About

I'm a city council member in Elgin, Illinois serving my second term, with four and a half years of elected experience. I've voted on emergency aid for homeless residents after an encampment fire, navigate how local government protects people from opaque and overly aggressive federal immigration practices, and push for accountability when city-funded organizations present gaps in service.

These aren't abstract policy debates...they're non-verifiable decisions. There's no algorithm for weighing emergency shelter costs against long-term housing strategy. No optimization function for balancing federal relations against protecting our neighbors. No correct answer for how much underperformance justifies contract revisions. These are value-laden tradeoffs requiring human judgment and democratic accountability.

That's exactly why I build AI tools for this context. Not to make these decisions...but to improve the quality of research, reasoning, and collaboration that informs them.

Technical Work

My open-source work has influenced product development at Coda. My Coda MCP server, a 34-tool integration layer for AI systems, has been used by Coda's engineering team to inform their official implementation. As Coda engineer Bharat Batra noted publicly: “We've been playing with your MCP as well and it has helped us think through our own design.”

I created CivicAide, a civic technology platform featuring PolicyAide—an 8-agent system for policy research. PolicyAide uses tournament-style competition between specialized AI agents to stress-test policy approaches against each other. Drawing on Google's AI CoScientist research and Anthropic's work on debate-based alignment, proposals compete head-to-head, weak arguments get eliminated, and stronger positions emerge through adversarial iteration by incorporating successful elements of eliminated proposals. An ELO rating system, borrowed from chess, tracks which proposals survive rigorous competition.

The result: policy research that's been attacked from multiple angles before it reaches the decision-maker. Council makes the decision; PolicyAide makes sure we've stress tested the decision and considered the strongest counterarguments.

Framework

This work led me to develop the Verifiability Framework—a methodology for determining when AI should automate government processes versus augment human judgment.

Drawing on Andrej Karpathy's distinction between specifiable and verifiable tasks, the framework provides municipalities with clear criteria for responsible AI adoption: automate what you can verify, use AI as a thought partner for everything else.

The decisions I described above...emergency aid allocation, immigration protection policy, accountability for partners...are exactly the kind of non-verifiable decisions where AI should augment, not decide. PolicyAide is built for that boundary and obsessed with co-building the collaborative local gov worksurface for enabling, and auditing, AI as a thought partner.

The companion to the Verifiability Framework is the Trust Stack...a framework for understanding when investing in trust accelerates AI adoption. Four layers of trust, from process compliance to democratic sovereignty, help municipalities understand what infrastructure strengthens different types of deployment. I'm bringing the Trust Stack as a diagnostic lens to an upcoming engagement with U.S. Digital Response...its first real-world application.

Speaking

I speak on municipal AI implementation at conferences including the Illinois Municipal League (IML) and City AI Connect. Topics include:

• The Verifiability Framework and Trust Stack for public sector AI
• Building AI tools from inside government
• Practical lessons from 4.5 years of elected service + civic tech development

Background

I work as a Coda developer for Western Governors University. Before that, I spent years in startup environments, which gave me a bias toward accountability, clear metrics, and shipping things that work.

I'm an AI-forward developer...I build by directing AI systems rather than writing code in the traditional sense. I've worked extensively with ChatGPT and custom GPTs, Google's Gemini and Gems, and Anthropic's Claude Desktop and Projects. My preferred tools come from Anthropic; I appreciate both the capability of their models and their commitment to AI safety research. This site was built with Claude Code.

I'm currently partnering with US Digital Response to help Elgin develop responsible AI policies...bringing the Verifiability Framework from theory into practice in my own municipality.

Beyond AI policy, I'm focused on building local government's internal capacity for custom software development...starting with Elgin. Too often, municipalities run to vendors for solutions that could be built in-house with the right tools. AI-assisted development makes this more accessible than ever.