The first article on this blog explained how it was built in 30 minutes with Claude Code. Naturally, a blog needs comments. Same constraints: no database, no external dependencies, no Disqus tracking visitors. Just PHP + JSON files. Built in one session with Claude Code — the interesting part wasn't the code, it was the security audit that followed. A comment system without a database seems trivia
When building applications with large language models (LLMs), one of the most overlooked costs is how structured data is represented. Most systems use JSON. And JSON is inefficient for LLM input. KODA (Knowledge-Oriented Data Abstraction) is a schema-first data format designed to reduce token usage when sending structured data to LLMs. It works by: Defining structure once (schema-first) Encoding v
More rules should mean better output. That's the intuition. I spent weeks building a comprehensive CLAUDE.md — 200 lines covering naming conventions, security rules, error handling, architectural patterns, import ordering, type safety requirements, and more. I was proud of it. I'd thought through every scenario. Then I scored the output. 79.0 / 100. My carefully crafted documentation was actively
Have you ever looked at code you wrote six months ago and thought: "Who wrote this monster?"? Relax, it happens to all of us. In software engineering, writing code that a machine understands is the easy part. The real challenge is writing code that other humans (including your future self) can understand, maintain, and scale. This is exactly where Software Design Principles come into play. In this
Part 1 of 5 in The New Engineering Contract — what it means to lead engineers when AI is doing more of the coding. SWE-CI tested 18 AI models across 71 consecutive commits. Most broke something on commit 47 they'd already broken on commit 1. That's not an intelligence problem. That's a learning system that isn't learning. A paper made me uncomfortable this month. Not because of what it found about