Summary: How I use AI agents to build a project end-to-end, with tests as the main safety net.
Summary: My current unified agentic workflow, where Claude Code, Copilot, and local models act as interchangeable executors, driven by a shared configuration and centered around VS Code as the review surface.
Summary: A review of the book 'AI Engineering'.
Summary: How Agentic AI has already changed the way I build software.
Summary: A practical guide to improving agent effectiveness through structured instructions, skills, rules, subagents, and AI-oriented documentation, without relying on fine-tuning or RAG.