Notes from the work.
Short, practical pieces on AI systems, production constraints, and what it takes to make technology hold up outside a demo.
From Notebook to Edge: ONNX and int8 Quantization, Measured
A runnable walkthrough of taking a PyTorch model to a small, fast production service: export to ONNX for a 1.81× latency win, quantize the head to int8 for a 3.66× smaller artifact, and measure it honestly.
June 22, 2026
Why AI Prototypes Stall Before Production
The model is rarely the whole problem. The gap is usually data discipline, evals, deployment, cost, and monitoring — and that gap is what most projects underestimate.
June 15, 2026
The Local Visibility Checklist: 7 Gaps Costing You Calls
Most local service businesses don't have an SEO problem — they have a handful of specific, fixable visibility gaps. Here are the seven I find most often, and how to close them.
June 8, 2026
What Battlefield Triage Taught Me About Shipping Reliable AI
Special Forces medicine runs on protocols, clear definitions of done, and outcome ownership under pressure. The same discipline is what separates AI demos from systems people can trust.
May 20, 2026
Edge AI at the Operator's Edge
Why inference on constrained hardware — not a GPU fleet in the cloud — is where a lot of real-world AI value lives, viewed through the lens of decision-making at the front lines.
May 12, 2026