About

The AI Toolkit for Product Engineers

The tools that let one developer do the work of a team


The difference between a developer and a product engineer often comes down to leverage. How much can you accomplish with the time you have? The right AI toolkit doesn’t just make you faster—it expands what’s possible.

Here’s what’s working right now.

Coding: Claude and Cursor

Forget autocomplete. The new generation of AI coding tools understand context, architecture, and intent. Claude Code operates directly in your terminal, reading your codebase and making changes across multiple files. Cursor embeds similar capabilities right in your editor.

The key insight: these tools are most powerful when you treat them as a junior developer who’s very fast but needs clear direction. Be specific about what you want. Review what they produce. Guide them toward your codebase’s patterns.

Design: v0 and Figma AI

v0 from Vercel turns descriptions into working UI components. It’s not perfect, but it’s remarkably good at getting you 80% of the way there. For product engineers who aren’t designers, this is transformative. You can prototype ideas in minutes instead of waiting for design resources.

Figma’s AI features are catching up fast, letting you generate variations, resize intelligently, and maintain consistency across components.

Research and Strategy: Claude, Perplexity, NotebookLM

Before you build anything, you need to understand the problem space. Claude excels at synthesizing complex information and helping you think through product decisions. Perplexity is your research assistant for competitive analysis and market understanding. NotebookLM turns your collected research into an interactive knowledge base.

Deployment: Vercel, Cloudflare, Railway

The infrastructure layer has gotten so good that deployment is nearly invisible. Vercel and Cloudflare Pages deploy on git push. Railway handles backends with minimal configuration. You’re not fighting infrastructure anymore—you’re just shipping.

The Meta-Skill

The real skill isn’t mastering any single tool. It’s knowing when to use which one, and how to chain them together effectively. Start with Claude to think through the problem. Use v0 to prototype the interface. Move to Cursor to build it properly. Deploy to Cloudflare and iterate.

The developers who thrive in this era won’t be the ones who know every tool deeply. They’ll be the ones who know how to orchestrate AI toward a coherent product vision.