I am a principal GenAI engineer. I build production AI systems: multi-agent platforms, the orchestration and routing layer that runs them, and the evals that keep them honest. Most of my writing here is about the parts of enterprise AI that decide whether any of it works: process, ownership, evals, and what happens when things fail.
What I work on
The technology I spend my days in:
- Multi-agent systems. Agents that plan, delegate, and use tools, with orchestration and guardrails deciding what they may do on their own and what needs a human.
- Model Context Protocol (MCP). Servers and tool integrations that let agents reach real systems through a standard, governed interface.
- Model routing. Choosing the right model for each task by complexity, cost, and confidence, with escalation when the cheap answer is not good enough.
- Evals. Harnesses that define what a good run looks like and measure agents against it, because whoever defines "good" owns the agent.
- Retrieval and knowledge. Search and knowledge structures that ground agents in real data instead of the model's best guess.
- Languages and cloud. Python day to day, a Java background before it, everything deployed on cloud infrastructure.
What I think about
The essays on this site circle a few questions I keep coming back to. When should you build an agent and when should you buy one? How do agents earn trust: identity, evals, accountability when the output is wrong? What changes when systems stop waiting to be asked and start acting on schedules? And what happens when the binary itself becomes an attack surface? If you read one piece, start with the flagship essay.
Beyond work
Metrocrest Toastmasters on Tuesdays, because presenting is a skill like any other and it improves with reps. The DFW AI community. Board games, video games, photography, and travel. I live in Flower Mound, Texas, with my family.
Elsewhere
LinkedIn is the best way to reach me. I read everything, and I reply to most of it.