Actionable companion · Feedback & scaffolding

Learning with agency: Development and implementation of a MediaPipe-based AI teaching-learning model in school physical education for health promotion

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): Secondary school. Verify the participant population and task before transferring the findings.

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

Introduction Artificial intelligence (AI) technologies are increasingly used in school physical education (PE) to provide real-time feedback and support instruction that promotes youth physical activity and health. However, many AI applications remain top-down and expert-driven, focusing on technical validation in controlled settings and paying little attention to everyday school contexts or the needs of lower-fitness students. This study aimed to develop and implement a MediaPipe-based AI teaching–learning program for health-oriented middle school PE. Methods A participatory action research (PAR) design with rapid prototyping was conducted over three months in one public middle school. PE teachers and 9th-grade students participated as co-researchers and co-developers. A web-based program using MediaPipe Pose was iteratively designed to recognize selected fitness movements and provide immediate visual and auditory feedback, with QR-code access and automatic logging. Data from semi-structured group interviews, observations, teachers' reflective journals, and student-created artifacts were analyzed using thematic analysis. Results Across three PAR cycles, the prototype evolved from a simple elbow-angle counter into a system that incorporated body alignment, tracking for isometric exercises, multimodal feedback, and automatic data recording. Teachers used the program to design lesson-specific recognition rules, monitor students' exercise participation, and support individual growth. Students deepened their understanding of exercise principles and engaged in computational thinking while experimenting with movements and refining feedback conditions. Conclusions A participatory, school-based approach enabled MediaPipe-based pose estimation to be reconfigured into a pedagogically meaningful, health-oriented program for middle school PE, suggesting that AI-supported PE can contribute to more inclusive, data-supported school health promotion.

What kind of evidence is this?

Supporting AI learning science · Qualitative / mixed methods

Stage: Secondary school. 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

This study employed a collaborative and participatory approach in which teachers and students jointly engaged in the development of the AI teaching–learning model. Participants were selected through purposive sampling to recruit information-rich cases relevant to the research questions (30).

Limitations and uncertainty · source passage

This study was conducted as a qualitative case study with a small number of participants to enable in-depth exploration. Accordingly, the findings should be interpreted in terms of transferability to similar school-based contexts rather than statistical generalizability across all educational settings. In addition, because the researcher actively engaged in the research process as an insider with an established trust relationship with participants, the researcher's positionality may have influenced data generation and interpretation. Although multiple strategies were employed to enhance trustworthiness, including iterative member checking, peer debriefing, and the maintenance of an audit trail where applicable, some degree of interpretive influence cannot be entirely ruled out. The study may also be subject to contextual and sampling-related constraints, such as participants' prior interest or experience in digital tools, which could have shaped engagement with the participatory development process.

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.
Limit simultaneous instructions and unnecessary dialogue. Compare task performance and a suitable mental-effort measure; easier-feeling work is not automatically better learning.
Measure engagement separately from achievement. Check whether novelty-driven participation persists and whether it translates to independent performance.
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

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. Ask learners to attempt a problem unaided, compare an agent hint, explain a revision and verify the final reasoning against a trusted source. Make the permitted use explicit for each assignment. 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. Measure unaided transfer and delayed retention, calibration of confidence and the ability to identify an incorrect AI explanation. Record whether help-seeking becomes answer copying. 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

Donghyun Kim; Yongchul Kwon; Gunsang Cho; Minseo Kang. Development and implementation of a MediaPipe-based AI teaching-learning model in school physical education for health promotion. Frontiers in Public Health (2026-03-20). https://doi.org/10.3389/fpubh.2026.1786427

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.