Commentary

In “Don’t Automate Your Moat,” I argue that engineering organizations should match AI autonomy to two independent dimensions: business risk and competitive differentiation. I used AI Gateway cost controls as a worked example throughout the piece because a single feature touches all four quadrants depending on which piece you’re building. A piece making that argument […]

In “Don’t Automate Your Moat,” I argue that engineering organizations should match AI autonomy to two independent dimensions: business risk and competitive differentiation. I used AI Gateway cost controls as a worked example throughout the piece because a single feature touches all four quadrants depending on which piece you’re building. A piece making that argument

Everyone is adopting AI coding tools. Engineers are writing code faster than ever. But are organizations actually delivering value faster? That’s not obvious. I wrote Enabling Microservice Success with a big focus on engineering enablement, guardrails, automated testing, active ownership, and light touch governance. I didn’t know AI coding agents were coming, but it turns

The release of Gemma 4 has added energy to the discussion of local models and their importance. Models that you can download and run on hardware you own are becoming competitive with the “frontier models” hosted by large AI providers. These models have gotten good enough for production use, good enough for tasks that until

This is the fifth article in a series on agentic engineering and AI-driven development. Read part one here, part two here, part three here, and part four here. I recently had a taste of humility with my AI-generated code. I live in Park Slope, Brooklyn, and recently I needed to get to the other side of the neighborhood.

I was talking to a senior engineer at a well-funded company not long ago. I asked him to walk me through a critical algorithm at the heart of their product, something that ran hundreds of times a second and directly affected customer outcomes. He paused and said, “Honestly, I’m not totally sure how it works.

We tend to assume that if every part of a system behaves correctly, the system itself will behave correctly. That assumption is deeply embedded in how we design, test, and operate software. If a service returns valid responses, if dependencies are reachable, and if constraints are satisfied, then the system is considered healthy. Even in

We tend to assume that if every part of a system behaves correctly, the system itself will behave correctly. That assumption is deeply embedded in how we design, test, and operate software. If a service returns valid responses, if dependencies are reachable, and if constraints are satisfied, then the system is considered healthy. Even in