AI Program Architect
Loren Cossette
Your organization doesn't need another AI vendor. It needs an AI lead.
I run production AI programs from inside organizations — architecting the systems, building the code, capturing institutional knowledge, and shipping outcomes weekly. Currently embedded as the AI lead for Multnomah County, running 5 production AI initiatives across accessibility, site intelligence, legacy modernization, and QA automation.
From the Multnomah County AI Program
Recent Activity
What shipped lately
Dated log of features, fixes, and milestones across the program and other work. The same kind of build-in-public feed you can see in the Multnomah County hub — anyone can verify the velocity.
Impact
Numbers that matter
Client Impact
What leaders say
“Loren didn't just build us an AI system — he rewired how our entire leadership team thinks about technology adoption. The governance framework alone saved us six months of false starts.”
Rachel Dominguez
Deputy Director, Digital Services
County Government Agency
“We had three failed AI pilots before Loren came in. Within 90 days he had a production pipeline running that our team could actually maintain. The difference was someone who understands both the code and the organizational politics.”
Michael Chen
VP of Engineering
Enterprise SaaS (Series C)
“His ability to translate between the C-suite and the engineering floor is rare. Our board finally understood why the AI investment mattered — and approved the next phase on the spot.”
Dr. Amara Osei
Chief Strategy Officer
Healthcare Technology Firm
The Four Pillars
How I run an AI program
Architect & Build Production AI Systems
Multi-agent orchestration, LangGraph pipelines, RAG, Vertex AI / Claude / GPT routing — the systems other people put on a roadmap, I put into production. A11yReady (95%+ WCAG, 30s/doc) and File Intelligence (56K files nightly) are live examples.
Capture Knowledge Before It Walks Out
Retiring SMEs take decades of tribal knowledge with them. I build typed knowledge corpora, SME-confirmation workflows, and behavioral test suites that turn institutional memory into executable specs. UCR Modernization captured 704 SME sessions and 208 behavioral Playwright tests.
Modernize Legacy Without Breaking It
Multi-agent testing platforms that index legacy codebases, generate regression suites from captured knowledge, and watch for drift on every commit. Lets the modernized system prove behavioral parity before it ships — and gives leadership confidence to greenlight the rebuild.
Run the Program, Not Just the Build
Stakeholder hubs, dated activity feeds, ROI calculators, validation against independent audits, SME approval queues. I close the loop between technical work and executive trust — so AI initiatives stop dying in pilot purgatory.
About
I'm an embedded AI program architect. Currently the AI lead for Multnomah County, running 5 production AI initiatives across accessibility, site intelligence, legacy modernization, and QA automation — shipping features weekly with a dated public activity feed.
Multi-agent systems on Vertex AI (Claude, Gemini, GPT). LangGraph pipelines. RAG with pgvector. Behavioral test capture from retiring SMEs. Stakeholder hubs, ROI calculators, and validation against independent audits — plus executive training at UT Austin and Johns Hopkins and peer-reviewed AI research on the side.
Technology
The stack I ship with
AI / ML
Languages
Full Stack
Cloud / DevOps
Data
Work With Me
Ready to bring in an embedded AI lead?
If your organization is modernizing legacy systems, scaling AI safely, or staring down a compliance deadline — let's talk about whether embedded AI program leadership is the right fit. Engagements start with a 30-minute working session, not a sales pitch.