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

Zevi Arnovitz is a product manager at Meta with no technical background who has figured out how to build and ship real products using AI. His engineering team at Meta asks him to teach them how he does what he does. In this episode, Zevi breaks down his complete AI workflow that allows non-technical people to build sophisticated products with Cursor. *We discuss:* 1. The complete AI workflow that lets non-technical people build real products in Cursor 2. How to use multiple AI models for different tasks (Claude for planning, Gemini for UI) 3. Using slash commands to automate prompts 4. Zevi’s “peer review” technique, which uses different AI models to review each other’s code 5. Why this might be the best time to be a junior in tech, despite the challenging job market 6. How Zevi used AI to prepare for his Meta PM interviews *Brought to you by:* 10Web—Vibe coding platform as an API: https://10web.io/lenny DX—The developer intelligence platform designed by leading researchers: https://getdx.com/lenny Framer—Build better websites faster: https://framer.com/lenny *Zevi's Slash Command Bank for Claude* https://zeviarnovitz.com/ *Episode transcript:* https://www.lennysnewsletter.com/p/the-non-technical-pms-guide-to-building-with-cursor *Archive of all Lenny's Podcast transcripts:* https://www.dropbox.com/scl/fo/yxi4s2w998p1gvtpu4193/AMdNPR8AOw0lMklwtnC0TrQ?rlkey=j06x0nipoti519e0xgm23zsn9&st=ahz0fj11&dl=0 *Where to find Zevi Arnovitz:* • X: https://x.com/ArnovitzZevi • LinkedIn: https://www.linkedin.com/in/zev-arnovitz • Slash commands and templates: https://zeviarnovitz.com *Where to find Lenny:* • Newsletter: https://www.lennysnewsletter.com • X: https://twitter.com/lennysan • LinkedIn: https://www.linkedin.com/in/lennyrachitsky/ *In this episode, we cover:* (00:00) Introduction to Zevi Arnovitz (04:48) Zevi’s background and journey into AI (07:41) Overview of Zevi’s AI workflow (14:41) Screenshare: Exploring Zevi’s workflow in detail (17:18) Building a feature live: StudyMate app (30:52) Executing the plan with Cursor (38:32) Using multiple AI models for code review (40:40) Personifying AI models (43:37) Peer review process (45:40) The importance of postmortems (51:05) Integrating AI in large companies (53:42) How AI has impacted the PM role (57:02) How to improve AI outputs (58:15) AI-assisted job interviews (01:02:57) Failure corner (01:06:20) Lightning round and final thoughts *Referenced:* • Becoming a super IC: Lessons from 12 years as a PM individual contributor | Tal Raviv (Product Lead at Riverside): https://www.lennysnewsletter.com/p/the-super-ic-pm-tal-raviv • Wix: https://www.wix.com • Building AI Apps: From Idea to Viral in 30 Days: https://www.youtube.com/watch?v=j2w4y7pDi8w • Riley Brown on YouTube: https://www.youtube.com/channel/UCMcoud_ZW7cfxeIugBflSBw • Greg Isenberg on YouTube: https://www.youtube.com/@GregIsenberg • Bolt: https://bolt.new • Inside Bolt: From near-death to ~$40m ARR in 5 months—one of the fastest-growing products in history | Eric Simons (founder and CEO of StackBlitz): https://www.lennysnewsletter.com/p/inside-bolt-eric-simons • Lovable: https://lovable.dev • Building Lovable: $10M ARR in 60 days with 15 people | Anton Osika (co-founder and CEO): https://www.lennysnewsletter.com/p/building-lovable-anton-osika • StudyMate: https://studymate.live • Dibur2text: https://dibur2text.app • Claude: https://claude.ai • Everyone should be using Claude Code more: https://www.lennysnewsletter.com/p/everyone-should-be-using-claude-code • Bun: https://bun.com • Zustand: https://zustand.docs.pmnd.rs/getting-started/introduction • Cursor: https://cursor.com • The rise of Cursor: The $300M ARR AI tool that engineers can’t stop using | Michael Truell (co-founder and CEO): https://www.lennysnewsletter.com/p/the-rise-of-cursor-michael-truell • Wispr Flow: https://wisprflow.ai • Linear: https://linear.app • Linear’s secret to building beloved B2B products | Nan Yu (Head of Product): https://www.lennysnewsletter.com/p/linears-secret-to-building-beloved-b2b-products-nan-yu • Cursor Composer: https://cursor.com/blog/composer • Replit: https://replit.com • Behind the product: Replit | Amjad Masad (co-founder and CEO): https://www.lennysnewsletter.com/p/behind-the-product-replit-amjad-masad • Base44: https://base44.com • Solo founder, $80M exit, 6 months: The Base44 bootstrapped startup success story | Maor Shlomo: https://www.lennysnewsletter.com/p/the-base44-bootstrapped-startup-success-story-maor-shlomo • v0: https://v0.app ... References continued at: https://www.lennysnewsletter.com/p/the-non-technical-pms-guide-to-building-with-cursor _Production and marketing by https://penname.co/._ _For inquiries about sponsoring the podcast, email [email protected]._ Lenny may be an investor in the companies discussed.

Speaker names marked ? are inferred from speaking time and the show’s known hosts — they are not voice-verified.

• 0:00Lenny Rachitsky?

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

• 0:05Speaker 01

  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 Loveable. It basically felt like someone came up to me and said, "You have superpowers now."

• 0:19Lenny Rachitsky?

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

• 0:22Speaker 01

  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 going to become a builder. Titles are going to collapse and responsibilities are going to collapse.

• 0:32Lenny Rachitsky?

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

• 0:36Speaker 01

  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.

• 0:52Lenny Rachitsky?

  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.

• 0:59Speaker 01

  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?

• 1:11Lenny Rachitsky?

  Today, my guest is Zevi Arnowitz. 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,

• 1:56Lenny Rachitsky?

  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. 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, Posttalk, Superhuman, Descript, Whisperflow, Perplexity, Warp,

• 2:38Lenny Rachitsky?

  Granola, Magic Pattern, Drake House, Chat, PRD, Mobbin, and Stripe Atlas. Head on over to lennysnewsletter.com and click Product Pass. With that, I bring you Zevi Arnowitz 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 2 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.

• 3:21Lenny Rachitsky?

  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/leni and use code LENNY for exclusive free credits and 30% off API or white labeled solutions. That's the number 10, W E B, dot I O, slash, LENNY. Vibe coding platform as an API.

• 4:06Lenny Rachitsky?

  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.

• 4:52Speaker 02

  Zevi, thank you so much for being here and welcome to the podcast.

• 4:56Speaker 01

  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.

• 5:06Speaker 02

  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-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 introduced us. "Zevi is the most hands-on vibe coding PM I know, and I 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."

• 5:37Speaker 01

  That's so nice.

• 5:38Speaker 02

  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. It's going to look very advanced, but just give people a little bit of sense of just your background.

• 6:04Speaker 01

  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,

• 6:47Speaker 01

  "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.

• 7:27Speaker 02

  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.

• 7:41Speaker 01

  I agree.

• 7:42Speaker 02

  Okay, so let's dive in and give people, 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 figured out and how you operate?

• 7:56Speaker 01

  This all started where I was a Project Power user. I love projects, GPT projects.

• 8:02Speaker 02

  ChatGPT projects.

• 8:03Speaker 01

  Yeah, exactly. GPT projects and Claude projects, 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 really annoyed me cuz I do a bunch of different things. Like I'm a terrible runner, I'm a PM, I was a student, a 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 be, and it would say, oh yeah, after this 5K, you're gonna crush all your next product reviews.

• 8:46Speaker 01

  And it's like, ah, I mean, 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. Uh, the first thing I noticed was that these products were built in a way where, and when I say these products, I mean bolts and lovable, were built in a way where they were super eager to write code. So their system prompt was your coding agent. So when you write something, they'd straight away start coding. So at the beginning of a project, this was super fun and exciting cuz they just go and start building your app. But later on, when things got more complex, this created much more problems

• 9:31Speaker 01

  cuz planning is really important when you're implementing something technical. And let's say you're implementing payments or something that's gonna be a change to your database. If the coding agent is just like, alright, 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, 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.

• 10:13Speaker 01

  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 chat GPTisms. Uh, 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 chat GPT 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 a few weeks ago, I was trying to learn about Bun JavaScript, which is was acquired by Anthropic and I was trying to understand what they do.

• 10:53Speaker 01

  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 Zoo Stand, 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 like the most terrifying and hilarious thing 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 chat GPT was a CTO, that would be the CTO who like goes along with your dumbest ideas.

• 11:36Speaker 01

  So creating the the project allowed me to mitigate that.

• 11:40Speaker 02

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

• 12:00Speaker 01

  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 chat box 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.

• 12:44Speaker 01

  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.

• 13:02Speaker 01

  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 like open a terminal. You know, go full dark mode, go full dev. So I would really recommend doing this gradually.

• 13:18Speaker 02

  That is awesome advice. And so just to be, 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. The way you put it, you're afraid of even looking at code.

• 13:32Speaker 01

  Yeah.

• 13:33Speaker 02

  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 chat GPT 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 in interim. And then you went to just straight to Cursor. What's the reason to just go straight to Cursor? Just because, is it just because Cursor can do everything? And once you get the hang of it, it's actually the most powerful tool?

• 14:02Speaker 01

  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. 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 on with multiple models and apps on my project. So. Start slow, but definitely there's a lot of places you can graduate to.

• 14:42Speaker 02

  Awesome. Okay, should we dive into a screen share showing how you operate?

• 14:47Speaker 01

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

• 14:49Speaker 02

  Mm hmm.

• 14:50Speaker 01

  Perfect. So, within my codebase, 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 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 codebase 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."

• 15:32Speaker 01

  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 slash, 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.

• 16:16Speaker 01

  So this is 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, when I want to pick this up, I have the Exploration phase. Exploration phase is basically telling Claude, "We're gonna 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 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

• 17:00Speaker 01

  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 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 study materials and create interactive tests based on their own materials. So here, we can go to the top.

• 17:43Speaker 01

  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.

• 18:21Speaker 02

  Terrible results.

• 18:22Speaker 01

  Yeah, lucky.

• 18:23Speaker 02

  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 just like a thing you vibe coded, having no technical experience.

• 18:32Speaker 01

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

• 19:00Speaker 02

  I love it. Crossing, crossing your fingers this'll work. I just want, 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 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.

• 19:31Speaker 01

  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 slash command, and then it will be automated within the workflow.

• 19:54Speaker 02

  Amazing. So just to summarize the slash commands. So one is create an issue in Linear, which I love. Linear is awesome. Shout out.

• 20:02Speaker 01

  That's also from, yeah, the Product Pass.

• 20:04Speaker 02

  From the Product Pass. There you go. Oh my God, what a value. 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 explore the idea, help me ideate on what this could be. And this is Claude helping you think through the feature and product. 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.

• 20:44Speaker 01

  Yeah. Cool. So let's go ahead and start building. So I'm going to use Whisperflow to dictate. And basically, this starts with slash 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

• 21:19Speaker 01

  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 gonna ask me a few questions. Quizzes are 100% multiple choice. Question structure, single sentence, passage of two blanks and priority. So one and two are correct.

• 22:03Speaker 01

  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.

• 22:30Speaker 02

  And by the way, as this is loading, I just love 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 ask you questions. Here's the clarification.

• 22:43Speaker 01

  Yeah, so at first, when I was doing this with the CTO, I would do it with ChatGPT Voice Vote. And that was crazy. That was like, literally felt like ideating with a person. It would push back, ask questions. And maybe one day, you know, the coding tools will get there too. But that was exactly, it really felt like sitting with my CTO. Great, so created STU 88. So if we open up linear now, we should be able to see.

• 23:12Speaker 01

  Let's see where, STU 88, 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 codebase, 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 slash 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

• 23:56Speaker 01

  that is extra context for the AI. So I can say here, linear STU 88, which is referencing the ticket. And now what it's gonna do is it's gonna go, it's gonna fetch the linear ticket.

• 24:12Speaker 02

  And what's the idea, what's the goal of the exploration phase? This is kind of idea on the idea?

• 24:16Speaker 01

  Exactly. 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 codebase, what files need to be affected? And how is the best way to implement this technically? And usually what happens is right now Claude's just basically reading a bunch of files, understanding the basic structure of the code. And then it's gonna come back with a bunch of clarifying questions as that will decide how we end up implementing this.

• 24:44Speaker 02

  So it's like, it feels like it's talking to your engineering manager.

• 24:48Speaker 01

  Exactly, exactly, 100%. This is, this is how I think about it.

• 24:51Speaker 02

  And you said that your CTO, so you used to use ChatGPT prompt to have a CTO in there. Now the CTO is living inside here in Cursor.

• 25:00Speaker 01

  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, it's just a kind of 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.

• 25:19Speaker 02

  Got it. So basically it's Claude code. Is there like a prompt you gave it to act like that? To act like the right kind of CTO?

• 25:26Speaker 01

  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, yeah, within the Claude MD file.

• 25:47Speaker 02

  Cool. One last question before before we move on here, just because it's I'm thinking about it as this happens. The linear issue they generated, how often is it is it actually great and ready? How often do you have to edit it? What's like the quality of the linear ticket that it generates? Because, you know, a lot of people are like, probably wondering, just like, all these terrible linear issues are being created by AI. Are they actually any good?

• 26:08Speaker 01

  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 like, 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, it's they're they're pretty quality. And also, it just kicks off the when I want to start working on it. It's not, I wouldn't say it's ready to be built. It's ready to start being explored.

• 26:43Speaker 02

  Got it. So it's just the beginning of an idea. Actually, let's come back after we go through this flow, 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?

• 26:56Speaker 01

  Yeah, interesting.

• 26:57Speaker 02

  Let's come back to that.

• 26:58Speaker 01

  Cool. All right. So this is Claude coming back. I have a comprehensive understanding of the codebase. I thoroughly analyzed StudyMate Live codebase and understand the current system, feature requests, 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 codebase and 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 request,

• 27:39Speaker 01

  and what it has identified as key areas. And then it asked 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 happen 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.

• 28:08Speaker 02

  Awesome. I love it. And I love just scanning those questions it was asking. It's like such smart, sophisticated, important questions instead of just, "Cool, here I go. I'm going to build it."

• 28:18Speaker 01

  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 slash command that I haven't showed yet is learning opportunity, which basically when something is really difficult for me to understand, I'll do slash 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 architect, 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.

• 29:01Speaker 01

  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 slash create plan.

• 29:26Speaker 01

  And while Claude's 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's finished writing the plan. So we'll be able to look and see exactly what the plan is.

• 30:07Speaker 01

  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 super fast. 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 frontend. And then I'll have Gemini just read the plan and do the frontend. 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,

• 30:49Speaker 01

  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.

• 31:20Speaker 02

  Let me ask you a question while this is happening. 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's kind of limitation you ran into with those products and why you switched to Cursor?

• 31:42Speaker 01

  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, you know, 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.

• 32:26Speaker 01

  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,

• 33:10Speaker 01

  it's probably best to be on one of these tools.

• 33:12Speaker 02

  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?

• 33:20Speaker 01

  Yeah, for sure. Lovable, Bolt, Replit, Base44.

• 33:24Speaker 02

  V0.

• 33:25Speaker 01

  Yeah, V0, all same bucket.

• 33:27Speaker 02

  So essentially they're kind of, they're doing that planning for you. And as you said, they're very opinionated. They're trying 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.

• 33:48Speaker 01

  Yeah, I don't want this to come out like I'm badmouthing them. Base44, let's say. Yeah, yeah. 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 another way? It would just do it out of the box. So, so that's basically the trade-off there.

• 34:16Speaker 02

  Awesome. Shout out, uh, Mayor, the founder of Base44.

• 34:19Speaker 01

  Yeah, Mal Shomol.

• 34:21Speaker 02

  Yep.

• 34:22Speaker 01

  Yeah, yeah. He's amazing.

• 34:25Speaker 02

  I just love how this is, like, the way you're like, uh, flinging, what's the word, slinging, slinging models, like Gemini 3 for front, like, I love that you have, you've never written any code, and you're just like, cool, he's Gemini for this, and Claude for this, and I'm just working in Cursor, talking to this, uh, CTO, helping you build stuff, and build like, significant product.

• 34:47Speaker 01

  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 a 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 went from no domain, no nothing, to live, uh, on a domain within an hour and a half.

• 35:32Speaker 01

  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? 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 optimistic and hardworking.

• 36:08Speaker 02

  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, the rocket ship and just like, hey, here's this thing that I figured out. Here's where we're going.

• 36:20Speaker 01

  Yeah. Best time to be alive. Um, 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?

• 36:42Speaker 02

  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.

• 36:49Speaker 01

  For sure. Yeah, for sure. Now, a composer, like the one thing is it's just so, so blazing fast, keeps you in flow. So yeah, full features take minutes.

• 37:00Speaker 02

  And that probably costs like a couple bucks in AI credits.

• 37:04Speaker 01

  I don't even look. I mean, I used to be so stingy about paying for products. And now I'm just basically, I look at it all as tuition, you know, as like, uh, stuff that I'm paying for learning. So I don't know how much it costs, but it's definitely worth it.

• 37:18Speaker 02

  That explains why they're the fastest growing products in history.

• 37:21Speaker 01

  A hundred percent.

• 37:23Lenny Rachitsky?

  Your marketing website sets the tone for your brand and is the one touch point 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're doing something wrong. That is why so many companies from early stage startups to Fortune 500s, including companies like DoorDash, Zapier, Proplexity, and 11 Labs turn to Framer, the website. Site builder that turns your dot 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 A/B testing. Changes to your Framer site go live to the web in seconds with a single click and without any help from engineering.

• 38:07Lenny Rachitsky?

  Whether you want to launch a new site, test a few landing pages, or migrate your full dot 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.

• 38:33Speaker 01

  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.

• 38:56Speaker 02

  I love this because 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. And what you're doing here is you're having Claude review its own code.

• 39:08Speaker 01

  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 it first to make sure if I can see any mistakes that Claude made. And then what I'll do is basically slash review. And this tells Claude to start reviewing its own code.

• 39:37Speaker 01

  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 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 working with. And just to put this in a mental model, this is basically my dev lead that I'm working with. I will take, the slash command is basically saying, you're the dev lead on this project.

• 40:21Speaker 01

  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. Each model. Yeah, each model has such distinct characteristics. So let's say Claude, she would be the perfect CTO. Like, she's very communicative, she's very smart.

• 41:05Speaker 01

  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 like, it's your dream, a very communicative, but very opinionated dev lead.

• 41:25Speaker 01

  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 like 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? You're gonna tell us what happened? Or whatever. And it's like, don't worry about it. I fix 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.

• 42:10Speaker 01

  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 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, 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. 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, like the way there is like a roller coaster and very scary. But at the end of the day, Gemini is very good at design.

• 42:55Speaker 01

  So I think that using all these models 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, basically. Like 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, cool thing that I've added and I haven't seen many people doing it.

• 43:31Speaker 02

  That is such an incredible rant slash 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, what you learned there.

• 43:45Speaker 01

  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.

• 44:11Speaker 01

  Of course, Branch is referring to the GitHub branch that we're working on. We're not working on the live codebase. And then I'll do this with Composer. Say with, we can do, let's do it with Composer 1. So I'll do slash review here as well. And basically, these are both going to run and do an 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 darkroom right now reviewing code. And we'll come back in a few minutes.

• 44:54Speaker 02

  Okay, cool. 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 copy and paste kind of these results? Is that the idea?

• 45:03Speaker 01

  Exactly. I'll copy and paste the results. I'll do peer review and then I'll say devlead1 and then paste from one of the models. And then I'll say devlead2 and paste from the other model and basically have them fight it out until I feel like we have no more issues. For me, this is super important because I'm not a, not technical 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 don't fully grasp.

• 45:30Speaker 02

  Incredible. What a clever solution to solving this code review problem where it's like, I don't know what you're, I don't, I don't know how to recode. So what am I going to even? Yeah.

• 45:39Speaker 01

  Yeah.

• 45:39Speaker 02

  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 going to be available. People can just plug this stuff into their cursor account and use it themselves.

• 45:52Speaker 01

  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 kinds 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

• 46:36Speaker 01

  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 to 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, you know? 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, 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.

• 47:20Speaker 01

  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.

• 47:38Speaker 02

  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 with that knowledge so that in the future it's not making that same mistake. 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.

• 48:00Speaker 01

  Exactly. Not always the slash commands. It will sometimes update different documentation or its tooling, but basically it's it's understanding what the root cause of the of the mistake that the AI made and fixing it.

• 48:15Speaker 02

  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 that stuff.

• 48:25Speaker 01

  A hundred percent. Yep.

• 48:26Speaker 02

  Amazing. Okay. Um. Is there anything else there before I move in a couple of other directions?

• 48:31Speaker 01

  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. 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 going to 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 release the feature.

• 48:59Speaker 02

  It's incredible that this was not possible, like, I don't know, two years ago, maybe a year ago, like you were 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. Uh, this is like, we're so used to this now, but it's insane what is now possible.

• 49:29Speaker 01

  It's the best time to be alive. A hundred percent. 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.

• 50:14Speaker 02

  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 slash commands and basically this whole workflow with the audience.

• 50:34Speaker 01

  Yeah.

• 50:34Speaker 02

  Okay.

• 50:34Speaker 01

  And like I said, just start a GPT, start a GPT, um, 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 like, be inquisitive, learn. Don't rush things.

• 50:51Speaker 01

  It's very important to just dive in and, and really spend the time to learn.

• 50:55Speaker 02

  And you share 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 of how this database issue works.

• 51:04Speaker 01

  Exactly.

• 51:05Speaker 02

  Okay, there's a couple of directions I want to make sure we touch on. One is coming back to a question 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?

• 51:27Speaker 01

  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 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.

• 52:06Speaker 01

  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 going to see that a lot in the next coming years. I think basically everyone's going to become a builder. So should be really interesting.

• 52:25Speaker 02

  Okay. So your advice here is as a PM, don't. Maybe don't go rinse a 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?

• 52:42Speaker 01

  If there are PMs.

• 52:45Speaker 01

  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

• 53:29Speaker 01

  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.

• 53:43Speaker 02

  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. Now it's actually not at all good. Or these linear tickets are 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 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, meh, it's just a bunch of AI generated slop?

• 54:25Speaker 01

  I have a very strong disagree to this, and I've heard it a bunch. I remember when I started using, Tal Aviv has like this whole course on, on building a PM co-pilot using projects, which is probably one of the best courses that you can take. And when I started working with my own co-pilot, 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.

• 55:08Speaker 01

  I think that there is 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, 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.

• 55:53Speaker 01

  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. Like, 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, I mean, on my side product, I can just do whatever decisions I want,

• 56:37Speaker 01

  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 you know, how do you you outsource certain stuff and you're not owning a hundred percent 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.

• 57:03Speaker 02

  Is there anything that you've learned about reducing the the sloppiness, the sloppiness of the output? Just like a tip for keeping the quality high of the stuff that it produces?

• 57:13Speaker 01

  Similar to people setting up AI for success for the task at hand. So like if I just brought in, you know, 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 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 slash command called dslp,

• 57:58Speaker 01

  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, no slop is is left behind.

• 58:12Speaker 02

  That is so funny. Dslp. Okay. One more question, which may lead to something else, but I'm 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?

• 58:37Speaker 01

  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 child now, when you say, how do you answer the phone? They'll they'll do this. You know, they'll do the the iPhone answer. And I feel like people who are 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 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.

• 59:23Speaker 01

  I took a ton of frameworks and 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.

• 1:00:04Speaker 01

  So basically, 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 human mocks. So cold outreach 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, there's no way to get around that.

• 1:00:38Speaker 02

  That is so cool they use 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 mocks online. 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 in collaboration with Gnome 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. Here's what you, 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.

• 1:01:21Speaker 01

  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 Lewis Lin, which basically is an always updating bank of questions that people are asked in real interviews. And I basically used Comet, which is the perplexities 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. 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.

• 1:02:07Speaker 01

  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.

• 1:02:20Speaker 02

  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 and help me prepare for this thing, help me figure it out.

• 1:02:32Speaker 01

  Yeah.

• 1:02:33Speaker 02

  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, it's for a long time, it's you'll be replaced by someone who's better at using AI than you.

• 1:02:47Speaker 01

  I agree.

• 1:02:48Speaker 02

  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 and start to learn how to get there yourself. Okay, Zebby, 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, 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 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?

• 1:03:26Speaker 01

  Yeah, I love this. I love this. I love Failure Corner. Big, big fan. So I'll tell a story about when I started at Wix. So basically, I started within Wix's 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. Like, 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 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.

• 1:04:07Speaker 01

  I would work tons of hours alone, and I was like, I'm gonna kill this product review. They're gonna 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, when it was over, I was like, ah, you're such an idiot. And I saw that. Everyone was like, alright, 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 shifted. And I think this is probably the best tip that I give now to junior PMs is basically,

• 1:04:52Speaker 01

  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 use them as a mentor for that. So Nari, who was still my mentor till today, he has the best product sense of anyone I've met. Oh, yeah, is super, she's like a methodology export expert. She just thinks in frameworks. 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 and consult them. And this does two things. First of all, I learned a ton. And the second thing is that

• 1:05:37Speaker 01

  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 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.

• 1:05:57Speaker 02

  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, learning opportunity slash 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?

• 1:06:25Speaker 01

  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 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, you know, 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? You know, on your own with a couple of friends, completely bootstrapped. And I see more and more people towards the end of the time, my time at Wix, I was interviewing.

• 1:07:08Speaker 01

  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.

• 1:07:43Speaker 02

  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?

• 1:07:52Speaker 01

  Yep, let's do it.

• 1:07:54Speaker 02

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

• 1:07:58Speaker 01

  So I'll, I'll take one from each kind of genre. So in like fiction, I love The Fountainhead by Ayn Rand, one of my favorite books. Really makes you think, really makes you feel.

• 1:08:11Speaker 01

  Business books, I'm a big fan of Shoe Dog, The Nike Story.

• 1:08:14Speaker 02

  I just finished reading that, so.

• 1:08:17Speaker 01

  Amazing.

• 1:08:17Speaker 02

  This is great, this is great.

• 1:08:18Speaker 01

  Yeah, I love Shoe Dog. And then more on like 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, you understand that it's completely psychological and, 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.

• 1:08:51Speaker 02

  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?

• 1:09:02Speaker 01

  Yeah, actually my, my wife is really into film, so we watch a lot of TV. It's probably our, our favorite together time. I just finished watching The Pit, which was amazing. 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.

• 1:09:20Speaker 02

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

• 1:09:24Speaker 01

  This is a good question. I'm always trying new products, like 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 like. Really sweating to the details and it's just a really, really great alternative. So I've been using that recently.

• 1:09:58Speaker 02

  There's also a product called Supercut that I love. That's also a Luma 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?

• 1:10:09Speaker 01

  Yeah, I'm kind of between two right now. One, which has like become a Twitter meme, basically, which is you can just do things. I feel like that is basically going all ways in my head. Every time I do something that I'm just shocked at the speed 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 kind of makes you take life more lightly. Uh, so yeah, nobody knows what the fuck they're doing.

• 1:10:39Speaker 02

  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 the ballpark. Yeah. Okay, last question. You've been, 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.

• 1:11:12Speaker 01

  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, for one of my sister's friends or something. And basically it was just packs of thermal clothing, 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.

• 1:11:55Speaker 01

  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 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, 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 and a half dollars apiece. So I was making like 100% profit.

• 1:12:40Speaker 01

  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, 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 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 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.

• 1:13:25Speaker 01

  So that was just a really cool experience, um, as a kid.

• 1:13:29Speaker 02

  This explains so much. Such a, just a 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, 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?

• 1:13:50Speaker 01

  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 really love to help whoever I can. How can you use, uh, 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're not using dictation yet, try Deporta Text, tell me what you think.

• 1:14:13Speaker 02

  Amazing. Uh, I just love how much, how much you're giving away and how useful that's gonna 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 gonna help, I think, a lot of people. And I think it's gonna 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, uh, thank you so much for being here and for sharing so much.

• 1:14:35Speaker 01

  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.

• 1:14:43Lenny Rachitsky?

  Amazing. Zebby, thank you so much for being here.

• 1:14:45Speaker 01

  Thank you.

• 1:14:46Lenny Rachitsky?

  Bye, everyone.

• 1:14:48Lenny Rachitsky?

  Thank you so much for listening. If you found this valuable, you can subscribe to the show on Apple Podcasts, 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.