I build AI tools that solve real problems — from token-efficient code intelligence to real estate marketing automation. By day, I manage critical plant systems. By night, I ship products.
For twenty years, I've been the person organizations call when complex systems need to work together. Manufacturing floors, content distribution networks, international deployments — the job has always been the same: understand how the pieces connect, find where they break, and make them hum.
When AI coding agents started struggling with the same problems — too much context, too little precision, systems that couldn't talk to each other — the parallel was impossible to ignore. The skills I'd spent two decades building in physical systems translated directly to building intelligent software. Not just writing code, but understanding how data flows, where bottlenecks form, and how to make complex systems reliable.
Today I split my time between managing plant systems at a security printing facility and building AI tools that solve problems I've lived firsthand. A code intelligence server that stops AI agents from drowning in context. A marketing platform that gives real estate agents back their evenings. A tax assistant that never guesses. Each project started the same way — with a real frustration and a belief that systems thinking could fix it.
Projects born from real frustrations and a belief that systems thinking can fix them.
Agent output governance for enterprise AI
AI agents are making procurement decisions, approving invoices, and modifying employee records — at machine speed, 24/7. Your team can't review thousands of agent outputs per day. I'm building a transparent governance layer that intercepts every decision, classifies it by risk, and escalates the ones that matter — before they execute.
Enterprise secure AI agent governance platform
AI agents are gaining autonomy, but the safety mechanisms guarding them are still just system prompts — speeches about why doing bad things is wrong. I’m building an enterprise-secure agent host that compiles morality into WASM sandboxes, Zod schemas, and Biscuit Datalog rules. A speech can be argued with. Physics cannot. PR1M3Claw is a deterministic governance architecture where an LLM is allowed to execute only what the cryptographic trust chain permits, only within a capability-scoped sandbox, and only after a Constitutional Supervisor co-signs the intent.
Private repository — active development
Token-efficient code intelligence for AI agents
AI coding agents burn through tokens like fuel — scanning entire codebases just to understand a single function. I built a tool that gives them surgical precision instead of brute force, cutting token usage by up to 80% while making them genuinely smarter about your code.
Semantic code intelligence — search by meaning, not just keywords
ContextLens gave AI agents a precise map of your codebase. ContextLens Turbo gives them the ability to search it by meaning. Searching for 'user authentication flow' now surfaces the right functions even when the code is named 'validateToken' or 'checkCredentials' — no keyword overlap required. It runs entirely offline, requires no GPU, no external APIs, and no database infrastructure. Just a local index that understands what your code does.
AI-powered real estate marketing in under 60 seconds
Over two million real estate agents spend an average of $1,200 a year on marketing — and most of that money buys mediocre listing descriptions and a handful of social posts. I built a platform that generates everything an agent needs to market a property, from copy to microsite, in less than a minute.
Free bilingual Canadian tax assistant that never guesses
Tax season in Canada means navigating a maze of CRA guides, credits, and deadlines — often in your second language. I built a bilingual AI assistant that answers tax questions using only official CRA documentation, cites its sources, and says "I don't know" when it doesn't. No hallucinations. No cost. No catch.
A concept for accessible AI integration
iiSP is a personal project exploring how Canadian small and mid-sized businesses could adopt AI in ways that actually make sense — not hype-driven chatbot widgets, but genuine integration of RAG systems, intelligent agents, and orchestration layers into existing business workflows. I've built the prototypes and documented the approach as a proof of concept.
An AI skill system that evolves after every coding session
Most AI coding tools forget everything between sessions. I built a meta-skill that watches how I work, identifies gaps in its own knowledge, researches current best practices, and rewrites its own playbooks — so every session starts smarter than the last.
The systems thinking behind the products.
My career has been a masterclass in making complex systems reliable. As Plant Systems Manager at Canadian Bank Note Company — one of Canada's most security-critical manufacturing environments — I lead a team responsible for the infrastructure that keeps production running: vision inspection systems, automated backup solutions, machine monitoring, and everything in between.
Before that, I spent years in the trenches of technical support and consulting — at International Datacasting deploying broadband multimedia systems across international markets, at CaseWare International supporting enterprise accounting platforms, and as an independent consultant helping organizations untangle their technical debt.
The thread connecting all of it: I'm the person who makes systems that don't talk to each other start talking.
Bachelor of Business Administration
Memorial University of Newfoundland
2016 – 2020
AI for Business Specialization
University of Pennsylvania
2024
Google IT Automation with Python
Coursera
2024
Fluent in Python and TypeScript. Comfortable with LLMs, RAG architectures, and the MCP protocol. Experienced with PostgreSQL, Redis, Docker, and Linux infrastructure. Equally at home debugging a manufacturing floor PLC as deploying a Next.js application to a VPS.
Interested in AI tools, collaboration, or building something together? Let's talk.
Location
Ottawa, Ontario, Canada
Whether you're interested in one of my projects, want to collaborate on something new, or just want to talk about building AI tools — I'd love to hear from you.