Latest Articles
- about 10 hours agoAI Coding
Eval is not a grade — it's a truth mechanism
How I dived into LangGraph and Langfuse through a single experiment — and what evaluation taught me about testing AI agents.
- 7 days agoAI Coding
AI Coding Isn't About Prompts. It's About Systems.
Claude, ChatGPT, Codex — the tool matters less than the engineer behind it. Why AI coding breaks in production, and what separates prompt users from AI workflow engineers.
- 12 days agoProgramming
Magnitude: vision-based E2E testing on a small AI budget
How Magnitude's planner/executor split and a self-hostable vision model let small QA teams run selector-less browser tests cheaply, and where it falls short of Playwright.
- 15 days agoDocumentation
Format Matters: When Markdown Is a Compromise and HTML Is the Answer
A practical checklist for choosing HTML vs Markdown for client decks, CI reports, and agent output—plus a copy-paste template and agent prompt.
