Technology shifts. Sometimes gradually. Sometimes all at once. After more than 40 years in IT, I’ve learned to pay attention when the wind changes direction. In late 2024, I made a deliberate pivot from quantum computing research to applied artificial intelligence. The signal was unmistakable: AI is not just another wave — it is infrastructure-level change. This site documents that work. My focus is practical AI architecture, security, governance, and threat modeling — buildi

I spent a long couple of sessions turning a “wouldn’t it be nice…” idea into an actual working pipeline: a daily briefing agent that can pull my personal Google Calendar (plus US holidays) and deliver a summary to my WhatsApp on a schedule. Of course, that is not my main Google account nor my main phone number in use for this. This is one of those projects where the  idea  is simple, and the reality is OAuth, containers, file permissions, corn runtimes, and messaging quirks,

Until recently, I had been curious about RAG systems in the abstract. I understood the basic promise: take a body of documents, convert them into embeddings, store them in a vector index, and then retrieve the most relevant pieces when a question comes in. But that was still fairly theoretical to me. About 2 months ago, I did my first RAG project which is in a prior post on this site. But lately, something came to me: what if I could load my own OneNote into a RAG type sys

Introduction Full disclosure: I wrote an introduction paragraph and ran it through ChatGPT - this is the combination of my original paragraph and some cleaned up verbiage by ChatGPT. Introduction: Traditional software systems are built on a predictable model: developers write code that processes input and produces output according to predefined logic. Security architecture for these systems focuses on protecting that deterministic behavior from manipulation. Agentic AI syste