PromptOS

PromptOS is a practitioner's reference for prompt engineering and multi-agent system design — 23 documents covering everything from core prompt patterns through adversarial security testing, behavioral benchmarking, and production observability for LLM-powered systems.

Most of what's in it came directly out of debugging real prompt failures in production, not from theory — it's the book that grew alongside the AI router and multi-agent systems covered on the Projects page, each documenting the other as both developed.

The 23-document collection is done. I'm on the third draft now, restructuring that collection into a narrative layer with a real cover.