{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T22:10:18Z","timestamp":1789164618264,"version":"build-2803163510"},"reference-count":43,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Educ"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n 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.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n 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\u2019 own reflections on their learning experience.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n 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\u20106 hours of weekly mentoring per team. A pre-post survey (pre: n=83; post: n=64) evaluated outcomes across Kirkpatrick levels 1\u20103, complemented by thematic analysis of open-ended reflections on self-perceived growth.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n The technologies that received the greatest curricular investment were associated with the largest self-efficacy differences (MCP:\n d<\/jats:italic>\n =1.57; overall effect:\n r<\/jats:italic>\n =.574), and participants most frequently cited MCP and RAG when describing how abstract concepts \u201cbecame concrete and actionable.\u201d 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.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n 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.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/97822","type":"journal-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T17:35:09Z","timestamp":1783704909000},"page":"e97822-e97822","source":"Crossref","is-referenced-by-count":0,"title":["Teaching Model Context Protocol, Retrieval-Augmented Generation, and AI Agents to a Multidisciplinary Hospital Workforce: Single-Group Pre-Post Survey Study"],"prefix":"10.2196","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1902-5203","authenticated-orcid":false,"given":"Gakyoung","family":"Baek","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1669-3086","authenticated-orcid":false,"given":"Hyunna","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5477-558X","authenticated-orcid":false,"given":"Dong Hyun","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7145-9272","authenticated-orcid":false,"given":"Minseo","family":"Kang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5089-7608","authenticated-orcid":false,"given":"Kun Hee","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8629-7881","authenticated-orcid":false,"given":"Minji","family":"Choi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2048-3727","authenticated-orcid":false,"given":"Yura","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7593-7020","authenticated-orcid":false,"given":"Kye Hwa","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"R1","doi-asserted-by":"publisher","DOI":"10.2196\/58329","article-title":"Evaluation framework of large language models in medical documentation: development and usability study","volume":"26","author":"Seo","journal-title":"J Med Internet Res"},{"issue":"1","key":"R2","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1038\/s41591-018-0300-7","article-title":"High-performance medicine: the convergence of human and artificial intelligence","volume":"25","author":"Topol","journal-title":"Nat Med"},{"issue":"8","key":"R3","doi-asserted-by":"publisher","first-page":"1930","DOI":"10.1038\/s41591-023-02448-8","article-title":"Large language models in medicine","volume":"29","author":"Thirunavukarasu","journal-title":"Nat Med"},{"issue":"1","key":"R4","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1038\/s41591-018-0307-0","article-title":"The practical implementation of artificial intelligence technologies in medicine","volume":"25","author":"He","journal-title":"Nat Med"},{"key":"R5","unstructured":"Lewis P Perez E Piktus A Petroni F Karpukhin V Goyal N et al. Retrieval-augmented generation for knowledge-intensive NLP tasks. Presented at: 34th Conference on Neural Information Processing Systems (NeurIPS 2020); Dec 6-12, 2020:9459-9474; 2020.URL: https:\/\/proceedings.neurips.cc\/paper\/2020\/file\/6b493230205f780e1bc26945df7481e5-Paper.pdf [Accessed 21-07-2026]"},{"key":"R6","unstructured":"What is the model context protocol (MCP)? Model Context Protocol. 2024. URL: https:\/\/modelcontextprotocol.io\/ [Accessed 08-09-2025]"},{"key":"R7","unstructured":"LangGraph overview. LangChain Docs. 2024. URL: https:\/\/docs.langchain.com\/oss\/python\/langgraph\/overview [Accessed 08-09-2025]"},{"issue":"6","key":"R8","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare11060887","article-title":"ChatGPT utility in healthcare education, research, and practice: systematic review on the promising perspectives and valid concerns","volume":"11","author":"Sallam","journal-title":"Healthcare (Basel)"},{"key":"R9","doi-asserted-by":"publisher","DOI":"10.1016\/j.caeai.2022.100101","article-title":"Artificial intelligence literacy in higher and adult education: a scoping literature review","volume":"3","author":"Laupichler","journal-title":"Comput Educ Artif Intell"},{"issue":"4","key":"R10","doi-asserted-by":"publisher","first-page":"446","DOI":"10.1080\/0142159X.2024.2314198","article-title":"A scoping review of artificial intelligence in medical education: BEME Guide No. 84","volume":"46","author":"Gordon","journal-title":"Med Teach"},{"key":"R11","doi-asserted-by":"publisher","DOI":"10.2196\/52483","article-title":"Embracing ChatGPT for medical education: exploring its impact on doctors and medical students","volume":"10","author":"Wu","journal-title":"JMIR Med Educ"},{"key":"R12","doi-asserted-by":"publisher","DOI":"10.2196\/49385","article-title":"Health care trainees\u2019 and professionals\u2019 perceptions of ChatGPT in improving medical knowledge training: rapid survey study","volume":"25","author":"Hu","journal-title":"J Med Internet Res"},{"key":"R13","doi-asserted-by":"publisher","DOI":"10.2196\/50658","article-title":"Using ChatGPT for clinical practice and medical education: cross-sectional survey of medical students\u2019 and physicians\u2019 perceptions","volume":"9","author":"Tangadulrat","journal-title":"JMIR Med Educ"},{"issue":"1","key":"R14","doi-asserted-by":"publisher","DOI":"10.2196\/19285","article-title":"Artificial intelligence education and tools for medical and health informatics students: systematic review","volume":"6","author":"Sapci","journal-title":"JMIR Med Educ"},{"key":"R15","doi-asserted-by":"publisher","DOI":"10.2196\/48785","article-title":"Opportunities, challenges, and future directions of generative artificial intelligence in medical education: scoping review","volume":"9","author":"Preiksaitis","journal-title":"JMIR Med Educ"},{"issue":"4","key":"R16","doi-asserted-by":"publisher","DOI":"10.2196\/31043","article-title":"Artificial intelligence education programs for health care professionals: scoping review","volume":"7","author":"Charow","journal-title":"JMIR Med Educ"},{"issue":"5","key":"R17","doi-asserted-by":"publisher","first-page":"524","DOI":"10.1097\/ACM.0000000000005618","article-title":"Defining medical AI competencies for medical school graduates: outcomes of a delphi survey and medical student\/educator questionnaire of South Korean medical schools","volume":"99","author":"Lee","journal-title":"Acad Med"},{"key":"R18","doi-asserted-by":"publisher","DOI":"10.2196\/54427","article-title":"Impact of health informatics analyst education on job role, career transition, and skill development: survey study","volume":"10","author":"Lee","journal-title":"JMIR Med Educ"},{"key":"R19","unstructured":"Bandura A . Self-Efficacy: The Exercise of Control. W.H. Freeman; 1997. ISBN: 9780716728504"},{"issue":"2","key":"R20","doi-asserted-by":"publisher","first-page":"189","DOI":"10.2307\/249688","article-title":"Computer self-efficacy: development of a measure and initial test","volume":"19","author":"Compeau","journal-title":"MIS Q"},{"issue":"3","key":"R21","doi-asserted-by":"publisher","first-page":"319","DOI":"10.2307\/249008","article-title":"Perceived usefulness, perceived ease of use, and user acceptance of information technology","volume":"13","author":"Davis","journal-title":"MIS Q"},{"issue":"3","key":"R22","doi-asserted-by":"publisher","first-page":"425","DOI":"10.2307\/30036540","article-title":"User acceptance of information technology: toward a unified view1","volume":"27","author":"Venkatesh","journal-title":"MIS Q"},{"key":"R23","unstructured":"Kolb DA . Experiential Learning: Experience as the Source of Learning and Development. 2nd ed. Pearson Education; 2015. ISBN: 9780133892406"},{"issue":"11","key":"R24","first-page":"9","volume":"31","author":"Kirkpatrick","journal-title":"Train Dev J"},{"key":"R25","unstructured":"Kirkpatrick JD Kirkpatrick WK . Kirkpatrick\u2019s Four Levels of Training Evaluation. ATD Press; 2016. ISBN: 9781607280088"},{"issue":"1","key":"R26","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1111\/j.1365-2923.2011.04076.x","article-title":"Kirkpatrick\u2019s levels and education \u201cevidence\u201d","volume":"46","author":"Yardley","journal-title":"Med Educ"},{"key":"R27","doi-asserted-by":"publisher","DOI":"10.2147\/AMEP.S372652","article-title":"Implementing faculty development programs in medical education utilizing Kirkpatrick\u2019s model","volume":"13","author":"Alhassan","journal-title":"Adv Med Educ Pract"},{"issue":"9596","key":"R28","doi-asserted-by":"publisher","first-page":"1453","DOI":"10.1016\/S0140-6736(07)61602-X","article-title":"The Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) statement: guidelines for reporting observational studies","volume":"370","author":"von Elm","journal-title":"Lancet"},{"issue":"6","key":"R29","doi-asserted-by":"publisher","first-page":"186345","DOI":"10.1007\/s11704-024-40231-1","article-title":"A survey on large language model based autonomous agents","volume":"18","author":"Wang","journal-title":"Front Comput Sci"},{"key":"R30","doi-asserted-by":"crossref","unstructured":"Hollander M Wolfe DA Chicken E . Nonparametric Statistical Methods. 3rd ed. John Wiley & Sons; 2014. [doi: 10.1002\/9781119196037]","DOI":"10.1002\/9781119196037"},{"key":"R31","doi-asserted-by":"crossref","unstructured":"Rosenthal R . Meta-Analytic Procedures for Social Research. Sage; 1991. ISBN: 9780803942462","DOI":"10.4135\/9781412984997"},{"key":"R32","unstructured":"Cohen J . Statistical Power Analysis for the Behavioral Sciences. 2nd ed. Lawrence Erlbaum Associates; 1988. ISBN: 9780805802832"},{"key":"R33","unstructured":"Nunnally JC Bernstein IH . Psychometric Theory. 3rd ed. McGraw-Hill; 1994. ISBN: 9780070478497"},{"key":"R34","doi-asserted-by":"publisher","DOI":"10.2196\/48633","article-title":"Barriers to and facilitators of artificial intelligence adoption in health care: scoping review","volume":"11","author":"Hassan","journal-title":"JMIR Hum Factors"},{"issue":"11","key":"R35","doi-asserted-by":"publisher","DOI":"10.2196\/jmir.8775","article-title":"Beyond adoption: a new framework for theorizing and evaluating nonadoption, abandonment, and challenges to the scale-up, spread, and sustainability of health and care technologies","volume":"19","author":"Greenhalgh","journal-title":"J Med Internet Res"},{"key":"R36","doi-asserted-by":"crossref","unstructured":"Pfeffer J Sutton RI . The Knowing-Doing Gap: How Smart Companies Turn Knowledge into Action. Harvard Business School Press; 2000. [doi: 10.1108\/scm.2001.6.3.142.1]","DOI":"10.1108\/scm.2001.6.3.142.1"},{"key":"R37","doi-asserted-by":"publisher","DOI":"10.1186\/1748-5908-7-50","article-title":"Knowledge translation of research findings","volume":"7","author":"Grimshaw","journal-title":"Implement Sci"},{"issue":"3","key":"R38","doi-asserted-by":"publisher","DOI":"10.2196\/28275","article-title":"Digital health training programs for medical students: scoping review","volume":"7","author":"Tudor Car","journal-title":"JMIR Med Educ"},{"key":"R39","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2022.990604","article-title":"Acceptance of clinical artificial intelligence among physicians and medical students: a systematic review with cross-sectional survey","volume":"9","author":"Chen","journal-title":"Front Med (Lausanne)"},{"issue":"2","key":"R40","doi-asserted-by":"publisher","first-page":"E146","DOI":"10.1001\/amajethics.2019.146","article-title":"Reimagining medical education in the age of AI","volume":"21","author":"Wartman","journal-title":"AMA J Ethics"},{"issue":"5","key":"R41","doi-asserted-by":"publisher","first-page":"435","DOI":"10.1177\/0193841X08316676","article-title":"The use of self-generated identification codes in longitudinal research","volume":"32","author":"Yurek","journal-title":"Eval Rev"},{"issue":"5","key":"R42","doi-asserted-by":"publisher","first-page":"879","DOI":"10.1037\/0021-9010.88.5.879","article-title":"Common method biases in behavioral research: a critical review of the literature and recommended remedies","volume":"88","author":"Podsakoff","journal-title":"J Appl Psychol"},{"issue":"2","key":"R43","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1177\/1529100612436661","article-title":"The science of training and development in organizations: what matters in practice","volume":"13","author":"Salas","journal-title":"Psychol Sci Public Interest"}],"container-title":["JMIR Medical Education"],"original-title":[],"language":"en","deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T21:22:06Z","timestamp":1789161726000},"score":1,"resource":{"primary":{"URL":"https:\/\/mededu.jmir.org\/2026\/1\/e97822"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,11]]},"references-count":43,"URL":"https:\/\/doi.org\/10.2196\/97822","relation":{},"ISSN":["2369-3762"],"issn-type":[{"value":"2369-3762","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,11]]},"article-number":"v12i1e97822"}}