Vibe-coding as a Teaching Competency in the Use of Artificial Intelligence for Medical Education: A Scoping Review

Introduction: The emergence of Generative Artificial Intelligence has given rise to vibe-coding, a paradigm that allows educators without technical backgrounds to develop software using natural language. This advancement necessitates redefining the teaching competencies required to transition from users to creators of educational tools. Methods: A scoping review of the literature was conducted following PRISMA-ScR guidelines. Studies retrieved from Web of Science and Scopus databases addressing the use of vibe-coding by educators in higher and medical education were included. After the selection process, four publications from 2025 were included. A deductive reflexive thematic analysis was applied to classify findings according to the TPACK model dimensions (Technological, Pedagogical, and Content Knowledge). Results: Qualitative analysis reveals a reconfiguration of Technological Knowledge (TK), which dissociates from programming syntax to focus on structuring prompts and iterative dialogue with AI. The emergence of the “clinician-developer” role was identified, where Content Knowledge (CK) acts as an indispensable auditing mechanism to validate clinical accuracy and prevent hallucinations in generated algorithms. Technological-Pedagogical Knowledge (TPK) enabled educators to deconstruct complex logic into sequential steps to design simulators and personalized tools. Conclusions: Preliminary evidence suggests that vibe-coding democratizes educational software development, allowing educators to materialize complex pedagogical strategies without external technical dependence. This competency appears to demand robust disciplinary mastery to guarantee the safety and quality of the created resources. It is recommended to foster training in this emerging competency and conduct future empirical studies to evaluate the impact of these tools on student learning and teacher cognitive load.