EUVIMEDAtrasti EUVIMED
StudienprotokollOpen access

Teaching Model Context Protocol, Retrieval-Augmented Generation, and AI Agents to a Multidisciplinary Hospital Workforce: Single-Group Pre-Post Survey Study

Gakyoung Baek iD, Hyunna Lee iD, Dong Hyun Yang iD, Minseo Kang iD, Kun Hee Lee iD, Minji Choi iD, Yura Lee iD, Kye Hwa Lee iD

JMIR Medical Education · 2026-09-11 · 12 · e97822-e97822

DOI: 10.2196/97822 ↗

At a glance

Studienprotokoll in JMIR Medical Education, published online on 2026-09-11. Written by Gakyoung Baek and 7 co-authors. Institution: Big Data Research Center, Asan Institute for Life Sciences, Asan Medical Center, Seoul, Republic of Korea. Major MEDLINE topics: Artificial Intelligence, Teaching. 43 references. The full text is freely available in PubMed Central.

SantraukaSubjectsBibliografiniai duomenysCiteRelated studies

Abstract (original language)

Background

Hospitals worldwide need to upskill their workforce in advanced AI technologies; yet, published guidance on how to design and deliver such training, particularly in agent-level tools like retrieval-augmented generation (RAG) and the model context protocol (MCP), remains virtually absent.

Objective

To describe the design, implementation, and lessons learned from an 8-week, 56-hour intensive generative AI training program for a multidisciplinary hospital workforce, drawing on both quantitative outcome data and participants’ own reflections on their learning experience.

Methods

The program was delivered on-site at Asan Medical Center with simultaneous online broadcast to 2 regional affiliate hospitals. The curriculum was built around the premise that MCP and AI agents would become the foundation of health care AI use, allocating 37% (11.5/31 hours) of on-site instructional time to MCP, and 71% (22/31 hours) to hands-on practice. Participants progressed from foundational concepts through RAG and MCP to team-based capstone projects, supported by funded AI tool subscriptions, a dedicated internal cloud platform, and 3‐6 hours of weekly mentoring per team. A pre-post survey (pre: n=83; post: n=64) evaluated outcomes across Kirkpatrick levels 1‐3, complemented by thematic analysis of open-ended reflections on self-perceived growth.

Results

The technologies that received the greatest curricular investment were associated with the largest self-efficacy differences (MCP: d =1.57; overall effect: r =.574), and participants most frequently cited MCP and RAG when describing how abstract concepts “became concrete and actionable.” Non-IT professionals, clinicians, health information managers, researchers, and administrative staff showed consistently larger gains than IT specialists; several reported coding for the first time through vibe coding, challenging the assumption that advanced AI training requires technical backgrounds. Despite significant overall gains, a knowledge-practice gap persisted: job-specific competency remained below the scale midpoint, though participants spontaneously reported generating workplace application ideas. Curriculum pacing was rated lowest despite high overall satisfaction (4.03/5), signaling that even 56 hours may progress too quickly for mixed-expertise cohorts. Capstone projects with dedicated mentoring received the highest satisfaction ratings; 11 of 12 teams presented functional prototypes, and one has since entered active pilot use in clinical departments ahead of planned hospital-wide deployment.

Conclusions

To our knowledge, this is the first program to teach 4 agent-level generative AI technologies, MCP, RAG, LangGraph orchestration, and AI agent design, to both IT and non-IT hospital staff. This program suggests that transforming a multidisciplinary hospital workforce into AI-capable professionals is achievable through intensive, hands-on training centered on agent-level technologies, and that capstone projects with dedicated mentoring can serve as a pathway from classroom learning toward institutional AI adoption. The knowledge-practice gap highlights the need for posttraining support structures to translate self-efficacy gains into sustained workplace practice.

Subjects

MeSH terms (MEDLINE)

Artificial IntelligenceTeachingHumansSurveys and QuestionnairesCurriculumGenerative Artificial IntelligenceWorkforce

Author keywords

artificial intelligencecurriculum designhealth personnellarge language modelsmedical educationmodel context protocolself-efficacystaff development

Authors and institutions

  • Big Data Research Center, Asan Institute for Life Sciences, Asan Medical Center, Seoul, Republic of Korea.
  • Department of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Republic of Korea.
  • Department of Information Medicine, Asan Medical Center, University of Ulsan College of Medicine, 88 Olympic-ro 43-gil, Songpa-gu, Seoul, 05505, Republic of Korea, 82 2-3010-5991.

ORCID profiles: Gakyoung Baek, Hyunna Lee, Dong Hyun Yang, Minseo Kang, Kun Hee Lee, Minji Choi, Yura Lee, Kye Hwa Lee

Cite

APA

Baek, G., Lee, H., Yang, D. H., Kang, M., Lee, K. H., Choi, M., Lee, Y., & Lee, K. H. (2026). Teaching Model Context Protocol, Retrieval-Augmented Generation, and AI Agents to a Multidisciplinary Hospital Workforce: Single-Group Pre-Post Survey Study. JMIR Medical Education, 12, e97822-e97822. https://doi.org/10.2196/97822

Vancouver

Baek G, Lee H, Yang DH, Kang M, Lee KH, Choi M, et al. Teaching Model Context Protocol, Retrieval-Augmented Generation, and AI Agents to a Multidisciplinary Hospital Workforce: Single-Group Pre-Post Survey Study. JMIR Medical Education. 2026;12:e97822-e97822. doi:10.2196/97822

BibTeX
@article{Baek2026,
  author = {Baek, Gakyoung and Lee, Hyunna and Yang, Dong Hyun and Kang, Minseo and Lee, Kun Hee and Choi, Minji and Lee, Yura and Lee, Kye Hwa},
  title = {Teaching Model Context Protocol, Retrieval-Augmented Generation, and AI Agents to a Multidisciplinary Hospital Workforce: Single-Group Pre-Post Survey Study},
  journal = {JMIR Medical Education},
  year = {2026},
  volume = {12},
  pages = {e97822--e97822},
  doi = {10.2196/97822}
}
Start for free →