Working with Andy Zhang, University of Conneticut '26, this project explores the use of Large Language Models (LLMs) to extract, organize, and evaluate municipal zoning regulations. By developing a query-based algorithm that assigns relevance scores to matched passages, we tested the model’s ability to retrieve accurate information from complex planning documents. The results demonstrate that, while LLMs are highly effective for structured prompts and tabular data, human judgment remains essential for interpreting distributed or ambiguous standards.