3 posts
Dumping the whole corpus into an AI agent makes it worse, not better. The fix is architectural: each task loads a curated slice, not everything you have. Here is the method, and the same move at three different layers: specs, sensor data…
Spec-driven development reads like a methodology for controlling AI agents. It isn't. It's a methodology for managing context across stateless sessions. The spec is the persistent memory.
Why spec-driven development and structured folder architecture are the missing infrastructure for AI-assisted engineering: methodology, common mistakes, and where to start.