Blog

This project started with a missing tool.

AI has dramatically changed how software gets written.

I recently listened to The Tim Ferriss Show episode #843, “Tactics and Strategies for a 2026 Reboot,” featuring Greg McKeown, the author of Essentialism. My biggest takeaway was simple but sticky:

Coding with AI is the new normal. Reviewing AI-written code is the new bottleneck.

This past Saturday, our team spent the day on-site at Community First! Village swinging hammers, raising walls, and learning from the community. It was energizing and a good reminder that the goal isn’t just to fund a house, it’s to help build a home for someone who doesn’t currently have one.

AI is changing how product teams work, from the way we discover opportunities to how we deliver features. The fastest teams today are AI forward: they use AI to validate ideas quickly, generate working prototypes, and ship production-ready code with strong guardrails.

Modern AI tools are transforming how we write, review, and ship code — but the real magic happens when you connect them into a structured, repeatable workflow.

Unlike traditional approaches that rely on iterative back-and-forth conversations with AI, Context Building invests time upfront to create a "perfect" context that equips the AI with everything it needs to generate accurate, actionable solutions immediately.

A couple of weeks ago, I wanted to test the bounds of agentic AI development workflows just as a fun exploration. I’d seen plenty of demos and played with a few basic examples, but this was my first real experiment to see if AI could handle meaningful dev work from start to finish. Short answer: it can (kinda - with some caveats). The process was as fascinating as the results.

If you want your AI coding assistant to actually “get” your project, great rules are non-negotiable. But writing effective Cursor rules isn’t just about dumping a list of do’s and don’ts—it’s about structure, clarity, and showing real patterns that match how your team works.

There’s something special about winding down with smart people, talking shop and life. Tonight, I got to catch up with Spencer, a dev who worked on some of my old projects after I left Razorfish. It was surreal to hear those projects were still in use. We talked about the tech behind them and the people who shaped my early career — things I built with Lauren Zugai (now at Firefox) and systems originally architected by my mentors, David Hezlep and Brad Tippet. It turned into a night of sentimental reflection, which got me thinking about just how far I’ve come.