Currently submitted to: JMIR Medical Education
Date Submitted: Aug 5, 2026
Open Peer Review Period: Aug 6, 2026 - Oct 1, 2026
(closed for review but you can still tweet)
NOTE: This is an unreviewed Preprint
Warning: This is a unreviewed preprint (What is a preprint?). Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn (a note "no longer under consideration" will appear above).
Peer review me: Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period (in this case, a "Peer Review Me" button to sign up as reviewer is displayed above). All preprints currently open for review are listed here. Outside of the formal open peer-review period we encourage you to tweet about the preprint.
Citation: Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author).
Final version: If our system detects a final peer-reviewed "version of record" (VoR) published in any journal, a link to that VoR will appear below. Readers are then encourage to cite the VoR instead of this preprint.
Settings: If you are the author, you can login and change the preprint display settings, but the preprint URL/DOI is supposed to be stable and citable, so it should not be removed once posted.
Submit: To post your own preprint, simply submit to any JMIR journal, and choose the appropriate settings to expose your submitted version as preprint.
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Making AI Agents Practical in Health Professions Education: An Implementation Framework
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
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.