AI Systems Architect and Product Builder
I work with enterprise change and program teams to uncover operational problems and create Microsoft-native AI products. I own the work from stakeholder discovery and product design through launch, governance, compliance, and production support.
I use coding agents to turn product requirements into production software while retaining responsibility for system design, quality, release decisions, and ongoing operations.
1. Start with the work.
I learn how stakeholders make decisions, where effort is lost, and which problems have not yet become formal requirements.
2. Define the product.
I turn the operating problem into a workflow, system design, success measures, and release plan that fit the organization's existing tools and controls.
3. Own it in production.
I direct coding agents, test the product, manage releases, support users, maintain compliance, and keep improving it after launch.
Most of my enterprise work lives in the Microsoft ecosystem. I build with Power Platform, Power Apps canvas, model-driven and code apps, Dataverse, Copilot Studio, Power Automate, Azure, Azure DevOps Boards and work items, Microsoft Fabric, Azure AI Foundry, Azure OpenAI, Azure AI Search, Microsoft Graph, and Entra ID.
AI-assisted program intake for a portfolio office handling about 60 programs per quarter. It reduces charter, readiness, risk, and routing preparation from 6-10 hours to about 10 minutes while keeping the final decision with a person.
Product discovery through production ownership
Two Azure DevOps Boards extensions used across 14 divisions: an AI-assisted change assessment that saves 150-200 hours of monthly data entry and a 12-month resource and capacity planning product.
Product discovery through production ownership
A proactive portfolio-intelligence platform for enterprise change leaders. It reads the reports, presentations, assessments, and transcripts teams already produce and surfaces changes, risks, dependencies, and conflicting accounts with every finding tied to its evidence.
Independent build for enterprise change portfolios
A Microsoft-native AI allocation product for about 90 events per quarter. It pairs a Copilot Studio agent for requesters with an operations app on Dataverse and is estimated to save close to $250K a year in specialist time.
Product discovery through production ownership
A change-management command center on Dataverse and Power Platform used by about 1,000 change managers, program managers, and sponsors across 14 divisions, with reporting that fed executive planning.
Built and ran from launch in 2020 to January 2024
Products I build and run on my own, applying the same approach in markets, research, and community operations.
An independent AI research project for U.S. rates that publishes morning and close notes from public market data, prediction markets, dealer surveys, and Street commentary.
Independent build
An agent pipeline that produces an independent weekly research briefing end to end. Every number is verified against primary sources, every chart is built from data filed in the repo, and each run records what it learned so the next one is faster.
Independent build
Multi-tenant platform for Nurse Honor Guard chapters: public sites, member portals, and admin tools that scale without mixing data.
Independent build