Graduation Term

Spring 2026

Degree Name

Master of Science (MS)

Department

Department of Technology

Committee Chair

Borinara Park

Committee Member

Hanna Sperry

Abstract

Hospital Length of Stay (LOS) analysis is essential for managing hospital efficiency and financial performance, yet the analytical depth required remains inaccessible to many organizations due to technical and resource constraints. This thesis introduces the AI Agent Modular Capabilities (AIAM) framework, which decomposes LOS analysis into discrete, codifiable capabilities integrated into a single skill activatable with one prompt. Seven AI Agent Modular Capabilities were developed using a Work Breakdown Structure and tested against a simulated hospital scenario across three successive skill versions. Results demonstrate that the packaged AIAM skill produces comprehensive, consistent, multi-section LOS analyses from a single interaction, outperforming unstructured AI prompting across all four evaluation dimensions. The findings establish benchmark verification as a critical quality gate in skill design and confirm that the AIAM framework offers a replicable pathway toward democratizing sophisticated LOS analytics in settings that have historically lacked the infrastructure to conduct it.

Access Type

Thesis-Open Access

Download

Share

COinS