The non-technical PM’s guide to building with Cursor | Zevi Arnovitz (Meta) (1h 15m)

ai-driven-innovation-economy

ai-in-skill-development

ai-in-workforce-disruption

ai-literacy-public-awareness

ai-driven-innovation-economy ai-in-skill-development ai-in-workforce-disruption ai-literacy-public-awareness

Release date: 2026-01-18
Listen on Spotify: Open episode

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:The complete AI workflow that lets non-technical people build real products in CursorHow to use multiple AI models for different tasks (Claude for planning, Gemini for UI)Using slash commands to automate promptsZevi’s “peer review” technique, which uses different AI models to review each other’s codeWhy this might be the best time to be a junior in tech, despite the challenging job marketHow Zevi used AI to prepare for his Meta PM interviews—Brought to you by:10Web—Vibe coding platform as an APIDX—The developer intelligence platform designed by leading researchersFramer—Build better websites faster—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• 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 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...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 podcast@lennyrachitsky.com.—Lenny may be an investor in the companies discussed.

Summary

🚀 Superpowers for Non-Tech Builders: Non-technical PMs like Zevi can now solo-build revenue apps using Cursor/Claude, from ideation to deployment, via shareable slash command workflows.
🔄 Structured AI Workflow: Key steps: /createissue in Linear, explore/plan/execute/review/peer-review with multi-models, and update docs—fully demonstrated live.
🤖 Multi-Model Code Review: Claude, Codex, and Composer review each other’s code as ‘dev leads,’ catching bugs non-experts miss and enabling trust in AI outputs.
📈 Gradual Onboarding & Learning: Start with GPT ‘CTO’ projects for exposure therapy, use /learningopportunity for 80/20 explanations, iterate via postmortems.
🌟 Future: Everyone Builds: Juniors thrive launching startups; PM roles evolve to shipping code in AI-native teams; best time to be curious and hardworking.

Insights

Can non-technical product managers now build and ship real products solo using AI tools?

Time: 0:00 – 2:23

Category: AI in Workforce Disruption

Answer: Zevi, a non-technical PM at Meta, demonstrates building a full-featured app like StudyMate using Cursor and Claude without writing code, from ideation to deployment. This unlocks superpowers for ambitious non-coders, enabling weekend projects that generate revenue and complex features like drag-and-drop quizzes. It democratizes building, making everyone a potential builder. (Start at 0:00)
Is this the best time in history for juniors to launch startups without technical skills?

Time: 0:59 – 1:05

Category: AI-Driven Innovation Economy

Answer: Zevi argues AI tools enable fresh grads to solo-build revenue-generating apps like StudyMate, collapsing titles and responsibilities as ‘everyone becomes a builder.’ Juniors gain unfair advantages in speed and iteration, outpacing traditional paths amid junior role scarcity. It flips narratives on entry-level job markets. (Start at 0:59)
Should non-technical people start with GPT projects before diving into code editors like Cursor?

Time: 7:56 – 13:49

Category: AI Literacy & Public Awareness

Answer: Zevi recommends ‘exposure therapy’ via ChatGPT projects as a ‘CTO’ for planning and learning, avoiding premature code terror, then graduating to Bolt/Lovable and Cursor. This gradual approach builds confidence, context awareness, and technical intuition through conversation. It prevents bugs from rushed coding agents. (Start at 7:56)
How can slash commands in Cursor turn AI into a structured CTO for product development?

Time: 14:47 – 20:44

Category: AI-Driven Innovation Economy

Answer: Zevi’s workflow uses custom slash commands like /createissue, /exploration-phase, /createplan, /execute, /review, and /peer-review to guide AI through ideation, planning, building, and reviewing code. This mimics a technical co-founder, starting from Linear issues to documentation updates, ensuring robust development even for code-fearful users. It provides a copyable template for others to replicate. (Start at 14:47)
Why is having multiple AI models review each other’s code a game-changer for non-technical builders?

Time: 38:52 – 45:40

Category: AI in Workforce Disruption

Answer: Zevi pits Claude against Codex and Composer in peer reviews, treating them as dev leads who ‘fight it out’ over bugs, leveraging each model’s strengths like Claude’s communication or Composer’s speed. This catches issues a single model misses, building trust in AI-generated code without personal expertise. It’s an innovative solution to the code review bottleneck. (Start at 38:52)
How does constant AI postmortems supercharge productivity for builders?

Time: 45:56 – 48:24

Category: AI in Skill Development

Answer: After bugs or failures, Zevi prompts AI to introspect on prompt/tooling flaws, then updates docs and slash commands to prevent repeats, turning setbacks into permanent improvements. This iterative refinement divides casual AI users from experts, akin to engineering postmortems. It ensures workflows evolve with each project. (Start at 45:56)
Can PMs at large companies start shipping UI code today with AI-native codebases?

Time: 51:27 – 53:34

Category: AI in Workforce Disruption

Answer: Zevi advises making codebases AI-friendly with markdown guides for navigation, allowing PMs to prototype contained UI features, create PRs for dev polish. While not for heavy migrations, it fosters collaboration and previews a future where PMs build directly. Teams investing now gain massive leads. (Start at 51:27)