I build the systems organisations run AI agents on.

01  The work

Most AI adoption stalls because agents have nothing reliable to run on.

The models are strong enough. What's missing is the memory underneath them. An organisation runs on a context layer that mostly isn't in tidy systems: stale documents indistinguishable from current ones, decisions buried in inboxes and chat threads, processes that run on tacit rules nobody wrote down, no source defined as authoritative. Point a capable agent at that and it retrieves confidently from the wrong place.

My work is that layer and the machinery around it. Three things separate a demo from a system an organisation can actually run on. The workspace architecture: the governed memory, roles, task flow, and guardrails a fleet of agents operates inside. The token economics: what a capable agent costs per unit of work, and the orchestration and model-tiering decisions that hold that cost down as usage compounds. And the loop engineering: which work runs unattended, which gets surfaced for human review, and which stays manual. I build all three, on a memory system designed to be read by agents as much as people.

02  Capabilities

Three primary practice areas

Each one runs daily in a production workspace and is documented in the open, pattern by pattern, in a public reference architecture.

Backed by

03  Selected work

Built, not demoed

04  Background

An engineer's discipline, applied to organisational memory

I came to knowledge architecture through data engineering, building production data platforms: cloud data warehouses, ETL pipelines, and the analytics executives actually decide on. Then I went deep on agent systems, building a full multi-agent workspace from the ground up, building and deploying an AI-driven SaaS end-to-end, and formalising the work through doctoral research into how autonomous agents share and govern memory. The two threads meet at the same place: the system of record an organisation runs on, now designed for agents to read as well as people.

It means I bring an engineer's production discipline (version control, testing, provenance, rollback, observability) to a field that is still mostly demos.

• Doctoral research — trustworthy shared memory for collaborative AI agents (James Cook University, from 2026)
• Master of Data Science — James Cook University
• Graduate Diploma in Research Methods — James Cook University

05  How we work together

Engagement models

Every engagement has a defined start, a defined deliverable and a defined end. No retainers, no standing availability, no on-call.

Practices where the firm pays for slow work: architecture and engineering design, planning and development applications, valuation, loss adjusting and claims assessment, accounting compliance, and other professions that quote a fixed fee or a fee per file. Private sector only. Not a fit where the agent would carry professional judgment without the professional's review. Larger estates with one high-value workflow are the Context Architecture Build's buyer.

Every engagement is a fixed fee, stated on its offer sheet. Ask for the pack.

How every engagement runs

• Bounded scope — one high-pain area at a time (a key-person departure, an onboarding bottleneck, a "nobody can find anything" domain), never "map our whole organisation".
• Non-extraction by design — analysis computes in your environment and emits derived structure, not content; raw material never leaves your tenant, and the data flow is auditable in your own logs.
• Auditable over autonomous — anything that runs is transparent, scoped, throttled, and logged, deliberately less autonomous than the technology allows; access expands only by explicit grant.
• An explicit IP split — findings about your organisation are yours; the generalised methods I arrive with and refine are mine. Written into every engagement, never discovered later.
• A hand-back clause — if the engagement must end early on either side, all work product to date is delivered within five business days, your systems are left in a working state, and fees settle pro rata against the stages completed.
• Your model access, your data — you pay the vendor directly for model access under business terms that do not train on your inputs, and I never hold your account or keys. Client data is classed at the start, and a one-page data note records which class goes through which route and where it is processed.

I build the capability, then hand over the keys. The goal is to make the engagement unnecessary, not to create a dependency.

Not a fit: generic ML or analytics builds, staff augmentation, or open-ended on-call retainers. I focus on the knowledge and context layer agents run on, in engagements that ship and end.