I work with CTOs, VPs of Engineering, and executive teams on architecture challenges that are too complex for a quick hire and too important to get wrong.
You've seen what AI agents can do. Maybe your team has built a few prototypes. But moving from demo to production — with proper tool orchestration, policy guardrails, observability, and governance — is a different problem entirely. You need someone who knows how these systems work from the inside.
I design agentic AI architectures that connect LLMs to your real-world systems safely and reliably. As a maintainer of the Model Context Protocol, I bring first-hand knowledge of the tooling layer that sits between AI models and enterprise infrastructure. I define the agent workflows, the policy boundaries, and the observability stack — then I help your team ship it.
A production-grade AI agent architecture with clear governance boundaries, integration patterns your team can extend, and measurable operational value — not a proof of concept that stalls.
The monolith served you well — until it didn't. Every change takes longer than it should. Teams step on each other. Deployments are risky. The board is asking why the technology can't keep pace with the business. You need a target-state architecture and a credible path to get there without stopping the engine mid-flight.
I define target-state architectures and technical roadmaps for commerce and customer platforms. That means domain modelling, service boundaries, eventing patterns, platform guardrails, and cost/performance trade-offs — all grounded in what your teams can realistically execute. I don't hand over a diagram and leave. I stay through the migration, aligning engineering, product, and leadership on sequencing and trade-offs.
A target-state architecture your teams understand and believe in, a phased migration plan with clear business milestones, and hands-on support through the hardest part — the cut-over.
You're moving off a legacy commerce platform — or building a new one from scratch. The vendor landscape is overwhelming. Everyone's pitching “composable” and “headless” but nobody's telling you how to actually get there with 30–80 engineers, existing integrations, and a business that can't afford downtime.
I lead composable commerce re-platforms end-to-end — from discovery through vendor evaluation, architecture definition, and delivery governance. I've run these programmes on both sides: as the technical lead building the platform, and as the architect defining the target state. I know where these projects go wrong, and I design around those failure modes from day one.
A composable platform architecture built for your specific business constraints, a delivery structure that keeps 30–80 engineers aligned, and an architecture that's designed to evolve — not one you'll need to replace again in three years.
I start by listening. Before I draw a single diagram, I need to understand the business context, the organisational dynamics, and the real constraints — not just the technical ones. The best architecture in the world fails if the team can't execute it or the business won't fund it.
Most of my engagements begin with a short discovery phase — typically a few focused sessions with your technical and business leadership. From there, I'll either embed with your team for the duration of the programme or operate as an advisory architect, depending on what the situation needs.
I work with your existing teams, not around them. The goal is always to leave your organisation stronger than I found it — with an architecture they understand, own, and can evolve without me.
Most conversations start with a problem, not a service line. Tell me what you're facing and we'll figure out the right approach together.
Start a Conversation