Shipping
Sep 26A11yReadyDesign workstream lands + Oct-16 path clears + 16 PRs merge in one day. External design…Sep 15VantageSept-15 internal tech talk delivered. Vantage architecture walk (11-slide restructured…Sep 6File ExplorerAgentic delivery team + GitHub Project board stood up; M0 baseline lane-reviews complete…Sep 5File ExplorerCanonical metrics source shipped — one provable set of file/page counts, killing…Sep 3A11yReadyForms V1 kicked off with the fidelity foundation shipped: a content-completeness gate now…Sep 2A11yReadyTrack A closed end-to-end. Batch-11 verified on the serving Cloud Run revision:…Aug 25VantageLocked suite reached 416 via the corpus→coverage loop — six net-new locks in a day, every…Aug 25VantageThe “A_Pgm de-gate” landed — one admin read now covers the config side of ~24 role-gated…Aug 25VantageFifth platform-found UCR defect filed — an admin “Active” flag that isn’t…Aug 25VantagePublic metrics pipeline moved to GitHub Actions after source-of-truth was consolidated to…Sep 26A11yReadyDesign workstream lands + Oct-16 path clears + 16 PRs merge in one day. External design…Sep 15VantageSept-15 internal tech talk delivered. Vantage architecture walk (11-slide restructured…Sep 6File ExplorerAgentic delivery team + GitHub Project board stood up; M0 baseline lane-reviews complete…Sep 5File ExplorerCanonical metrics source shipped — one provable set of file/page counts, killing…Sep 3A11yReadyForms V1 kicked off with the fidelity foundation shipped: a content-completeness gate now…Sep 2A11yReadyTrack A closed end-to-end. Batch-11 verified on the serving Cloud Run revision:…Aug 25VantageLocked suite reached 416 via the corpus→coverage loop — six net-new locks in a day, every…Aug 25VantageThe “A_Pgm de-gate” landed — one admin read now covers the config side of ~24 role-gated…Aug 25VantageFifth platform-found UCR defect filed — an admin “Active” flag that isn’t…Aug 25VantagePublic metrics pipeline moved to GitHub Actions after source-of-truth was consolidated to…

AI Architect

Loren Cossette

Your organization doesn't need another AI vendor. It needs an AI lead.

AI Architect and hands-on engineer who designs enterprise AI systems, writes the production code behind them, and directs the agentic development squads that ship them. Sole AI resource for Multnomah County — delivered six production platforms across three departments (DCA, DCHS, DDAP) on two clouds (GCP + Azure) under reviewed-PR, git-worktree-isolated governance with zero production incidents.

San Antonio, TX5 Production AI Initiatives · Multnomah County · Shipping Weekly

Delivery Evidence

Dated record of what shipped

Production milestones, validation improvements, and shipped functionality across the Multnomah County AI Program and other work — dated and traceable to specific case studies. The same auditability standard the program maintains internally.

Impact

Numbers that matter

$2.7M+
Cost Saved
USAA Q1 Impact
56,567
Files Automated
WCAG Compliance
90%
Scope Reduction
Triage Pipeline
26×
Speed Increase
Content Platform
89%
Cost Reduction
$35K Saved
64%
Cycle Time Cut
Decision Time

Independent Validation

Verifiable, not just claimed

Every metric on this site can be traced to a public artifact, an industry-standard validation engine, or an external audit. No testimonials. No hand-waving.

Independent PHP Audit · Xingwu

Cross-Validated File Classification

92.3%

agreement on 33,738 UUIDs

Civic Sentinel's six-bucket classification was independently audited by Xingwu's PHP-based site crawler against the same Drupal inventory. Result: 92.3% direct agreement across 33,738 file UUIDs, with reconciled deltas tracked month-over-month.

Civic Sentinel

axe-core · Industry-Standard WCAG Engine

First-Pass WCAG 2.1 AA Compliance

95%+

first-pass axe-core score

Every A11yReady-converted document is validated through axe-core running real automated checks via Playwright in the production container — the same WCAG 2.1 AA testing engine used by accessibility auditors worldwide. Validation runs before any document reaches human review.

A11yReady

SME Review Queue · Deployed UI

Human-Validated Knowledge Capture

20+

SME-confirmed sessions

Subject Matter Experts confirm captured knowledge through the deployed review interface before it becomes authoritative for downstream agents. 20 SME-confirmed knowledge sessions and 32 tribal-knowledge questions answered in a single day prove the workflow operates end-to-end.

UCR Modernization

The Four Pillars

How I run an AI program

Architect & Build Production AI Systems

Multi-agent orchestration, LangGraph pipelines, RAG, Vertex AI Model Garden routing (Claude Opus/Sonnet/Haiku, Gemini) — the systems other people put on a roadmap, I put into production. A11yReady (~185K lines Python, 95%+ WCAG), Civic Sentinel (56K files nightly), and Vantage (multi-tenant agentic testing, 718 locked tests) 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 AI Architect and hands-on engineer. Sole AI resource for Multnomah County, running 6 production platforms across three departments (DCA, DCHS, DDAP) on two clouds (GCP + Azure) — directing agentic development squads under reviewed-PR, git-worktree-isolated governance with zero production incidents. Shipping 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.

Ph.D. CandidateProsci CertifiedSHRM-SCPSAFe Agilist20-Year Military (E-9, Top 1%)5 Publications
Learn more about me

Technology

The stack I ship with

AI / ML

LangGraphCrewAIGoogle ADKMCPVertex AI Model GardenClaude Opus / Sonnet / HaikuGemini 2.5 / 3GPTPyTorchTensorFlowscikit-learnXGBoostpgvectorSnowflake Cortex

Languages

PythonTypeScriptJavaScriptSQLPHPC# (.NET 8)

Full Stack

React 19.NET 8 / Blazor ServerFastAPIREST APIsNode.jsDrupal 10Playwright

Cloud / DevOps

GCP (Cloud Run, Vertex AI, Pub/Sub, Cloud Tasks, Cloud Functions gen-2)Azure (App Service, Azure SQL / DACPAC)Snowflake (Cortex, Snowsight)AWSTerraformOpenTofuWorkload Identity Federation (keyless, dual-pool)GitHub ActionsAzure DevOps PipelinesDocker

Data

BigQueryFirestoreCloud SQLPostgres 16 + pgvectorAzure SQLSnowflakePandasNumPyETL Pipelines

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.