scripod.com
The non-technical PM’s guide to building with Cursor | Zevi Arnovitz (Meta)

Overview

Shownote

Highlights

Transcript

Chapters

Pins

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

Lenny's Podcast: Product | Career | Growth

Jan 18
Lenny's Podcast: Product | Career | Growth

Lenny's Podcast: Product | Career | Growth

Jan 18
OverviewShownoteHighlightsTranscriptChaptersPins

Shownote

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 co...

Highlights

In an era where AI is reshaping how software is built, non-technical professionals are gaining unprecedented power to create real products. This episode dives into the practical strategies that enable product managers without coding backgrounds to design, develop, and ship applications using cutting-edge AI tools.
13:26
Code is just words and files; projects can move across apps.
14:42
The 'create issue' slash command captures bugs or features directly in the codebase for later tracking in Linear
23:15
Claude reads the codebase and asks targeted questions to refine the development plan.
35:53
Cursor Composer can build full-featured apps in minutes compared to human engineers' weeks
38:33
Using Claude to review its own code, alongside tools like Codex and Cursor, improves code quality.
40:40
Claude is like a communicative and opinionated CTO, Codex a non-communicative problem-solving coder, and Gemini an artsy yet erratic designer.
43:37
Use '/learning opportunity' to understand unfamiliar coding concepts during review
45:40
When AI makes a mistake, ask it to reflect on the root cause and update your processes accordingly.
51:05
In a few years, everyone may become a builder as AI models improve.
53:43
Using AI intentionally allows junior PMs to operate at a higher level and gain valuable experience.
57:03
Use context and style guidance to improve AI results, similar to managing a junior colleague.
1:00:54
One may be replaced by those better at using AI in interviews.
1:04:00
He changed his mindset to become a '10X learner' and sought mentorship from experienced PMs
1:09:01
Nobody knows what the fuck they're doing

Chapters

Introduction to Zevi Arnovitz
00:00
Zevi’s background and journey into AI
04:48
Overview of Zevi’s AI workflow
07:41
Screenshare: Exploring Zevi’s workflow in detail
14:41
Building a feature live: StudyMate app
17:18
Executing the plan with Cursor
30:52
Using multiple AI models for code review
38:32
Personifying AI models
40:40
Peer review process
43:37
The importance of postmortems
45:40
Integrating AI in large companies
51:05
How AI has impacted the PM role
53:42
How to improve AI outputs
57:02
AI-assisted job interviews
58:15
Failure corner
1:02:57
Lightning round and final thoughts
1:06:20

Transcript

Lenny Rachitsky: You are a product manager shipping product without knowing how to write code, barely knowing how to review code. Zevi Arnovitz: I have zero technical background. Did music in high school when ChatGPT 3.5 came out. I remember watching a Yo...