Sqlhammer

Fully autonomous AI code generation is the future… for certain types or work. In my Calibrate Autonomy to Stakes article, I talk about the two variables for deciding how autonomous to make your code generation; stakes and reversibility. In this article, w

The largest productivity gain available from AI is not the one most leaders are measuring. Personal speedups, the 20 to 30 percent lift on your own keyboard, are the floor. Two altitudes above that, in the team's workflow and in the product your customers

The most expensive decision in an agentic system is not which model you run. It is how you divide the work. The industry's first instinct was to specialize. Borrow the lesson from microservices, shatter the monolith, give each agent a single narrow respon

Your team is shipping faster than ever. The question is whether they understand what they shipped. Comprehension debt is the growing gap between code volume and genuine developer understanding. It accumulates silently: CI passes, velocity metrics climb, s

First Principles of AI Usage - Part 9 AI is a multiplier. The thing it multiplies is you. That framing has a sharp implication most teams prefer not to confront: multiplying a strong foundation produces outsized returns; multiplying a weak one produces ou

First Principles of AI Usage - Part 8 AI produces fluent output. That is the problem. When an AI response is well-structured, confidently phrased, and grammatically clean, it reads like a finished artifact. The temptation is to accept it as one. MIT Sloan

First Principles of AI Usage - Part 7 Constraints make AI better. This is counterintuitive. Most teams assume that giving an AI system more access, more context, and more freedom produces better results. The opposite is true. An AI with clear boundaries,

First Principles of AI Usage - Part 6 Ninety percent of engineering teams now use AI. Only 23% extract meaningful productivity gains from it. That gap is not a tooling problem. The teams in the 23% are not running better models or allocating larger budget

First Principles of AI Usage - Part 5 I asked an AI agent to build a procedurally generated terrain system for a Godot video game. I gave it a comprehensive requirements list. It built one. The code ran, the terrain rendered, and it was more effective to

First Principles of AI Usage - Part 4 Amazon's Kiro AI agent caused a 13-hour AWS outage by deleting and recreating a production environment. The AI did not go rogue. It did not hallucinate. It executed the action it was authorized to take. The engineer's