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
1. The access collection black hole You need Figma access, Google Analytics, WordPress admin, GitHub, and the client's Slack. You ask. They forward a password email from two years ago. You ask again. Their developer says they'll get back to you. Three days pass. The fix: Send a single, complete access list on Day 1 — not "we'll need some access" but the exact list, with specifics for each tool,