Explore AI-driven workflows for discovering novel superconductors in this comprehensive lecture presented by Richard Hennig and Jason Gibson from the University of Florida. Delve into three innovative AI algorithms designed to accelerate materials discovery and design, including data augmentation techniques for improving crystal graph neural networks, ultra-fast interpretable machine-learning potentials, and symbolic regression methods for enhancing superconducting transition temperature predictions. Gain insights into the challenges and opportunities of developing efficient complex workflows for materials science, and learn how these cutting-edge approaches are revolutionizing the field of superconductor research and materials discovery.