JMIR Publications

ABSTRACT

The integration of large language models (LLMs) into medical education has significantly increased, providing valuable assistance in single-turn, isolated educational tasks. However, their utility remains limited in complex, iterative instructional workflows characteristic of clinical education. Single-prompt AI chatbots lack the necessary contextual awareness and iterative capability required for nuanced educational tasks. This Viewpoint article argues for a shift from conventional chatbot paradigms towards a modular, multi-step AI agent framework that aligns closely with the pedagogical needs of medical educators. We propose a modular framework composed of specialised AI agents, each responsible for distinct instructional subtasks. Furthermore, these agents operate within clearly defined boundaries and are equipped with tools and resources to accomplish their tasks and ensure pedagogical continuity and coherence. Importantly, specialised agents enhance accuracy by using models optimally tailored to specific cognitive tasks, increasing the quality of outputs compared to single-model workflows. Using a clinical scenario design as an illustrative example, we demonstrate how task specialisation, iterative feedback, and tool integration in an agent-based pipeline can mirror expert-driven educational processes. Crucially, the framework maintains a human-in-the-loop structure, with educators reviewing and refining each output before progression, ensuring pedagogical integrity, flexibility, and transparency. Our proposed shift towards modular AI agents offers significant promise for enhancing educational workflows by delegating routine tasks to specialised systems. We encourage educators to explore how these emerging AI ecosystems could transform medical education.