Essays on AI, engineering and Rails
Honest takes on code, AI, and what actually works
-
Latest ·
·
5–7 minutesThe Rise of Wasteful Resources
Read essay →: The Rise of Wasteful ResourcesWe used to be proud of making things small. Now the default is to throw more tokens, more context and more compute at every problem. Why AI waste became normal, what it really costs, and how to get the craft…
Recent essays
-
ADD in Context: Greenfield, Legacy, Refactoring, and Testing
The ADD cycle is consistent across contexts: Specify, Generate, Evaluate, Integrate. But how you apply each phase changes depending on what you are building and where you are building it. Greenfield projects…
-
WebMCP Is Coming: How AI Agents Will Reshape the Web
On February 10, 2026, the Chrome team quietly published a blog post announcing something called WebMCP. It was framed as an “early preview,” tucked behind a feature flag in Chrome 146. If…
-
No, Average People Will Not Build Their Own Software With AI
There is a narrative gaining traction in tech circles, on social media, and in breathless conference keynotes that goes something like this: AI will soon let anyone build their own software. Need…
-
Full-Time CTO vs. Fractional: The Real Math Nobody Shows You
Every startup founder eventually faces the same inflection point. The product is gaining traction. Technical decisions are getting more complex. Investors are asking who’s driving the technology strategy. The board wants a…
-
Architect or Extinct: Why Software Developers Must Evolve Beyond Writing Code
A house architect does not lay bricks. They do not mix concrete, install plumbing, or wire electrical panels. They design the building. They decide how spaces connect, where light enters, how loads…
-
Integrate: Completing the ADD Cycle for AI-Driven Development
Code that passes evaluation is ready for integration. This is the final phase of the ADD cycle, where generated code becomes part of your system. But integration is more than merging a…
-
Evaluation Checklists: Building Your Quality Gate for AI Code
In the previous post, I covered the five dimensions of evaluating AI-generated code: correctness, fitness, security, performance, and maintainability. Understanding these dimensions is essential. But understanding is not enough. Under time pressure,…
-
You Don’t Want a Claude Code Guru
The job posting practically writes itself these days. “Looking for a senior developer proficient with AI coding tools. Must be comfortable using Claude Code, Cursor, or Copilot to rapidly produce production-ready code.…
-
An Honest Take on Deploying Rails with Kamal: What Works and What Doesn’t
Kamal has been positioned as the answer to a question Rails developers have asked for years: how do you deploy to your own servers without the overhead of Kubernetes or the cost…
Work with me
AI-driven development, Rails and engineering leadership. See what I do and how we can work together.