JMIR Publications

ABSTRACT

Artificial intelligence (AI) agent systems can combine autonomous action, persistent memory, multistep planning, and dynamic tool use, representing a shift beyond conversational large language models. They are increasingly relevant to health professions education, yet practical implementation remains limited. A recent survey reported that 43% of United States health systems were piloting agentic AI, whereas only 3% had deployed agents in live workflows, underscoring both institutional interest and implementation challenges. Existing publications have largely described the capabilities, potential applications, and risks of AI agents, but educators still lack practical guidance for translating these capabilities into bounded, governable educational workflows. This Viewpoint presents an implementation framework for program directors, clerkship directors, simulation leaders, faculty developers, and associate deans. The framework guides educators in selecting appropriate use cases, defining agent roles and boundaries, identifying required data and tools, establishing human oversight, and evaluating educational value, safety, equity, and failure modes before scaling. We apply the framework to administrative coordination, adaptive tutoring, clinical reasoning coaching, simulated-patient practice, competency-based medical education portfolio synthesis, and faculty development. For each workflow, we specify the educational problem, bounded agent task, required data and tools, intended output, oversight model, validation metrics, and level of educational stakes. A worked example illustrates how a simulated-patient agent can be configured, constrained, monitored, and evaluated. AI agents should be introduced in health professions education as bounded workflow supports rather than autonomous educational decision-makers. Programs should begin with low-stakes pilots, evaluate educational value and safety before expansion, and reserve decisions regarding assessment, wellness, remediation, progression, and promotion for human decision-makers