How a Meta PM ships products without ever writing code | Zevi Arnovitz

• A non-technical product manager can leverage AI tools like Cursor and Claude Code to build and ship real products independently, overcoming the fear of coding.
• The speaker developed a structured workflow using custom /commands within an AI-native code editor, managing the entire product development lifecycle from ideation to deployment and documentation.
• AI empowers non-technical individuals to become "builders," challenging the traditional need for extensive coding expertise and making product creation more accessible.

• AI empowers non-technical product managers: Individuals with no prior coding background can successfully build and ship functional applications using AI tools, significantly accelerating personal productivity and product development.
• Leverage AI-native code editors and LLMs: Tools like Cursor, powered by models such as Claude Code, provide an integrated environment where AI directly assists with coding, planning, and review, making complex tasks accessible.
• Develop a structured AI workflow with /commands: Create reusable, custom prompts (e.g., /create issue, /exploration phase, /create plan, /execute plan, /review, /peer review, /update docs) to streamline the entire product development lifecycle.
• Mitigate "people-pleaser" AI tendencies: Configure AI with specific "CTO" prompts that challenge ideas and focus on technical feasibility, preventing the AI from simply agreeing with potentially flawed concepts.
• Employ multiple LLMs for code review: To enhance accuracy and catch AI-generated mistakes, feed the code to different large language models (e.g., Claude Code, Codex, Cursor's built-in AI) for independent review.
• Adopt a gradual learning curve for AI tools: Start with user-friendly chat interfaces (like ChatGPT projects), then progress to AI app builders (like Bolt or Lovable), and finally to advanced AI-native code editors (Cursor) to ease into coding exposure.
• Integrate AI with project management tools: Utilize AI's tool-use capabilities (such as Anthropic's MCP) to automatically generate and update issues in platforms like Linear based on voice dictation or text prompts.

Sonnet 3.5 — A version of Anthropic's Claude large language model, noted for its capabilities in understanding and generating text. Bolt — An AI-powered application builder mentioned as an early tool that allowed non-technical users to create apps. Lovable — Another AI-powered application builder, similar to Bolt, used for building applications without traditional coding. Cursor — An AI-native code editor that integrates large language models directly into the development environment to assist with coding tasks. Claude Code — An AI model (likely a version of Anthropic's Claude) specifically optimized for generating and understanding code, used within Cursor. /commands — Custom, reusable prompts saved within a code editor (like Cursor) that can be invoked quickly to automate specific AI interactions or workflows. Linear — A popular issue tracking and project management software, often used by product and engineering teams to manage tasks and bugs. GPT projects / Claude projects — Conceptual "shared folders of chats" within an LLM interface, allowing for compartmentalized contexts, custom instructions, and shared knowledge bases for different tasks or roles. System prompt — The initial set of instructions or context given to a large language model at the beginning of a conversation or task to define its role, persona, and constraints. MCP — (Model-Controlled Programming / Anthropic's tool-use technology) — A technology developed by Anthropic that grants AI models the ability to use external tools and APIs, such as integrating with project management systems.

You are a product manager shipping product   without knowing how to write code,  barely knowing how to review code. 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." These days, you're using Cursor with Claude Code. If you're non-technical like me, code  is terrifying, but AI just makes it so   much possible. In the next coming years, I  think everyone's going to become a builder.   Titles are going to collapse and  responsibilities are going to collapse. The main challenge people have is  reviewing the code that AI has written. It's very difficult for me to catch  mistakes. What I'll do is basically   /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. 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. 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? Today, my guest is Zevi Arnovitz. Zevi is 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 /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, Devin, PostHog,  Superhuman, Descript, Wispr Flow, Perplexity,   Warp, Granola, Magic Patterns, Raycast,  ChatPRD, Mobbin, 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 backend.   Users can build any website at any complexity,  e-commerce, portfolios, information websites,   blogs, and it comes with the 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 labeled solutions. That's the number  10web.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. Zevi, thank you so  much for being here and welcome to the podcast. 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. I've been on here,   so it's a crazy moment for me.  I'm really excited for this. I really appreciate that. I want  to start by reading actually a note   I got about you from Tal Raviv,  who is a previous podcast guest,   many times 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 introduced us.  Zevi is 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. 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   figured out. We're going to get very hands-on.  We're going to do a lot of show versus tell,   showing people what you've figured out about how  to be a PM, a non-technical PM building stuff. I   want to give people a little bit of background  on you because I think this is going to inspire   a lot of listeners to feel like they can also  do what we're about to show you. This is going   to look very advanced, but just give people a  little bit of sense of just your background. I'm very non-technical. I have zero technical  background. Did music in high school. A lot of   Israelis do technology units in the Army. I was  not in a tech unit. And basically a year ago,   I was traveling with my wife for three  months in Asia and we were in Japan and   that was around when Sonnet 3.5 came out.  And I remember watching a YouTube video.   I think it was either Greg Isenberg or Riley  Brown and they were basically building apps using,   it was either Bolt or Lovable, just using AI. And it was like a crazy moment for me because   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. 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, 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 failed. And if people walk away and  open their computer and start building,   you've succeeded." So I really hope that  we can inspire some people to do the same. I love that so much. I feel like that should  be the goal for my podcast. If you're like,   "I love that guest." It's less of a win.  If it's just like, "Oh, I'm so inspired   to do the thing that they figured out, that  is the real win." I love, Claude is the best. I agree. Okay. So let's dive in and give people, let's  start with kind of a high level overview of   how you operate and you 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 figured out and how you operate? This all started where I was a project's  power user. I love projects, GPT projects. ChatGPT projects? Yeah, exactly. GPT projects and Claude projects,  which are basically a shared folder of chats which   share both custom instructions and shared  knowledge base. And I think it was around   when GPT started using memory where I thought  it was interesting, but it really annoyed me   because I do a bunch of different things. I'm  a terrible runner, I'm a PM, I was a student,   psychology student, so I had all these  different facets of life. And what happened was   the memory feature was mixing stuff up. So like I talked to GPT about running   and it would say, "Oh yeah, after this 5K, you're  going to crush all your next product reviews." And   it's like, okay, I understand that you have that  in your memory, but it's just not relevant. And   projects basically allows you to compartmentalize  and have things within the right context. So   tracking back to the story I told when we came  back from Japan, I started building this app.  The first thing I noticed was that these products  were built in a way where, and 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   because they just go and start building your app. But later on when things got more complex, this   created much more problems because planning  is really important when you're implementing   something technical and let's say you're  implementing payments or something that's   going to be 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,   some really gnarly bugs that I had. And to mitigate this, what I did was I created   sort of a CTO. So again, I'm not technical. I  have been in product for a while, but I know   zero stuff about code. So basically what I did was  I created a CTO with the custom prompt of it 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 of how  this is going to 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. I always think about this  where 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 ... Just a short story I had   a few weeks ago, I was trying to learn about  Bun JavaScript, which 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   co-founder 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 talking   about what it meant and I was like, "Wait,  no, these are not the same at all." And it   said the most terrifying and hilarious thing. He goes, "Oh, I'm sorry. I thought you were   just making this up and I was riffing  with you." And I was like, "Oh no, no,   no, this is terrible." So basically if regular  ChatGPT was a CTO, that would be the CTO who goes   along with your dumbest ideas. So creating  the project allowed me to mitigate that. So this is, just to be super clear, you have  a ChatGPT project that you've given a prompt   to be your CTO of your product  and being a non-technical person,   this is kind of like the thing you talk to  when, and we'll get to what you're actually   using to build when you have questions about  architecture and decisions that are technical. Yeah. So now 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 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 Claude or in Cursor, you might be excited to   start using those, but I would really recommend  starting slow with a GPT project, beautiful UI,   super simple, then maybe graduate to like a Bolt  or a Lovable, and then go to Cursor in light mode,   slowly, slowly, gradually ease  in until you open a terminal,   go full dark mode, go full dev. So I would  really recommend doing this gradually. That is awesome advice. And so just to be clear,   these days you're using Cursor with Claude Code  powering it. And what I love about that is that   you've never written code. The way you put  it, you're afraid of even looking at code. Yeah, 100%. You can do exposure therapy, and I love  that Cursor 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 said that you actually went  to Bolt and Lovable kind of in the interim   and then you went just straight to Cursor. What's  the reason to just go straight to Cursor? Is it   just Cursor can do everything and once you get the  hang of it, it's actually the most powerful tool? 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  and I kind of started losing it and then   I graduated to Cursor and I've actually fallen  in love with Claude. So I'm using Claude Code,   but that also runs within Cursor, and  I think this is Tal who told me this.  I'm not sure who he's quoting, but code is  just words at the end of the day. 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 with multiple models and apps   on my project. So start slow, but definitely  there's a lot of places you can graduate to. Awesome. Okay. Should we dive into  screen share showing how you operate? 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.   Here on the right is Cursor. 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 going to close cursor for a second.  What you can see here are all my /commands.  Basically what /commands are, they are reusable  prompts that I save within the code base that   I can run by writing / and then the name of  the file. So here you can see Create Issue,   which is the first command that I'm going to  use. And basically what this tells Claude,   it says the user is meant 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 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   /create issue and this injects this prompt  into Claude. So it says, "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 want to   work on right now, but I want to 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 the create issue /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, when I want to pick this up,   I have the exploration phase. Exploration  phase is basically telling Claude,   we're going to only explore what we want to  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 going to create a plan. So you can see create plan. This basically has   a template that I love for creating 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, and at the end, we update the docs.  So this is updating documentation and everything  so that agents can write better code later on. So   I think what we'll do is we're going to build a  feature live for my app, which I think is really   cool. But first what I'd like to do 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 study materials and create   interactive tests based on their own materials. So here we can go to the top. Let's upload a PDF.   We can decide what pages we want to 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 augmentations the users decided to   Gemini and we create a quiz. These are 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? 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   you built that's making money. That's like a thing  you vibe coded having no technical experience. Yeah, this is my weekend  project. Yeah. This is what I do. Amazing. On weekends. Yeah. So you get basically  deep explanations into why each   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 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 build that live. How's that sound? I love it. Crossing your fingers, this all  work. I just want to highlight the stuff   you shared right before this in cursor. So this  is a huge deal, what you describe here. This is   essentially what you've figured out is a way as  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 /commands that   you've concocted that you're going to 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 figured out. Yeah, 100%. Basically what happened  was I formulated the backbone of this   with the CTO, and it was basically  within the system prompt of the CTO   project that I had within GPT. 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 /command and then it  will be automated within the workflow. Amazing. So just to summarize the /command.  So one is create an issue in Linear, which   I love. Linear is awesome. Shout out Linear. That's also from the product pass. From the product pass. Oh my God, what a value?  Okay. So step one is create the issue in linear.   So it's a command. So this prompt /command you've  created, just create issue. Then it's explore,   which is explore the idea, help me ideate on  what this could be. And this is Claude helping   you think through the feature and product.  And then it's actually create the plan.  And so it's like the AI helping you build the plan  to build the product. Then it's actually execute,   which is just build the thing.  And then there's this review,   peer review step, which is awesome that  you'll share. And then there's document,   update documentation based on the  new feature that we're adding. Sweet. Yeah. Cool. So let's go ahead and start  building. So I'm going to use Wispr Flow   to dictate and basically this starts with /create  issue. So this basically sends that prompt. And I   love this because I usually do this 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 waste time on this.  So just ask some brief questions so that  you have enough to capture within linear.   So I want to add fill in the blank questions to  StudyMate. 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   for two blank spots, and of course there's only  going to 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 a quick  think of how I want this to work.   So it's going to ask me a few questions. Quizzes  are 100% multiple choice, question structure,   single sentence passage to blanks and priority.  So one and two are correct, and this is   not high priority. It's a nice to have feature. So now basically what Claude is going to do is   it's going to use MCP, which is basically  a 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   going to do now is it's going to use everything  we've said and create an issue within Linear. And by the way, as this is loading, I just  love the way, the way you described 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. Yeah. So at first when I was doing this with  the CTO, I would do it with ChatGPT voice mode,   and that was crazy. That literally felt like  ideating with a person. It would push back,   ask questions, and maybe one day the coding tools  will get there too, but that was exactly ... It   really felt like sitting with my CTO. Great. So  created STU88. So if we open up Linear now, we   should be able to see ... Let's see where STU88. There it is. Fill in the blank questions with drag   and drop interface. So it has a TLDR, it has the  current state. It did a little bit of research on   the code base, I think, expected outcomes, some  context. So yeah, so this is basically ready for   me to pick up when I'm interested in building.  So now let's say a few days go by, I finished the   current project I'm working on, I can pick it up. So when I pick it up, I do /exploration phase,   which is what we said. And then instead of  pressing enter, I'll press tab and I'll show   you this. So basically, exploration phase, what  it does is it will take an argument. This is   basically a placeholder within the prompt,  which allows me to enter something that is   extra context for the AI. So I can say here,  Linear STU88, which is referencing the ticket.   And now what it's going to do is it's going  to go, it's going to fetch the Linear ticket. And what's the idea? What's  the goal of the exploration   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   trying to solve and also understand  the current state of the code base,   what files need to be affected, and how is  the best way to implement this technically.   And usually what happens is right now, Claude  is just basically reading a bunch of files,   understanding the basic structure of the  code, and then it's going to come back with   a bunch of clarifying questions that will  decide how we end up implementing this. So it feels like it's talking  to your engineering manager. 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   to have a CTO in there. Now the  CTO's living inside here in Cursor? Yeah, because of the way the tools have developed  and they've become so good at both exploration and   code execution. So now it's just a habit that  I call it a CTO, but it's basically all in one.   The same agent will both do the exploration and  write the plan and end up executing the code. Got it. So it's basically it's  Claude Code. Is there a prompt   you gave it to act like that? To  act like the right kind of CTO? Yeah, so within the Claude.md, which is  basically the system prompt that's loaded   within Claude's context in every conversation, I  have some basic stuff like this is our workflow,   this is how we work. Within exploration  phase, I want you to challenge my thinking,   all kinds of stuff like that that can  be loaded within the Claude.md file. 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,   how often is it actually great and ready? How  often do you have to edit it? What's the quality   of the Linear ticket that it generates? Because  a lot of people are probably wondering just like   all these terrible linear issues are being  created by AI. Are they actually any good? It's completely different because I'm a company  of one. So a lot of the context is within here   and there's no need for me to talk to other teams  and understand. It's basically very accessible,   and also I can easily see when  Claude understood something wrong.  I don't want to say that I would create Linear  issues at work like this, but definitely if you're   building your own side project, they're pretty  quality. And also, it just kicks off when I want   to start working on it. I wouldn't say it's ready  to be built. It's ready to start being explored. Got it. So it's just the beginning of an idea.  Actually, let's come back after we go through this   flow of how you would approach this if you were  at say Meta or another, maybe a smaller company,   how this workflow might work at a larger  company that isn't just your own startup. 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   base. I thoroughly analyzed StudyMate live  codebase and understand the current system,   feature quest and key areas that it's identified.  Usually I'd spend a lot of time going over this   because this is super, super important, but  just for the sake of development right now,   we're going to brush through this. Now Claude basically comes back after it's   gone through the code base and understood the  way it currently works. It's basically telling   me what the current understanding is. So it's  talking about how the app is set up at the moment,   how the data is structured, what it understood  from the feature quest, and what it has identified   as key areas, and then it asks me some questions. So it's asking about the scope, it's asking about   the data model, the UX/UI of the feature, how  it should be validated, how it should be graded,   what changes need to be happened to the AI  system prompt and all kinds of questions   about the app. I've prepared answers to all these  questions beforehand because I don't think we all   want to sit through this. So I'm just going to  paste that in and we'll see what Claude says. Awesome. I love it. And I love just scanning those  questions I was asking. It's like such smart,   sophisticated, important questions instead of  just, "Cool, here I go, I'm going to build it." Yeah, and I think this is the big difference  between just vibe coding and going along with the   vibes and really building serious apps. I spend  a lot, a lot of time going back and forth and   understanding. Also, a very cool /command that I  haven't showed yet is learning opportunity, which   basically when something is really difficult for  me to understand, I'll do /learning opportunity   and then talk about what I want to learn. And this basically primes Claude and says,   "I am a technical PM in the making. I  have mid-level engineering knowledge.   I understand architecture and basically I want  you to explain what we're currently working on   using the 80/20 rule." So this is a great way to  learn. I would definitely take this and every time   you kind of see something that you don't fully  understand, I would definitely use this to learn.  Great. So Claude basically comes back and says how  it understands the current data model and how it's   going to implement. Yeah, so it's ready to create  the plan. So basically what I'm going to do now   is I'm going to go and do /create plan and while  Claude is doing this, I'm going to show really   quick what this looks like. So basically, these  plans are from a template that I found on Twitter.  I forgot who it was, but it was just a  template that really resonated with me. And   it's basically saying, based on our exchange,  create a markdown file that will be the plan,   include clear, minimal, concise steps, track the  status. So this basically has like status trackers   on each task that Claude updates as it's going  through and it will have a TLDR, some critical   decisions that we've made and the plan itself. So Claude has finished writing the plan,   so we'll be able to look and see exactly what the  plan is. So it has a TLDR, it has the critical   decisions we've made and the tasks broken down.  And this is a perfect plan and it's also a really   good way to write this because a lot of times,  I'll use different models to execute certain   stuff. So Cursor has an amazing model called  Composer, which is superfast. So a lot of things   that are not that complex, I'll use Composer. Gemini 3 that just came out is unbelievable   at UI. So a lot of times, I'll split  the plan into backend and front end,   and then I'll have Gemini just read the plan and  do the front end. So having this as a markdown   file is really good. And also going forward,  it's really good to have within the app so that   later on, if an agent is writing code in a certain  area, I can see what's already been done there.  So what we're going to do now is we're going to  execute the plan. So now I think we're going to   do this with Cursor just because 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 basically understands what the plan is and  it's going to go ahead and start writing the code. 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.   You said that Lovable and Bolt and other  apps in that space are just not enough to   build really serious apps and you have to move  to Cursor to do that. Tell us more about that.   Just what's the limitation you ran into with  those products and why you switched to Cursor? I started using Cursor and Claude Code a few  months ago and I haven't looked back, but at that   time, these teams have been moving like crazy.  So I don't want to 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 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. 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 hard decisions out for the user.  So the user doesn't 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 you can't build really amazing  production apps using Bolt or Lovable now,   but I think basically if you want the most cutting  edge abilities of the models and you want to   be able to make all the decisions on your own,  it's probably best to be on one of these tools. 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? Yeah, for sure. Lovable, Bolt, Replit, Base44. v0. Yeah, v0, all same bucket. So essentially, they're doing that  planning for you. And as you said,   they're very opinionated. They try  to make it easy. So it's just like,   "Here's how to do it. Here's the way 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 want to go in a different direction,   you don't have the power to change how  they plan. So Cursor lets you do that. Yeah, I don't want this to come out like  I'm badmouthing them. Base44, let's say. No, absolutely. Yeah. Base44 does an amazing job at basically  taking all the complex guesswork out of   building product and just allows you  to just 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 what database  am I using. Do I need sign in with Google this way   or another way? It would just do it out of the  box. So that's basically the trade-off there. Awesome. Shout out Maor, the founder of Base44. Yeah. Maor Shlomo. Yeah. He's amazing. Okay. I just love how this is like the way you're  like flinging, what's the word? Slinging models   like Gemini 3 for frontend. I love that you've  never written any code and you're just like,   "Cool, use Gemini for this and Claude  for this. And I'm just working on Cursor,   talking to this CTO, helping you build  stuff and build significant product." Yeah. We just live in the craziest of times where  basically the world changes once a week, it feels   like. And there is just no boundaries. You can  use all of these just on your regular MacBook   or regular laptop. And I have these moments,  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 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 went from   no domain, no nothing, to live 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 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, at the moment it was my wife,   I'll just say, "We live in the future." And she'll  be like, "Huh, what?" 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 an API away.   You can use anything. So I think it's an awesome  time to be curious and optimistic and hardworking. 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, as you said, poke your head out of the   rocket ship and just like, "Hey, here's this thing  that I figured out. Here's where we're going." Yeah, best time to be alive. So  awesome. So it looks like it's finished.   So now what we're going to do is we're going  to run the app locally and we'll be able to see   what Composer ended up building and we're  going to see if anything else is needed   on our end to maybe do some manual  review. Does that sound good? 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 for work. For sure. Yeah, for sure. No, Composer  like the one thing is it's just so,   so blazing fast, keeps you in flow.  So yeah, full features take minutes. 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,   I look at it all as tuition,  as stuff that I'm paying for   learning. So I don't know how much it  costs, but it's definitely worth it. That explains why they're the  fastest growing products in history. 100%. Your marketing website sets the tone for  your brand and is the one touchpoint that   every single one of your customers sees.  In today's age, if you're still having   a hard time making small changes and simple  updates to it, you are doing something wrong.   That is why so many companies from  early stage startups to Fortune 500s,   including companies like DoorDash, Zapier,  Perplexity, and ElevenLabs turn to Framer,   the website builder that turns your .com from a  formality into a tool for growth. Framer works   like your team's favorite design tool and comes  with real-time collaboration, a robust CMS with   everything you need for great SEO and advanced  analytics that includes integrated AB testing.  Changes to your Framer site go live to the web  in seconds with a single click and without any   help from engineering. Whether you want to  launch a new site, test a few landing pages   or migrate your full.com, Framer has programs for  startups, scale-ups, and large enterprises to make   going from idea to live site as easy and fast as  possible. Learn how to turn your website into a   growth engine from a framer expert or get started  building for free today at framer.com/lenny,   that's framer.com/lenny. Rules  and restrictions may apply. So now we have this feature, which basically  we built and I can ask it to make some changes   because it's running locally and once  it's ready, I'll be able to ship it to   users. So now the next phase after I've  QA'd it and basically tested it manually,   I'll have Claude review its own work. So  what I'll do is I'll reopen Claude Code. I love this because this is one of the things  that comes up a lot in this podcast is writing   code is now so easy. The main challenge people  have is reviewing the code that AI has written. 100%. And what you're doing here is you're  having Claude review its own code. 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 as good as possible   and to catch as many things as possible. So  I'll always manually QA at first to make sure   if I can see any mistakes that Claude made.  And then what I'll do is basically /review.  And this 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 I do is I have a /command called peer  review, which is really interesting. And basically   what it does is it's going to take Claude,  which is usually the agent who I'm working with.  And just to put this in a mental model, this  is basically my dev lead that I'm working with.   The /command is basically saying, "You're the dead  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 said at face value. The reason is you have  more context than them and you led this project.  You need to either explain why the stuff they  found are not real issues and wrong or fix them   yourself. 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 really tell you how each one of these   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   be the perfect CTO. She's very communicative.  She's very smart. She doesn't just go with the   flow and do whatever you tell her. She's very  opinionated, but also super collaborative, which   is I think why I'm always drawn to Claude because  I need to do so much learning and it's your dream,   a very communicative, but very opinionated  dev lead, but then there's also Codex.  So I use Codex 5.1 Max, whatever. I don't  know, they're not the best at naming models,   but GPT's model. I always imagine it as like  the best coder within the company who comes   to the office with 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 it will just   close the door for two hours and come out and say,  I fixed it." And you're like, "Wait, what? Are you   going to tell us what happened or whatever?" And he's like, "Don't worry about it. I fixed   it." It's like really not communicative, but  it solves all the worst problems. And let's   say Gemini is like a crazy scientist who's  super artsy, super talented at designing,   but if you sit next to it and watch it work,  it's terrifying. You would fire that person   instantly. This might be just my experience,  but when I'm using Gemini within antigravity,   which is Google's new competitor to  Cursor, when it's writing code, you can   see the steps it's taking and it's terrifying. You'll say, "I want you to redesign the top of   the dashboard." 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. I'll bring   it back." And then it will say, "Oh, can I  edit the database?" And you're like, "No,   do not edit the database. You're just doing a  redesign." And then it will end up designing   something beautiful. So the way there is 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   and basically playing to their strengths  and mitigating their weaknesses by using   other models is a game changer for me. So I'll  do peer review a bunch of times and I'll have   other models review other models code and kind  of have them fight it out basically. Sometimes   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 thing that I've added  and I haven't seen many people doing it. That is such an incredible rant/way  to understand what's 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 you learned there. Yeah. So basically Claude has reviewed its code  and it's found a bunch of bugs, a critical bug   it found in the prompt, 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 all the code in this branch. Of course, branch is referring to the GitHub   branch that we're working on. We're not working  on the live code base. And then I'll do this with   Composer say with, let's do it with Composer One.  So I'll do /review here as well. And basically   these are both going to run and do a in-depth  review similar to what Claude does. But again,   because of the differences between the models,  they're all going to catch different things and   they're all going to look differently,  and this is a really cool way to work.  It's basically if you had other team leads  within the company 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 we'll come back in a few minutes. Okay, cool. So we can let these  run in. 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 copy and paste  kind of these results. Is that the idea? Exactly. I'll copy and paste the results. I'll  do peer review and then I'll say dev lead one   and then paste from one of the models. And then  I'll say dev lead two and paste from the other   model and basically have them fight it out  until I feel like we have no more issues. Incredible. For me, this is super important  because I'm not technical and   I'm not a developer. And I'll also  use /learning opportunity a bunch   during this to learn about stuff that I  don't understand or don't fully grasp. Incredible. What a clever solution to solving  this code review problem where it's like,   I don't know what you ... I don't know how to  recode, so what am I going to even ... Yeah. Yeah. Okay. Incredible. Let's wrap up this  workflow. Is there anything else that's   important in this workflow? And again,  all this stuff is going to be available   where people can just plug this stuff into  their Cursor account and use it themselves. 100%. The one thing I'll say is that I think just  like working in general with AI and even just like   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 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 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   an internal tool or anything. And  I think this is just like working.  If 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,   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 okay with using AI  and the people who actually know how to use it. That is such good advice. So what  I'm hearing is 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 /command prompts  with that knowledge so that in the future,   it's not making that same mistake,  and it just keeps getting better. Exactly. These things just keep getting smarter  and smarter. So you're building up this   really incredible prompt that  just gets better and better. Exactly. Not always the /commands.  It will sometimes update   different documentation or its tooling,  but basically it's understanding what   the root cause of the mistake  that the AI made and fixing it. Awesome. So the models are getting smarter  and then there's also the other parts of   your workflow can get smarter as you  find flaws in the way it does stuff. 100%. Yep. Amazing. Okay. Is there anything else there  before I move in a couple other directions? I think that's it. I think we covered pretty  much everything. Basically, just to wrap this up,   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.   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 going to  release this. This was just a show, but hopefully   maybe by the time the podcast comes out, I'll  have done this correctly and release the feature. It's incredible that this was not possible, I  don't know, two years ago, maybe a year ago,   you are a product manager shipping 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  all of these different AI models. You're   making money with this product. We're so used to  this now, but it's insane what is now possible. It's the best time to be live. 100%.  I think that I understand the fear,   but AI just makes it so much possible. Just  a quick 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   and seniors understand to use technology and  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 a full-fledged CRM system and   automation system for his business completely  alone. So for the people who are curious,   optimistic, hardworking, this is  the best time to be a builder. 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 going to be   sharing all these /commands and basically  this whole workflow with the audience. Yeah. Okay. And like I said, just start at GPT.  Start on GPT, tell it what your idea is,   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 inquisitive, learn.   Don't rush things. It's very important to just  dive in and really spend the time to learn. And you share this. One of your /commands is  learning opportunity, and it's how you learn   a lot of these things. Just teach me this  thing and how this database issue works. Exactly. Okay. There's a couple directions I want to  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 want to start trying to ship  code, at least showing people what's possible? I think that first making your code base 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 code   base and high level structure so that the  agents navigate through the code base easier.  And I think that if this is set up in  a really good way, I still don't think   PMs should be shipping heavy database  chain migrations or any big project,   but contained UI projects, especially if  you just build it, create the PR and send   it to a dev to do the final finishes. I  think that's definitely something that's   possible. And I think we're going to see  that a lot in the next coming years. I   think basically everyone's going to become a  builder, so it should be really interesting. Okay. So your advice here is as a PM, 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 in a couple years, PMs will  be doing this and it'll feel less scary and crazy? If there are PMs. Yeah, I think titles are  going to collapse and responsibilities are   going to collapse and everyone's just going to  be building. I definitely think that the models,   the context window is getting bigger, the models  are getting smarter 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 going to be difficult.  A lot of developers are very, very  skeptic about the current state,   and I think that it's going to 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 want   to take the time to work on their workflow  about how can our team become more AI native,   I think that these teams are going to probably  be a few years in the future and they're going   to look back at the few weeks they spent  setting this up as the best time they spent. 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 PMs for every function I  imagine is just you start to rely on these things,   your skills start to atrophy, you're  producing all this slop that looks great,   cool, amazing strategy doc. No, it's  actually not at all good. Are these Linear   tickets or just products that are half-baked? What's your take on these two parts of just like,   how has this impacted your craft as a PM?  Do you feel like this is weakening your   skills because you're so reliant on these  tools and just how do you keep the quality   of this stuff up and not just like, "Eh,  it's just a bunch of AI generated slop." I have a very strong disagree to this and I've  heard it a bunch. I remember when I started using   Tal Raviv has this whole course on building a PM  Copilot using projects, which is probably one of   the best courses 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 role of the PM is, it's the exact opposite.  It's basically harnessing anything that can get  us as quick as possible to delivering the right   solution to users. And I just think this is  like that really smart person that has context   or your mentor or whatever, but is just always  available and doesn't judge you and can really   help you. So if you're using it to just create  your outputs and then putting them out there,   yeah, that's AI slot, 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 show  something in a product review and you say, "Oh,   sorry, that was built by AI." That's your mistake.  I think if you use these intentionally 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. I think   that at Wix, I wasn't thinking of what's the  marketing strategy of the company and how will   the onboarding be completely revamped within  the whole product. But 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 reps,  which is one of the most important things   at the beginning of your career. So I understand  the fear that how do 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 if you're using it wrong. Is there anything that you've learned about  reducing the sloppiness of the output,   just like a tip for keeping the quality  high of the stuff that it produces? Similar to people, setting up AI for success,  for the task at hand. So if I just brought in   a junior 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 top strategy deck 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 and all these  different things, I think that's probably   one of the biggest unlocks. So that's just a quick  tip. And also Cursor has a /command called deslop,   which is basically going back over the code.  I don't know if this is integrated into the   product yet, but it's on Twitter. Their  founders have been talking about this,   so that's definitely something I would run after  just to make sure that no slop is left behind. That is so funny, deslop. Okay. One more question,   which may lead to something else, but 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 reading about all   these people using AI to help them interview. You  actually did it. What did you use? What worked? 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  formed differently. So if you ask me, how do you   answer a phone, I'll do this. But a child now,  when you say, "How do you answer the phone?"   They'll do this. They'll do the iPhone answer. And  I feel like people who are growing up now in their   professional lives were 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 Meta reached out and said they'd   like me to interview. Straight away, I opened  up a project 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 stuff from Ben Erez who has  written a guest post 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, 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 in Base44, which helped me ... I   was really struggling with segmentation  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. 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, I think Ben talks   about this a bunch, so I don't 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 human mocks. So cold outreaching to people on LinkedIn and   having them do actual mocks for me, I think that  at the end of the day, especially for the Meta PM   prep, which is super competitive and difficult,  I think there's no way to get around that. That is so cool they use that post. I wasn't  aware. We're going to link to it. And in that   post, Ben shares all these prompts you can feed  ChatGPT to help you prepare for interviews,   do mocks online. It's a really important point  to say that those take you to a point, but it's   actually better to use humans. I actually have a  post coming out soon in collaboration with Noam   Segal about how everyone is using AI to interview. And one of the most interesting ways I've heard   people and that we've 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.   Here's what you missed because 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 can do that. So I'll add two things to that. One, which  is exactly this. So I'll mock with AI. Also,   I did something really cool where there's  a question bank online free by Louis Lynn,   which basically is an always updating bank  of questions that people are asked in real   interviews. And I basically used Comet, which  is the Perplexity's browser. And I had the   agent run all kinds of analyses on what the most  asked questions are. And that's how I knew how   to prioritize what questions I would mock. And then at the end of these mocks, I would   tell Claude within the project, "You're my coach  and I don't want you to make me feel good. I want   you to make me as ready as possible for these  interviews. So give me feedback, like you said."   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 perfect answer. Oh, man. 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. Let's go to AI immediately and help   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   hearing, but 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. I agree. And that's what these conversations are for  to help people keep up with all that and to   learn some of these skills. And again, see  where the future is going and start to learn   how to get there yourself. Okay. Zevi, before  we get to our very exciting lightning round,   I'm going to take us to a recurring segment  on this podcast I call Failure Corner.  And why I love this segment is people  come on this, just even this conversation,   it's like all these amazing things  you figured out, everything is going   so well. People rarely hear the things that  don't go well, and those are often the most   interesting and impactful stories. So  the question is just, what's the story   of a time you failed in your career and  what did you learn from that experience? Yeah, I love this. I love this. I love Failure  Corner, big fan. So I'll tell a story about   when I started at Wix. So basically I started  within Wix as a student program and straight   out of the student program, you get put into a  certain team. So I was in the editor, which is   the core product of Wix. And the other  PMs were just the best PMs almost at Wix.  There's four other people 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 going to blow these people's   socks off. They're not going to believe how  good of a PM I am. And I basically didn't   really share what I was thinking. I would  work tons of hours alone and I was like,   "I'm going to kill this product review. They're  going to be so impressed." And I ended up failing   miserably. My product review was not good. It wasn't the format they expected. They   had a ton of questions that I missed and  I felt awful when it was over. I was like,   "Ah, you're such an idiot." And I saw that  everyone was like, "All right, cool. Yeah,   just come back in two weeks and we'll keep getting  at this." And 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  shifted. And I think this is probably the best tip   that I give now 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 assessed what their   strength is and used them as a mentor for that. So Neri who's still my mentor till today,   he has the best product sense of  anyone I've met. Oya is super,   she's like a methodology expert. She just thinks  in frameworks. Yahra, who is the head of product,   basically can look at a product and then instantly  understand 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 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  because it wasn't this kid who's trying   to show us up how cool he is. It was like our  mentee kind of making us all proud. And it was   such a great shift for me. And basically at the  end of the day, I really excelled through this. That is an awesome story. And this idea of  learning is such a good thread throughout   this whole conversation that AI 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 opportunity   /command. So awesome. Great story. 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? Yeah. So kind of to tie back into the first  thing I said where if people walk away thinking,   "Zevi's so cool." 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  contrary to what a lot of people are saying how   there's no more junior roles out there and people  get out of school and 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 on your own with a couple  of friends completely bootstrapped. And I see   more and more people towards the end of my  time at Wix, I was interviewing and I saw   more and more people building their own stuff  with AI. And I think 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 want to 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 I really hope people get inspired  by this and start killing it with their projects. Amazing. So many ways to be inspired  from this conversation. Zevi, with that,   we've reached our very exciting lightning round.  I've got five questions for you. Are you ready? Yep, let's do it. What are two or three books that you find  yourself recommending most to other people? So I'll take one from each kind of genre. So in  fiction, I love The Fountainhead by Ayn Rand,   one of my favorite books. Really makes you  think, really makes you feel. Business books,   I'm a big fan of Shoe Dog, the Nike  story, one of my favorite books. I just finished reading that. So funny. Amazing. This is great. It was great. Yeah. I love Shoe Dog. And then more on  the psychology side Mindset by Carol Dweck,   who coined the term growth mindset.  It's just such an amazing book. It   kind of sounds like a self-help book, but  then you understand that it's completely   psychological and is based on research  and that book completely changed my life.  Really, I was always with a fixed mindset, and  then after reading that, I kind of understood   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. Again, connects to that thread of the way you  described it, being a 10X learner versus a 10X   doer. Okay. Next question. Favorite recent  movie or TV show you have really enjoyed? Yeah, actually, my wife is really into film, so  we watch a lot of TV. It's probably our favorite   together time. I just finished watching The Pitt,   which was amazing. It was really good.  And my first recommendation to everyone   is if you haven't seen Severance run to  see Severance, one of my favorite shows. Is there a favorite product that you have  recently discovered that you really love? This is a good question. I'm always trying new  products. I'll always have three or four browsers   installed on my computer and all this different  kind of stuff, and I recently discovered a Loom   alternative. I was kind of disappointed with Loom.  They were taking so much money and the product,   I don't know, I just didn't love it. And  there's an open source alternative called Cap,   which is just really well-crafted. You can  see that the person was really sweating the   details and it's just a really, really great  alternative. So I've been using that recently. There's also a product called Supercut  that I love that's also a Loom alternative.   Shout out. Okay. Two more questions. Do  you have a favorite life motto that you   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,   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 ability to   do things now 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   kind of makes you take life more lightly. So  yeah, nobody knows what the they're doing. I think people see these companies on the outside  and it feels like everything they've got 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. It's all about to fall apart. Yeah. Okay. Last question. You've had a long entrepreneurial   thread throughout your career. There's a  couple other 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. Yeah, I'd love to. Really fun that you asked about  this. So I'll tell the thermal clothing because   I think it's really cool. So in high school,  I was selling thermal clothes in 10th grade   for one of my sister's friends or something,  and basically it was just packs of thermal   clothing, shirt and pants. I grew up in  Jerusalem, so it's a bit chillier there.  So it was perfect for the weather. And in 10th  grade, when I was selling them, they were like 20,   $25 a piece 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 going to be   my career. Either do it or not. And we basically  negotiated throughout the whole summer. And this   was also like how I did things before ChatGPT.  So he would throw out something, he'd say, "Oh,   the import tax has gone up." And I'll just search  Google, like Import Tax Israel and start reading.  And I'll be on the phone with him and I'll be  like, "Hey, I would just basically stall." And   then I'd somehow come back with a challenge.  And I ended up getting a really great price,   like 12 and a half dollars a piece. So I was  making 100% profit and I spread throughout a   bunch of different schools. Each school, I had the  coolest people in school selling for me. And then   a really fun thing that I did was we had a really  awesome basketball team and our basketball team   would basically be 30 points up within the first  half and it kind of got boring for the crowd.  So I wrote a song, like a basketball  chant about Thermal Clothes that   basically has my number within it. And  the end of it was if you join in now,   we'll give you a discount. And it was with drums  and everything. And still when I go to Jerusalem,   I know some people who I don't even 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 as a kid. This explains so much just the marketing  genius of that move. Oh man. Okay. Zevi,   this was incredible. Two final questions.  Where can folks find you if they want to reach   out and maybe follow up on some of the stuff?  We'll link to the scripts and prompts and all   that in the show notes so you don't have to read  that, and then how can listeners be useful to you? Awesome. So I've been helped throughout my  whole career a ton, so I love helping any   way I can. So reach out on LinkedIn or on X.  I'd really love to help whoever I can. How can   listeners be useful to me? So if you're a student,  try StudyMate, tell me what you think. If you're   in Israel and you are not using dictation  yet, try Dibur2text. Tell me what you think. Amazing. I just love how much you're giving  away and how useful that's going to be to so   many people. So again, we'll link to that in  the show notes. Zevi, you're awesome. Thank   you so much for being here. Thank you so much for  sharing so much. This is going to help, I think,   a lot of people and I think it's going to  help people get over the hump on. Okay,   I see all these people doing cool stuff.  Here's how I can actually do this stuff. So   thank you so much for being  here and for sharing so much. Thank you for having me. And  if you build something cool   with some stuff that I learned here,  hit me up, send me. I'd love to see. 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   show on Apple Podcast, Spotify, or your favorite  podcast app. Also, please consider giving us a   rating or leaving a review as that really helps  other listeners find the podcast. You can find   all past episodes or learn more about the show at  lennyspodcast.com. See you in the next episode.