, and he's basically built, uh, like, a full-fledged CRM system and automation system for his business completely alone. So, I mean, for the people who are curious, um, optimistic, hardworking, this is the best time to be, to be a builder.

    19. LR

      And what I love about this conversation we're having here is it feels like the biggest barrier for a lot of people is, like, "How do I get started? What exactly do I do? I open up Cursor, it looks very intimidating. I don't know how to write code. I don't know how to build stuff. I don't know about databases." And so you're gonna be sharing all these slash commands and basically this whole workflow with the audience.

    20. ZA

      Yeah.

    21. LR

      Okay.

    22. ZA

      And like I said, just start at GPT. Start in GPT. Um, tell it what your idea is. Uh, tell it to explain to you what are even the first steps of thinking, what are the decisions you need to make, and just be, like, be inquisitive. Learn. Um, don't rush things. Uh, it's very important to just dive in and, and really spend the time to learn.

    23. LR

      And you shared this... One of your slash commands is learning opportunity, and it's how you learn a lot of these things. Just, like, "Teach me this thing and how this database issue works."

    24. ZA

      Exactly.

  11. 51:05 – 53:42

    Integrating AI in large companies

    1. LR

      Okay. Okay, there's a couple directions I wanna make sure we touch on. One is coming back to a question I asked earlier about how this might work at a larger company. Say, it's not like Meta, but just like, I don't know, a thousand-person company, 500 people. How much of this can you plug and play into a workflow as a PM at a larger company? What would be your advice for someone that may wanna start trying to ship code, at least s- showing people what's possible?

    2. ZA

      I think that first making your codebase AI native is a really important step, and I think this needs to be done by technical people. So basically, my codebase has a ton of just plain text in it, so it will have a bunch of markdown files that explain to agents how to work in certain areas of the codebase, um, and high-level structure so that the agents, uh, navigate through the codebase easier. And I think that if this is set up in a really good way, I still don't think, uh, like, PMs should be shipping heavy, uh, database chain migrations or any, like, big project, but, you know, contained UI, uh, projects, especially if you just build it, create the PR, and, and send it to a dev to, like, do the final finishes, uh, I think that's definitely something that's possible, and I think we're gonna see that a lot in the next coming years. I think basically everyone's gonna become a builder, so should be really interesting.

    3. LR

      Okay, so your advice here is, as a PM, don't... maybe don't go right to Cursor, start building, shipping, trying to ship features to production, especially complicated features. Do you think we'll get there? Do you think, like, in a couple of years, PMs will be doing this, and it'll feel less scary and crazy?

    4. ZA

      If there are PMs. Um-

    5. LR

      Hmm.

    6. ZA

      Yeah, I think titles are gonna collapse, and responsibilities are gonna collapse, and everyone's just gonna be building. Um, I definitely think that the models- the context window's getting bigger. The models are getting smarter. Um, and I definitely see how PMs or any other background can be writing. At the moment, I wouldn't wait for that. I would use this as a collaborative learning opportunity to work with your dev team. It's gonna be difficult. A lot of developers are very, very skeptic about the current state, and I think that it's gonna be a lot of sales work on your end to convince. But if you're able to convince, and I think teams that are really sold on this and wanna take the time to work on their workflow about how can our A- team become more AI native, I think that these teams are gonna probably be a few years in the future, and they're gonna look back at the few weeks they spent setting this up as,

  12. 53:42 – 57:02

    How AI has impacted the PM role

    1. ZA

      as the best time they spent.

    2. LR

      Let me ask you another question around just the job of a PM. One of the biggest fears people have with these AI tools for, for PMs, for every function, I imagine, is just they- you start to rely on these things, your skills start to atrophy, you're producing all this slop that looks great. Cool, amazing strategy document. No, it's actually not at all good. Or these linear tickets or just products that are, like, half-baked. What's your take on kind of these two parts of just, like, how has this impacted your, uh, craft as a PM? Do you feel like this is weakening your skills 'cause you're so reliant on these tools? And just how do you keep the quality of the stuff up and not just like, "Meh, it's just a bunch of AI-generated slop?"

    3. ZA

      I, I have a, a very strong disagree to, to, to this, and I've heard it a bunch. I remember when I started using... Tal Raviv, um, has, like, this whole course on, on building a PM copilot using projects, uh, which is probably one of the best courses, uh, that you can take, and when I started working with my own copilot, I remember people at work looking and saying, like: "Oh, so you're basically outsourcing your thinking?"... and to me, that's just the worst way to look at it. And I think for some reason, these people usually have a high correlation with the kind of person who doesn't like to show their presentation when it's only 10% done, or doesn't want to ask for help a lot. I think that there's a misconception with a lot of PMs that the job is always having the right answers and being the smartest person in the room. And at least how I was trained and how I believe the, the role of the PM is, it's the exact opposite. It's basically harnessing anything that can get us, uh, as quick as possible to delivering the, the right solution to users. And I just think this is like that really smart person that has context or, or your mentor or whatever, but is just always available and doesn't judge you, and, uh, can really help you. So if you're using it to just create your outputs and then putting them out there, um, I mean, yeah, that's AI slop, but it's also human error. I think it's really important that you own your own outputs. If you put anything out there or, um, show something in a product review, and you say, "Oh, sorry, that was built by AI," that's- that's your mistake. I think if you use these intentionally and, and really take the time to understand how to use AI in the correct way, it's one of the biggest game changers that will make you much better as a PM. And another thing here is that, especially for more junior PMs, it allows you to play at such a higher level than you would normally. Like, I think that at Wix, I wasn't thinking of what's the marketing strategy, uh, of the company, and how will the onboarding be completely revamped within the all- the whole product? But, I mean, on my side product, I can just do whatever decisions I want and think of the strategy and marketing and the messaging, and this is basically just getting me, uh, reps, uh, which is one of the most important things at the beginning of your career. So I understand the fear that, you know, how do you... You outsource certain stuff, and you're not owning 100% of everything, but I think the upside is so much more valuable, and I think the only way that AI makes you worse at your job is

  13. 57:02 – 58:15

    How to improve AI outputs

    1. ZA

      if you're using it wrong.

    2. LR

      Is there anything that you've learned about reducing the, the sloppiness, the slop-iness of the output, just like [clears throat] a tip for keeping the quality high of the stuff that it produces?

    3. ZA

      Similar to people, setting up AI for success for the task at hand. So, like, if I just brought in, you know, uh, a junior to, to write a deck or something, and I didn't give it any guideline, I just said, "Give a strategy deck," he would probably just go online and find, you know, top strategy deck and, and just reproduce that, which is basically what AI is doing. It's basically just fed all of the internet. So instead of that, guiding it and giving it context on what your style of writing is and what you're trying to solve, um, and all these different things, I think that's probably one of the biggest unlocks. Um, so that's just a quick tip. And also, uh, Cursor has a slash command called Deslop, which is basically going back over the code. Um, I don't know if this is integrated into the product yet, but it's, uh, on Twitter. Their founders have been talking about this, so that's definitely something I would run after just to make sure that no, no slop is, is left behind.

    4. LR

      That is so funny. [chuckles] Deslop.

  14. 58:15 – 1:02:57

    AI-assisted job interviews

    1. LR

      Okay, one more question, uh, which may lead to something else, but, um, kind of going in a whole different direction. You used AI to help you actually interview for the job that you got at Meta. Talk about how you did that, because a lot of people right now are struggling to find a job, uh, reading about all these people using AI to help them interview. You actually did it. Uh, what did you use? What worked?

    2. ZA

      I feel like the analogy here is... I have 12 nieces and nephews, and you can see how people who have grown up in a different world, how their mind is, is formed differently. So if you ask me, "How do you answer a phone?" I'll do this. But a, uh, a child now, when you say, "How do you answer the phone?" They'll- they'll do this. You know, they'll do the, the, the iPhone answer. And I feel like people who are, um, growing up now in their professional lives, we're the same, just with AI. So every time I'm faced with a new challenge or problem, I think AI first how to solve it. So, uh, Meta reached out and said they'd like me to interview. Straight away, I opened up a project, um, within Claude. I started looking online for all the best information out there, things that I resonated with. I took a ton of frameworks and, and stuff from Ben Erez, who's written a guest post, uh, for you, who I think is one of the best minds out there right now, and basically, I created a project, which was my coach, uh, which I would come and consult what to do at each phase, I would mock interview with, and this was amazing. Also, I created a game, uh, in Base44, which helped me... Uh, I was really struggling with segmentation, uh, within the product questions, so thinking of the correct segments. So I basically just created a quiz game, which creates questions and different segmentations, and I have to choose. Uh, so this was like I spun this up. It's a web app that I would play sometimes when I was on the bus to work. So basically, uh, I think Ben talks about this a bunch, so I don't, like, just go read Ben's stuff, but just creating a project and feeding it with all the best information on the internet, and then mocking a bunch. I will say that the biggest game changer for me was doing, uh, human mocks. So cold outreaching to people, uh, on LinkedIn and having them, uh, do actual mocks for me, I think that at the end of the day, especially for the, the Meta PM prep, which is super competitive and difficult, uh, I think there's no, there's no way to, to get around that.

    3. LR

      That is so cool they used that post. I wasn't aware. We're gonna link to it, and in that post, Ben shares all these prompts you can feed ChatGPT to help you prepare for interviews, do, uh, mocks online. Uh, it's a really important point to say that those are take you to a point, but it's actually better to use humans. I actually have a post coming out soon, uh, in collaboration with Noam Segal about-... how everyone's using AI to interview, and one of the most interesting ways I've heard people, and that we found in this research, was that people use it to get feedback. They record the interview, and then it gives them feedback: "Here's where you could have done better-

    4. ZA

      Mm.

    5. LR

      "Here's what you, here's what you missed." 'Cause the feedback loop is so missing. No one ever tells you, "Here's what you did badly in this interview." No one tells you that, and AI-

    6. ZA

      Yeah

    7. LR

      ... can do that.

    8. ZA

      So I'll add two things to that. One, which is-

    9. LR

      Yeah

    10. ZA

      ... uh, exactly this. So I'll mock with, um, AI. Also, I did something really cool where there's a question bank online, uh, free, uh, by Lewis Lin, which basically is an always updating, uh, bank of questions that people are asked in real interviews. And I basically, uh, used, uh, Comet, which is the Perplexity's browser, and I had the agent run all kinds of analyses on, like, what the most asked questions are, and that's how I knew how to prioritize what questions I would mock. Um, and then at the end of these mocks, I would, um, tell Claude within the project, um, "You're my coach, and I don't want you to make me feel good. I want you to make me, um, as ready as possible for these interviews. So give me feedback, like you said." Um, and the other thing that I did was really cool was some questions where I didn't have time to mock, I would ask Claude to play the candidate, and then it would just give me a really good answer, and I could also learn from that, like learning from someone who does a, a perfect answer.

    11. LR

      Oh, man. I, I really love the way you phrased it, that people kind of in your generation, the default is, "I have something I need to do. Well, let's go to AI immediately and, and help me prepare for this thing, help me figure it out."

    12. ZA

      Yeah.

    13. LR

      And this comes back to this quote that I always think about, which I think everyone's always hearing, but I just... It's such an important quote: that it's not that you will be replaced by AI, at least for a long time, it's you'll be replaced by someone who's better at using AI than you.

    14. ZA

      I agree.

    15. LR

      And that's what these conversations are for, to help people keep up with all that, and to, and to learn some of these skills, and again, see where the future's going and, and start to learn how to get there yourself.

  15. 1:02:57 – 1:06:20

    Failure corner

    1. LR

      Okay, Zevi, uh, before we get to our very exciting lightning round, I'm gonna take us to a recurring segment on this podcast I call Failure Corner. And why I love this segment is people come on this, you know, just even this conversation, it's like all these amazing things you figured out, everything's going so well. People rarely hear the things that don't go well, and those are often the most interesting and im- impactful stories. So the question is just: What's a, what's a story of a time you failed in your career, and what did you learn from that experience?

    2. ZA

      Yeah, I love this. I love this, uh... I love Failure Corner. Big, big fan.

    3. LR

      [chuckles]

    4. ZA

      Um, so I'll tell a story about, uh, when I started at Wix. So basically, I started within Wix's student program, and straight out of the student program, you get, um, put into a certain team. So I was in the editor, which is, uh, the core product of Wix, and the other PMs were just the best PMs almost at Wix. Like, the- these four other people, uh, had much more experience than me, and they were ridiculously good, and I remember coming in and thinking, like, "My first product review, I'm gonna blow these people's socks off. They're not gonna believe how good of a PM I am." And I basically didn't really share what I was thinking. Uh, I would work tons of hours alone, and I was like: I'm gonna kill this product review. They're gonna be so impressed. Uh, and I ended up failing miserably. Uh, my product review was not good. Uh, it wasn't the format they expected. They had a ton of questions that I missed, um, and I felt awful when it was... When it was over, I was like, "Argh, you're such an idiot!" And I saw that everyone was like: "All right, cool. Yeah, just come back in two weeks and, and we'll keep, we'll keep getting at this." And I, I understood in that moment that they had zero expectation of me being a 10X PM, but the expectation of me was being a 10X learner. And the second I understood that, my whole mindset switch, uh, shifted, and I think this is probably the best tip that I give now, uh, to junior PMs, is basically: be the best learner you can be at the beginning. No one expects you to know all the answers, and no one expects you to be good. So basically, what I did was I took each person on the PM team, there was four other PMs, and I, uh, assessed what their strength is and used them as a mentor for that. So Neri, who's still my, uh, mentor till today, he has the best product sense of anyone I've met. Oya is super, uh... She's like a methodology expert, expert. She just thinks in frameworks. Um, Yara, who is the head of product, basically can look at a product and then instantly understand, like, the third and fourth order effects of them, the system thinking. So every time I had an issue with one of these areas, I would come to one of them, um, and consult them. And this does two things: first of all, I learned a ton, and the second thing is that when- the next time, the next product review, my success felt to them like their success, 'cause it wasn't, "This kid who's trying to show us up how cool he is," it was, um, like, "Our mentee kind of making us all proud." Um, and, uh, it was such a great shift for me, and basically, at the end of the day, I, I really excelled through this.

    5. LR

      That is an awesome story, and it- this connect- this idea of learning is such a good thread throughout this whole conversation, that, uh, AI is, is good at getting stuff done, but it's also really good at helping you learn how to do the thing and to be this partner, this thought partner, the way you talked about the interview process you went through and this learning, learning opportunity slash command. Um, so awesome. Great story. Uh,

  16. 1:06:20 – 1:15:12

    Lightning round and final thoughts

    1. LR

      Zevi, okay, before we get to our very exciting lightning round, is there anything else that you wanted to share? Anything you want to leave listeners with?

    2. ZA

      Yeah, so kind of to tie back into the, uh, first thing I said, where if people walk away thinking, um, "Zevi's so cool," then, then, then I've failed here. I think that it's just the best time to be alive. I think it's the best time to be a junior. Uh, contra- contrary to what a lot of people are saying, how, you know, there's no more junior roles out there, and people get out of school, and you, you can't find a role. Yeah, that's true, but also, when else in history could you get out of school and just build a startup, you know, on your own with a couple of friends, uh, completely bootstrapped? And I see more and more people, uh, towards my end, towards the end of the time, at my time at Wix, I was interviewing-... and I saw more and more people building their own stuff with AI, and I think, uh, contrary to what a lot of people think, it's the best time to be a junior. It's the best time to be a learner, and I think if any listener is listening to this, and you're a curious person, you're a hardworking person, I, I wanna say kind, I'm not sure, but if you're a kind person and a good communicator, you have such an unfair advantage, and you can give more value to companies than most people who have 20 years of experience. So, uh, I really hope people get inspired by this and, uh, start killing it with their projects.

    3. LR

      Amazing. So many ways to be inspired from this conversation. Zevi, with that, we've reached our very exciting lightning round. [bell dings] I've got five questions for you. Are you ready?

    4. ZA

      [swoosh] Yep, let's do it.

    5. LR

      What are two or three books that you find yourself recommending most to other people?

    6. ZA

      So I'll, I'll take one from each kind of genre. Um, so in, like, fiction, I love The Fountainhead, uh, by Ayn Rand, one of my favorite books. Uh, really makes you think, really makes you feel. Um, business books, I'm a big fan of Shoe Dog, uh, the Nike story. One of my favorite books-

    7. LR

      I just finished reading that. So funny.

    8. ZA

      Oh, it's amazing.

    9. LR

      It was great. It was great.

    10. ZA

      Yeah.

    11. LR

      Yeah.

    12. ZA

      I love Shoe Dog. Um, and then more on, like, the psychology side, uh, Mindset by Carol Dweck, who, uh, coined the term growth mindset.

    13. LR

      Mm.

    14. ZA

      It's just such an amazing book. It kind of sounds like a h- self-help book, but then you un- you understand that it's completely psychological and, and is based on research. Um, and that book completely changed my life. Uh, really, I was always with a fixed mindset, and then after reading that, I kinda understood, uh, that it was something holding me back, and since then I've been really, really trying to cultivate a growth mindset. So I really recommend everyone reading that.

    15. LR

      Again, connects to that thread of, uh, the way you described it, being a 10X learner versus a 10X, uh, doer. Okay, next question: Favorite recent movie or TV show you have really enjoyed?

    16. ZA

      Yeah, actually, my, my wife is really into film, so we watch a lot of TV. Uh, it's probably our, our favorite, uh, together time. Uh, I just finished watching The Pit, which was amazing. Uh, it was really good, and the... my first recommendation to everyone is, if you haven't seen Severance, run to see Severance, one of my favorite shows.

    17. LR

      Is there a favorite product that you have recently discovered that you really love?

    18. ZA

      It's a good question. I'm always trying new products. Like, I'll always have, uh, three or four browsers on [chuckles] installed on my computer and all this different kind of stuff. Um, and I recently discovered a Loom alternative. Um, I was kinda disappointed with Loom. They were taking so much money, and the product, uh, I don't know, I just didn't love it, and there's an al- open source alternative called Cap, which is just really well-crafted. Um, you can see that the person was, like, uh, really sweating the details, and, uh, it's just a really, really great alternative, so I've been using that recently.

    19. LR

      There's also a product called Supercut that I love that's also, uh, a Loom alternative.

    20. ZA

      Mm.

    21. LR

      Shout out. Okay, two more questions. Do you have a favorite life motto that you find yourself, uh, coming back to in work or in life?

    22. ZA

      Yeah, I'm kinda between two right now. One, which has, like, become a, a Twitter meme, basically, which is, "You can just do things." I feel like that is basically going always in my head every time I do something that I'm just shocked at the speed and, and ability to do things now. Uh, so, "You can just do things," and the second one I stole from my brother. His motto is, "Nobody knows what the fuck they're doing," and I just love that, and I think it kinda makes you take life more lightly. Uh, so yeah, nobody knows what the fuck they're doing.

    23. LR

      I think people see these companies on the outside, and it feels like everything, they've got it all figured out, and if you're ever on the inside of a company that's doing really well, you're like, "How is this staying on the rails? How is this still a thing that is working? Doesn't make any sense."

    24. ZA

      Yeah.

    25. LR

      "It's all about to fall apart."

    26. ZA

      I've been there. [chuckles]

    27. LR

      Yeah. Okay, last question. Uh, you've been... You've had a long entrepreneurial, uh, thread throughout your career. There's a couple other, uh, real-world businesses you've started in the past. You did a thermal clothing business and then, like, a hummus delivery thing. So maybe pick one of those and just tell the story of what that's about.

    28. ZA

      Yeah, I'd love to. Uh, really fun that you asked about this. Um, so I'll tell the thermal clothing, 'cause I think it's really cool. So in high school, I was selling thermal clothes in 10th grade, uh, for, for one of my sister's friends or something, and basically, it was just, uh, packs of thermal clothing, uh, shirt and pants. Uh, I grew up in Jerusalem, so it's a bit chillier there, so it was perfect for, for the weather, and in 10th grade when I was selling them, they were, like, 20, $25 apiece, and I was making, like, $4 a sale. And if you look in the food chain, I was, like, sixth or seventh down the line, so this was, like, crazy margins. So during the summer, I thought about it, like, "I should just go straight to the importer." So throughout the summer, I called the importer, and at first he was really, really mad. He was like: "No, you have to work for me for years to get to this state." And I said: "Listen, man, I'm finishing school soon. This is not gonna be my career. Either do it or not," and we basically negotiated, uh, throughout the whole summer, and this was also, like, how I did things before ChatGPT. So he would, like, throw out something. He'd say, "Oh, the import tax has gone up," and I'll just search Google, like, import tax Israel, and, like, start reading, and I'll be on the phone with him, and I'll be like, "Hey, uh..." [chuckles] I'd, I would just basically stall, and then I'd somehow come back with a, uh, with a challenge. Um, and I ended up, uh, getting a really great price, like, $12.50 apiece, so I was making, like, 100% profit, and I spread throughout a bunch of different schools. Each school I had the coolest people in school, uh, selling for me. Um, and then, the cool- uh, a really fun thing that I did was we had a really awesome basketball team, and, like, our basketball team would basically be 30 points up within the first half. Um, and it kinda got boring for the crowd, so I wrote a song, like a, a basketball chant, about thermal clothes that basically has my number within it, and, like, the end of it was, um: "If you join in now, we'll give you a discount." And it- like, it was with drums and everything, and still, when I go to Jerusalem, I know, like, some people who I don't even know, like, know my number by heart because they know it by the tune. And sometimes when I walk in Jerusalem, people stop me and say, like, "Hey, it's Thermal Zevi."... so that was just a really cool experience, um, as a kid.

    29. LR

      This explains so much. [chuckles] Such a- just the marketing genius of that move. Oh, man. Okay, Zevi, this was incredible. Two final questions: Where can folks find you if they wanna reach out, maybe follow up on some of the stuff? We'll link to the scripts and prompts and all that in the show notes, so, uh, so you don't have to read that. And then, uh, how can listeners be useful to you?

    30. ZA

      Awesome. Um, so I've been helped throughout my whole career a ton, so I love helping any way I can. So reach out on LinkedIn, uh, or on X. I, I'd really love to help whoever I can. How can you s- you s- uh, listeners be useful to me? So if you're a student, try StudyMate, tell me what you think. Uh, if you're in Israel and you are not using dictation yet, try Dibur2text, tell me what you think.

Episode duration: 1:15:12

Install uListen for AI-powered chat & search across the full episode — Get Full Transcript

Transcript of episode 1em64iUFt3U

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.

Add to Chrome