Actionable companion · Feedback & scaffolding

Learning with agency: Ambient Listening Devices as a Feedback Tool in the Simulated Learning Environment

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 paper Search paper agent CC 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. Verify the participant population and task before transferring the findings.

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

Introduction: The use of artificial intelligence (AI) in medical education is expanding, yet evidence supporting its role in delivering formative feedback during simulated clinical encounters remains limited. Ambient listening (AL) technology has demonstrated utility for clinical documentation but is underexplored as an educational feedback tool. This study aimed to evaluate the feasibility, perceived quality, and learner acceptance of AI-generated feedback produced by an AL transcription system during simulated patient encounters in undergraduate medical education. Materials and methods: First- and second-year medical students at a single U.S. medical school voluntarily participated in the study during their scheduled simulated patient encounters. Encounters were recorded using an AI-powered AL application. Students submitted a standardized skills rubric and predefined prompt to generate automated feedback and SMART goals following their encounter. Learners completed an anonymized post-encounter survey on the perceived quality of AI-provided feedback, using the validated Quality of Assessment for Learning index and optional free-text responses. Results: A total of 10 learner evaluations were collected. All participants reported that the AI-generated feedback provided sufficient evidence of performance, included suggestions for improvement, and linked feedback directly to observed behaviors. Qualitative responses consistently described the feedback as accurate, sustainable, and closely aligned with standardized patient feedback and learner self-assessment. Suggested areas for improvement included greater contextual awareness and more specific, example-driven feedback. Conclusions: This study is best viewed as a promising pilot study. The findings suggest AI-powered AL may serve as an easily integrated and well-accepted method for supplementing formative feedback in simulated clinical encounters. Early findings suggest it may serve as a scalable supplement to direct observation, particularly in settings with limited faculty availability. Larger, multi-institutional studies are needed to evaluate generalizability, educational impact, and effectiveness across learner levels and clinical environments.

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

First- and second-year medical students at a single U.S. medical school were recruited to the study via a mass email sent to the class-wide mailing list. Students were invited to voluntarily participate in the study, which supplemented regularly scheduled simulated patient encounters in their clinical skills course with feedback from an AL device. Students did not receive compensation for their participation in the study. Their grades and class standing were not affected by participation or non-participation. Interested students contacted the study authors via email and completed a one-hour training session on the software. During the training, students viewed a simulated patient encounter recorded by the AL technology Otter (Otter.ai, Inc., Mountain View, CA, USA). They were then instructed to enter the prewritten prompt into the AL device’s chatbot and to review the chatbot's feedback. Following the training, 10 students volunteered to participate in the study. Students provided written consent, created an Otter account, and downloaded the application to their personal mobile devices. All standardized patients (SPs) with whom participating students were scheduled to have a simulated encounter consented in writing to being recorded with the AL device. The West Virginia University Institutional Review Board issued approval 2308828386.

Limitations and uncertainty · source passage

Notably, the use of AL as a feedback mechanism may address longstanding limitations associated with DO in medical education. Although DO is widely regarded as essential for bridging the gap between knowledge and clinical performance, its implementation is often constrained by faculty time, learner discomfort, and clinical workflow pressures. Prior studies have shown that learners frequently prefer written formative feedback and that sociocultural factors can limit the effectiveness and frequency of DO in practice [11-13]. Our findings suggest that AL-generated feedback may supplement DO, providing timely, individualized written feedback without increasing faculty workload.

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.

A 90-day district pilot

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.
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.
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.
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

Robert Snedegar; Kendra Unger; Jason F Craig; Lauren Kozlowski; Devanie Carpenter; Emilee Pyles; Jonathan Williamson; Erika Bodkins; Dorian Williams. Ambient Listening Devices as a Feedback Tool in the Simulated Learning Environment. Cureus (2026-02-08). https://doi.org/10.7759/cureus.103222

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.