Skip to content
Lenny's PodcastLenny's Podcast

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

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

Lenny RachitskyhostZevi Arnovitzguest
Jan 17, 20261h 15mWatch on YouTube ↗

At a glance

WHAT IT’S REALLY ABOUT

A non-technical Meta PM builds and ships using AI workflows

  1. Zevi Arnovitz, a Meta PM with no technical background, demonstrates how he builds and ships real product features without writing code by relying on a structured AI workflow in Cursor.
  2. His system centers on reusable “slash commands” that turn product ideas into Linear issues, guide an exploration phase, generate an implementation plan, execute it with AI coding agents, and then run multi-model code review.
  3. To mitigate risks (especially code review), he pits different models (Claude, Codex, Gemini) against each other via “peer review,” and continuously improves prompts/documentation through postmortems.
  4. He argues AI doesn’t replace thinking—if used intentionally, it accelerates learning and enables juniors to build faster, gain reps, and even prepare effectively for high-stakes interviews like Meta’s.

IDEAS WORTH REMEMBERING

5 ideas

Use a staged workflow to prevent “AI jumps straight to code” failures.

Zevi found tools like Bolt/Lovable overly eager to code without sufficient planning. His workflow forces a deliberate sequence—capture → explore → plan → execute—so complexity (payments, DB changes, prompts) doesn’t spiral into bugs.

Start with “compartmentalized” AI contexts to avoid polluted memory and bad advice.

He recommends Projects (ChatGPT/Claude) to separate domains (running vs. PM work vs. coding). This improves relevance and makes AI feel like a dedicated “CTO” rather than a generic, mixed-context assistant.

Slash commands turn good prompting into a scalable operating system.

He saves reusable prompts inside the repo (e.g., create issue, exploration phase, create plan, execute plan, review, peer review, update docs). This reduces cognitive load and makes consistent quality repeatable across features.

Automate fast idea capture into Linear to protect flow.

When a bug/idea appears mid-build, his “create issue” command asks minimal clarifying questions and generates a structured Linear ticket via MCP tooling—good enough to resume later, not “final spec” perfection.

Treat exploration as an engineering-style discovery phase, not ideation fluff.

In exploration, Claude reads the codebase, identifies affected files, and asks sophisticated scope/data/UX/grading/prompt questions. This is how Zevi avoids “vibe coding” pitfalls and builds more production-ready changes.

WORDS WORTH SAVING

5 quotes

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

— Zevi Arnovitz

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

Code is terrifying… I look at it as kind of like exposure therapy.

— Zevi Arnovitz

It’s very difficult for me to catch mistakes… I will have each of them review the code.

— Zevi Arnovitz

I think titles are gonna collapse, and responsibilities are gonna collapse, and everyone’s just gonna be building.

— Zevi Arnovitz

Non-technical PMs building with AICursor + Claude Code workflowSlash commands as reusable promptsLinear issue capture via MCPExploration → plan → execution pipelineMulti-model code review and “peer review”Postmortems, documentation, and AI-native codebasesAI for interview preparation and mock feedback“Titles collapsing” and future of PM work

High quality AI-generated summary created from speaker-labeled transcript.

Get more out of YouTube videos.

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

Add to Chrome