AI solutions architecture and advisory. I evaluate, design, and build LLM-based systems — and tell you when you shouldn’t.
Twenty years of software systems architecture. Two years designing production AI. Independent assessment, architecture, and technical talks for companies deciding what to do about AI.
How I think about it
Most companies are investing in the two lowest-return ways to use AI — a chat window on every desk, assistants for the developers — and have barely touched the one that pays the most: a model embedded as a component inside real software, running unattended at scale. It doesn’t get attention because it doesn’t demo well. It’s also where the return is.
The discipline behind it is easy to state and hard to do: the model is a component, not a product. It reads and judges; deterministic code decides, checks, and keeps the record. Done right, that takes an unstructured, manual process and makes it structured, scalable, and controllable — the opposite of the flashy agent demo that gets quietly canceled six months later. Before any of it, one question sorts the high-return work from the low-return work: can this process be boxed?
What I do
Assess. Evaluate AI decisions before the budget is committed — proposal and vendor due diligence, readiness, architecture review. The honest answer, including when it’s “don’t.”
Architect & build. Design the systems and build the proofs of concept: deterministic-first, evaluated, cost-routed pipelines that hold up in production, not just in a demo.
Train. Technical talks and workshops for leadership and engineering teams — from a 60-minute executive briefing to a full-day engineering intensive. See the catalog.
Who it’s for
Leadership teams weighing what to spend on AI, and the engineering teams who have to build it. My depth is in document-heavy, regulated work — financial services, insurance, healthcare — where being wrong has consequences and “mostly works” isn’t good enough.
Why me
I’m a Principal AI Solutions Architect at a Fortune 500 company, building enterprise AI systems daily, and an independent practitioner. I started skeptical — informed by prior technology cycles where capability was oversold relative to production reality — and I still am, in the ways that matter. More about me.
Deciding what to do about AI? Get in touch.