As Artificial Intelligence (AI) continues to transform cataloging and metadata work in libraries worldwide, the University of Central Florida (UCF) Libraries have developed its own programming script for automatic subject generation. This approach generates both Faceted Application of Subject Terminology (FAST) terms and keywords using OpenAI API for traditional and digital collections, incorporating OCLC's FAST Reconciliation Service and a custom made FAST headings vector database for validating terms. UCF has also explored Alma AI Metadata Assistant and interactive Agents for subject generation. This presentation will describe the experience of UCF's AI approach and the Alma AI Metadata Assistant, focusing on the evaluation of generated terms, features, advantages, and limitations of each method. It will also examine their impact on metadata workflows, internal and external collaborations, and key lessons learned. Attendees will gain valuable insights into integrating AI into cataloging practices and the practical outcomes of adopting these innovative approaches.