Skip to main content
Hilary Gridley shows how non-technical PMs can interrogate codebases to understand technical complexity and avoid being the engineering team’s least favorite PM. She loads a GitHub repository for MS Paint into Cursor and sets the context: “I’m going to be a PM. I’m going to ask you some questions, and I want you to answer those as if you are a knowledgeable and product minded engineer who is excellent at communicating with non-technical stakeholders.” She asks: “What are some feature upgrades that I, as a PM, would be really excited about implementing that my engineering team would find challenging for reasons that are not obvious to me?” The response reveals hidden complexity. Layer support seems simple but involves state management, memory optimization, and undo/redo complexity. Real-time collaborative editing seems straightforward but requires conflict resolution, network handling, and state synchronization. “I really appreciate it goes through and explains the types of complexity,” Hilary notes. “You could sit down and ask an engineer these questions, and you should. Help me understand if it’s right or wrong, so you’re not just taking it at face value.” ➡️ Load any codebase into Cursor and ask it to explain complexity like a patient engineer would. You’ll finally understand why “simple” features aren’t simple and can have informed conversations about tradeoffs.

​
Let’s build together

If you’re reading this, you’re in the top 5% of people leaning into AI agents for real work (even if it doesn’t feel that way, trust me). To go deeper, join me for a live, hands-on workshop. To get your team on board, book an AI build sprint.

​
Get notified about future posts

Subscribe