I spent more than four decades building and leading software systems. I have retired from corporate life and now work as an independent advisor, author, and researcher focused on distributed systems, desktop architectures using local LLMs, and software engineering in the age of AI. I am the author of several O'Reilly books and have spoken at numerous industry conferences, and am currently completing a practitioner's guide to applying spec-surface engineering in the construction of LLM-assisted systems.

My current research centers on how engineering discipline must adapt when implementation tools are probabilistic. I am building a production financial planning system as a primary research instrument — a working system that makes the question of correctness in LLM-assisted development concrete and measurable. The core claim: LLMs don't break software correctness — they relocate where it must be governed.

Recent Writing

Books

Speaking