GenAI
Every coding agent already has a harness
People keep asking whether harness engineering is worth doing. I think that question starts one layer too late. If you…
Technology
GenAI
WTF does code quality mean when humans stop reading the code?
I have been using AI to write code since GPT and Claude 3.5 Sonnet made it useful enough for real…
Technology
Best practices for writing unit tests
Unit tests should work like a safety net, but they often end up becoming a problem. Fragile tests, tied to…
Technology
What Is Context Engineering and How to Apply It in Real Systems
An AI code assistant generates a function to handle user uploads. The code looks correct, compiles, and passes all tests.…
Leadership
Context Engineering vs Prompt Engineering: the shift in how we build AI systems.
You receive a pull request coming from an AI. The code looks clean, follows the prompt, and all unit tests…
Leadership
Gradual Rollouts in Software: How to Ship Safely with Feature Flags (2026)
Shipping a large change to a production system with a big user base creates a very familiar kind of stress.…
Leadership
Implementing Domain-Driven Design in a Growing Company
At a certain stage of growth, the codebase stops making intuitive sense. Logic that used to be simple becomes spread…
Leadership
Dealing with legacy code in modern applications
A new feature request lands, and you realize it has to touch the old permissions module. The project planning meeting…
Code Review
The limitations of using only Claude for code security review
The first time you see an AI comment on a pull request, the feedback loop stands out. A full review…