Explore the code, data, products, and processes that bring Urban Institute research to life.
Content Reference
A person’s financial well-being is nuanced, encompassing many different metrics and situations. A single dataset rarely paints a complete picture of people’s financial lives. Therefore, building a holistic understanding of financial well-being often requires linking data from several disparate sources.
Rapid Prototyping with Agentic AI to Make Better Technical Decisions, Faster
- Two recent projects show how agentic tools like Claude Code let us prototype and test technical approaches in minutes, ruling out dead ends before committing p…Two recent projects show how agentic tools like Claude Code let us prototype and test technical approaches in minutes, ruling out dead ends before committing project time and budget, and take on more ambitious work with confidence.
Introducing AI@Urban: Practical, Evidence-Based Learning on AI in Public Policy
- We are introducing AI@Urban, a new series within the Urban Institute's Data@Urban platform dedicated to sharing practical, evidence-based learning at the intersection of AI and public policy. Through quick, digestible posts, we'll cover what we're learning as we incorporate AI into our policy work and support government and nonprofit partners in using it responsibly.
Rebuilding a Fair Housing Data Tool with Claude Code
- When the federal government terminated the Affirmatively Furthering Fair Housing rule and its data mapping tool, Urban Institute's data science team had 12 weeks to build a replacement in partnership with the National Fair Housing Alliance. Here's what we learned using AI-assisted coding to get it done.
Could Retrieval-Augmented Generation with Large Language Models Help Make Local Zoning Codes Easier to Navigate?
- We ran a benchmarking exercise to evaluate how well large language models could answer zoning and permitting questions about Minneapolis’ local zoning code.
How We Used Routing Analysis to Map Access to Social Security Offices
- A step-by-step look at how we calculated drive time from the population-weighted centroid of every census tract to the closest Social Security office.
Five Lessons for Building Sustainable Data Systems to Support Policy Insights
- We offer a behind-the-scenes look at our approach and the lessons we’ve learned, with the aim of helping other organizations and leaders build the foundations for data systems that unlock insights and improve outcomes.
