Agentic education · Learning science

Actionable companion · Feedback & scaffolding

Learning with agency: Development of a Clinical Clerkship Mentor Using Generative AI and Evaluation of Its Effectiveness in a Medical Student Trial Compared to Student Mentors: 2-Part Comparative Study

AI-assisted editorial implementation guide, separate from the original research. Proposed actions are not claims or recommendations attributed to the source authors. No independent peer review of this guide is asserted.

Read original paperSearch paper agentCC BY 4.0

Evidence and context

Title and abstract screening; stage labels describe reported settings, not verified numerical ages. Design labels require full-text appraisal. Reported stage(s): Higher education. Health-professions learning must be distinguished from K–12 instruction.

Original authors’ abstract, reproduced under the linked source license:

Abstract Background At the beginning of their clinical clerkships (CCs), medical students face multiple challenges related to acquiring clinical and communication skills, building professional relationships, and managing psychological stress. While mentoring and structured feedback are known to provide critical support, existing systems may not offer sufficient and timely guidance owing to the faculty’s limited availability. Generative artificial intelligence, particularly large language models, offers new opportunities to support medical education by providing context-sensitive responses. Objective This study aimed to develop a generative artificial intelligence CC mentor (AI-CCM) based on ChatGPT and evaluate its effectiveness in supporting medical students’ clinical learning, addressing their concerns, and supplementing human mentoring. The secondary objective was to compare AI-CCM’s educational value with responses from senior student mentors. Methods We conducted 2 studies. In study 1, we created 5 scenarios based on challenges that students commonly encountered during CCs. For each scenario, 5 senior student mentors and AI-CCM generated written advice. Five medical education experts evaluated these responses using a rubric to assess accuracy, practical utility, educational appropriateness (5-point Likert scale), and safety (binary scale). In study 2, a total of 17 fourth-year medical students used AI-CCM for 1 week during their CCs and completed a questionnaire evaluating its usefulness, clarity, emotional support, and impact on communication and learning (5-point Likert scale) informed by the technology acceptance model. Results All results indicated that AI-CCM achieved higher mean scores than senior student mentors. AI-CCM responses were rated higher in educational appropriateness (4.2, SD 0.7 vs 3.8, SD 1.0; P=.001). No significant differences with senior student mentors were observed in accuracy (4.4, SD 0.7 vs 4.2, SD 0.9; P=.11) or practical utility (4.1, SD 0.7 vs 4.0, SD 0.9; P=.35). No safety concerns were identified in AI-CCM responses, whereas 2 concerns were noted in student mentors’ responses. Scenario-specific analysis revealed that AI-CCM performed substantially better in emotional and psychological stress scenarios. In the student trial, AI-CCM was rated as moderately useful (mean usefulness score 3.9, SD 1.1), with positive evaluations for clarity (4.0, SD 0.9) and emotional support (3.8, SD 1.1). However, aspects related to feedback guidance (2.9, SD 0.9) and anxiety reduction (3.2, SD 1.0) received more neutral ratings. Students primarily consulted AI-CCM regarding learning workload and communication difficulties; few students used it to address emotional stress–related issues. Conclusions AI-CCM has the potential to serve as a supplementary educational partner during CCs, offering comparable support to that of senior student mentors in structured scenarios. Despite challenges of response latency and limited depth in clinical content, AI-CCM was received well by and accessible to students who used ChatGPT’s free version. With further refinements, including specialty-specific content and improved responsiveness, AI-CCM may serve as a scalable, context-sensitive support system in clinical medical education. Keywords: artificial intelligence, AI, mentoring, clinical clerkship, medical students, social support

What kind of evidence is this?

Supporting AI learning science · Evidence synthesis

Stage: Higher education. Screening labels describe reported context and study-design language. They are not a risk-of-bias rating or proof of effectiveness for an age band.

Study methods · source passage

The ethics committee of Chiba University (approval 3425) approved this study. The study database was anonymized. Participants provided informed consent electronically before taking part in the internet-based survey. Participants did not receive any financial or other compensation for their participation. All methods were conducted in accordance with the relevant guidelines and regulations.

Limitations and uncertainty · source passage

This study has some limitations. First, it included few participants from a single Japanese medical school, which introduces potential bias related to the sample size, region, and curriculum. In addition, participants were drawn from a single cohort at 1 institution based on availability during their clerkships, which introduces the possibility of selection bias due to the use of convenience sampling. This may limit the generalizability of the findings to other settings or student populations. Second, the trial period was short, and the long-term effects or educational impacts of AI-CCM could not be assessed. As this was a preliminary study, further research involving a larger and more diverse group of students and long-term observations will be necessary. Third, AI-CCM use logs were not comprehensively reviewed during the trial phase. Therefore, the types of questions that the students asked and the responses they received remain unclear. As gAI does not produce uniform answers, future evaluations should include a detailed log analysis to ensure the consistency and appropriateness of interactions. Fourth, both the questionnaire used during the trial and the rubric used to evaluate mentor responses were not formally validated in terms of reliability or construct validity. Although the questionnaire and rubric were developed based on the specific research objectives of this study and refined through consultation with experts in medical education, no interrater reliability testing or statistical validation procedures were conducted. Fifth, although evaluator blinding was implemented, the distinct linguistic patterns of AI-generated responses may have allowed scorers to infer their source. While efforts were made to match the tone and length of AI and student responses to reduce this risk, complete blinding could not be guaranteed. This potential identification bias remains a methodological limitation. Sixth, this study did not assess the variability of AI-CCM’s responses across different users, prompts, or repeated trials. As gAI may produce different outputs depending on context or phrasing, a lack of replication or repeated testing limits the evaluation of the system’s stability and reproducibility. Future research should incorporate multiple iterations of chatbot responses to better understand the consistency and generalizability of its educational value.

Design the system before the pilot

Use this study to inform a learning mechanism or implementation question. It is not direct evidence that autonomous agents improve learning. Keep the proposed agent behavior separate from what the source actually tested.

  • Give feedback on the learner’s reasoning, then fade hints. Record whether the learner can complete the next task without that scaffold.
  • Use common rubrics, blind scoring where feasible and a fresh unaided reasoning task. Document permissible assistance and avoid treating AI-detector scores as proof of misconduct.
  • Co-design accommodations with learners and specialists. Check access and error burden across groups without inferring subgroup effectiveness from small or unreported samples.

A 90-day district pilot

  1. Days 1–15 · Appraise. Have the curriculum lead and a teacher read the methods and limitations. Record the study design, sample, comparator, outcomes and evidence gaps. Define a local question that the study can help inform.
  2. Days 16–30 · Design. Choose one disciplinary task. Require a first attempt, a documented AI consultation, a critique of the output and an independent explanation. Align the comparison group and scoring rubric with the same objective. Name an accountable owner and set the baseline, success threshold and budget before implementation.
  3. Days 31–60 · Test. Start with a small voluntary cohort, preserve an accessible non-AI route and require teacher review. Use synthetic or de-identified examples; approve data handling and tool terms through district processes.
  4. Days 61–90 · Decide. Blind-score reasoning and accuracy on a new task without AI. Distinguish model examination scores, student perceptions and actual learner gains; only the last directly tests educational benefit. Compare with baseline, document uncertainty and stop or revise if learning worsens, access is unequal or critical errors persist.

The board decision brief

Report the learning problem, evidence quality, participating population, total cost including review time, measured benefit, errors, access differences and remaining uncertainties. Make a dated recommendation to stop, revise or expand. A positive perception survey alone does not establish learning improvement.

Attribution and reuse

Hayato Ebihara; Hajime Kasai; Ikuo Shimizu; Kiyoshi Shikino; Hiroshi Tajima; Yasuhiko Kimura; Shoichi Ito. Development of a Clinical Clerkship Mentor Using Generative AI and Evaluation of Its Effectiveness in a Medical Student Trial Compared to Student Mentors: 2-Part Comparative Study. JMIR Medical Education (2025-09-04). https://doi.org/10.2196/76702

Companion prepared 2026-10-30. Original authorship and DOI are preserved. The abstract is an attributed source extract; the implementation plan is new AI-assisted editorial material, offered under the same CC BY 4.0 license. This guide has not undergone independent peer review.