This foundational workshop equips participants with essential knowledge and practical skills for evaluating and using AI tools in health professions education. Through hands-on practice and collaborative learning, participants will develop competencies in systematic tool evaluation, advanced prompting techniques, critical validation frameworks, and ethical AI implementation.

While building on the successful 2025 pilot program, this workshop features significantly updated content reflecting the rapid evolution of AI tools and capabilities. New elements include enhanced frameworks for responsible AI use (incorporating AAMC principles and IACAI recommendations), expanded coverage of AI agents and autonomous capabilities, updated tool comparisons, and refined prompting techniques. Previous attendees will gain valuable new knowledge and skills aligned with current developments in the field.

Content Areas:

• Understanding AI capabilities and limitations
• Systematic Generative AI tool evaluation and comparison
• Advanced prompting techniques and AI agents
• Critical validation and evaluation frameworks
• Ethical and responsible AI use (incorporating AAMC and IACAI frameworks)
• Hands-on skills building with participant materials

Instructional Methods: Brief conceptual presentations, structured hands-on exercises, small group comparative analysis activities, real-world scenario discussions, and artifact creation with personalized feedback.

Target Audience: Health professions educators, curriculum designers, and academic leaders with basic to intermediate AI familiarity seeking to enhance their capabilities in evaluating and implementing AI tools in educational settings.

Learning Objectives

1. Analyze the capabilities, limitations, and appropriate applications of large language models (LLMs) in health professions education contexts, including recognition of common biases and training data constraints.
2. Evaluate and compare generative AI tools using established rubrics and systematic frameworks to select appropriate tools for specific educational needs.
3. Apply advanced prompting techniques and iterative strategies to optimize AI output quality, relevance, and educational utility for diverse medical science education applications.
4. Assess AI-generated content for reliability, accuracy, and appropriateness using critical evaluation frameworks before implementation in educational settings.
5. Integrate ethical principles and responsible AI practices into educational workflows, addressing academic integrity, data privacy, HIPAA/FERPA compliance, and distinctions between open and closed AI systems.