The non-technical PM’s guide to building with Cursor | Zevi Arnovitz (Meta)
🤖 AI Summary
Overview
This episode features Zevi Arnovitz, a non-technical product manager at Meta, who has mastered the art of building and shipping sophisticated products using AI tools like Cursor. Zevi shares his complete workflow, which empowers non-technical individuals to create real products, leveraging multiple AI models and innovative techniques like peer reviews. He also discusses how AI can be a game-changer for junior professionals and shares insights into using AI for job interview preparation.
Notable Quotes
- It's not that you will be replaced by AI, you'll be replaced by someone who's better at using AI than you.
– Lenny Rachitsky
- If people walk away thinking how amazing you are, you've failed. If people walk away and open their computer and start building, you've succeeded.
– Zevi Arnovitz, on inspiring others to take action.
- Titles are going to collapse, and responsibilities are going to collapse. Everyone's just going to become a builder.
– Zevi Arnovitz, on the future of work in tech.
🚀 Building Products as a Non-Technical PM
- Zevi uses Cursor, an AI-powered coding tool, to build products without writing code.
- His workflow includes creating reusable slash commands for tasks like creating issues, exploring ideas, planning, executing, reviewing, and updating documentation.
- He emphasizes starting with simpler tools like ChatGPT before graduating to more advanced platforms like Cursor.
- Zevi’s workflow includes using multiple AI models for different tasks: Claude for planning, Gemini for UI design, and Codex for debugging.
🤝 Peer Review with AI Models
- Zevi employs a unique peer review
process where different AI models review each other’s code.
- He uses slash commands to prompt one AI model to critique another’s work, ensuring higher code quality.
- Each AI model is treated as a team member with specific strengths: Claude as the collaborative CTO, Codex as the reclusive coding expert, and Gemini as the creative designer.
📚 AI as a Learning Partner
- Zevi uses AI not just for execution but as a learning tool. His learning opportunity
slash command prompts AI to explain technical concepts in a digestible way.
- He views AI as a mentor, helping him understand complex topics and improve his skills as a PM.
- Zevi believes that AI allows junior professionals to gain experience and operate at a higher level than traditionally possible.
🎓 Using AI for Job Interview Preparation
- Zevi used AI to prepare for his Meta PM interviews by creating a project in Claude that acted as his coach.
- He conducted mock interviews with AI, received feedback, and even built a quiz game to practice segmentation questions.
- He combined AI preparation with human mock interviews for a comprehensive approach.
🌟 Why This is the Best Time to Be a Junior in Tech
- Zevi argues that despite a challenging job market, AI tools enable juniors to build startups or side projects independently, gaining valuable experience.
- He encourages leveraging AI to learn, experiment, and create, emphasizing that curiosity, optimism, and hard work are key to thriving in this era.
- Zevi highlights the importance of being a 10X learner
rather than a 10X doer,
especially for those early in their careers.
AI-generated content may not be accurate or complete and should not be relied upon as a sole source of truth.
📋 Episode Description
Zevi Arnovitz is a product manager at Meta with no technical background who has figured out how to build and ship real products using AI. His engineering team at Meta asks him to teach them how he does what he does. In this episode, Zevi breaks down his complete AI workflow that allows non-technical people to build sophisticated products with Cursor.
We discuss:
1. The complete AI workflow that lets non-technical people build real products in Cursor
2. How to use multiple AI models for 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
DX—The developer intelligence platform designed by leading researchers
Framer—Build better websites faster
—
Episode transcript: https://www.lennysnewsletter.com/p/the-non-technical-pms-guide-to-building-with-cursor
—
Archive of all Lenny's Podcast transcripts:
—
Where to find Zevi Arnovitz
• X: https://x.com/ArnovitzZevi
• LinkedIn: https://www.linkedin.com/in/zev-arnovitz
• Website: 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 i