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

AI-generated code still needs a process for resolving defects and conflicting feedback. Product manager Zevi Arnovitz describes testing the app manually first, then asking several AI systems to review the code. He returns their findings to the agent leading implementation and asks it to fix valid issues or explain why a criticism is mistaken. The extra reviews supply challenges to investigate, while manual testing checks the behavior he can observe. His workflow gives a builder with limited coding experience several opportunities to catch problems, without establishing that model agreement proves correctness.

“It basically felt like someone came up to me and said, you have superpowers now.”

Zevi Arnovitz

“If you're non-technical, like me, code is terrifying, but AI just makes so much possible.”

Zevi Arnovitz

“It's not that you will be replaced by AI, you'll be replaced by someone who's better at using AI than you.”

Zevi Arnovitz

“I think titles are gonna collapse and responsibilities are gonna collapse and everyone's just gonna be building.”

Zevi Arnovitz

“I've learned over time that updating documentation and tooling is one of the biggest hacks for productivity.”

Zevi Arnovitz