sqlew

Why Claude Code Is Chosen: The "Harness" Perspective on AI Coding

When choosing an AI coding tool, most developers first look at the LLM's capability — how smart the model is, how accurately it generates code. That's certainly…

Decision and Constraint: How sqlew's Dual Records Transform AI Reasoning Patterns

Recent research suggests that ADR (Architecture Decision Record) can dramatically improve the reasoning efficiency of coding agents. But in traditional ADR, two…

Is Your CLAUDE.md Just a Mission Statement on the Wall?

You keep adding rules to CLAUDE.md — coding standards, architecture policies, naming conventions, testing guidelines. Before you know it, it's hundreds of lines…

AI Fills the Gaps: How Incomplete Design Intent Triggers Over-Implementation

Recording design intent and feeding it to AI improves code quality. Our experiments confirmed this. But they also revealed something less intuitive. When desig…

Why AI Ignores Your "Use TDD" Instruction: The Compliance Gap Between Instruction and Rationale

You wrote "Use TDD" in CLAUDE.md, but the AI doesn't write tests. Or it writes them, but they're clearly going through the motions. If you've tried pr…

Recording Design Intent for AI Efficiency: What Measured Data Shows About the Power of "Why"

Write a function that returns a string. Give this instruction to an AI coding tool, and the implementation you get back varies wildly depending on context. In C…