Agentic education · Learning science

Actionable companion · Feedback & scaffolding

Learning with agency: Generative Artificial Intelligence as a Tool for Teaching Communication in Nutrition and Dietetics Education—A Novel Education Innovation

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): Age / stage not established. Verify the participant population and task before transferring the findings.

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

Abstract Although effective communication is fundamental to nutrition and dietetics practice, providing novice practitioners with efficacious training remains a challenge. Traditionally, human simulated patients have been utilised in health professions training, however their use and development can be cost and time prohibitive. Presented here is a platform the authors have created that allows students to interact with virtual simulated patients to practise and develop their communication skills. Leveraging the structured incorporation of large language models, it is designed by pedagogical content experts and comprises individual cases based on curricula and student needs. It is targeted towards the practice of rapport building, asking of difficult questions, paraphrasing and mistake making, all of which are essential to learning. Students appreciate the individualised and immediate feedback based on validated communication tools that encourage self-reflection and improvement. Early trials have shown students are enthusiastic about this platform, however further investigations are required to determine its impact as an experiential communication skills tool. This platform harnesses the power of artificial intelligence to bridge the gap between theory and practice in communication skills training, requiring significantly reduced costs and resources than traditional simulated patient encounters. Keywords: artificial intelligence, education, communication, simulated patients, dietetics

What kind of evidence is this?

Supporting AI learning science · Design requires full-text appraisal

Stage: Age / stage not established. 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

ATLAS is a voice to chat based platform that harnesses state-of-the-art large language models, artificial intelligence and educator designed patient personas to simulate real-world HSPs. The interface operates through a series of interconnected processes, beginning with the student’s spoken input. This input is captured and translated into text using speech-to-text algorithms. The text is then fed, together with detailed persona data and the conversational history, into a large language model. Next, the model generates a contextually appropriate response that moves the conversation logically forward in a way that aligns with the persona’s characteristics and the educational objectives of the simulation. Finally, the response is returned to the student as synthesised speech, together with a textual description of the patient’s body language. This unique platform was created to replicate learning from HSP interactions multiple times during course progression with varying cases and personas. This interface is shown pictorially in Figure 2.

Limitations and uncertainty · source passage

Although this technology is rapidly developing, limitations to VSPs do exist. A broader diversity of patient portrayals has not yet been researched to assess cultural competence and safety. Learning experiences should not reinforce biases, therefore AI identities should be three dimensional and avoid stereotyping [20]. Having the personas designed and tested by people with a shared lived experience may ensure this, and reduce the bias inherent in commercial large language models. This is in line with patient-centred care principles, which calls for patient involvement in education design [21]. Further research in this area is required. There is also a need to ensure that simulations are pedagogically sound and are accompanied by measures of quality and impact on learning to build evidence that harnessing generative artificial intelligence as a communication tool in health professions education is effective. For example, the ATLAS VSPs should be compared with other active learning methods [22], with such a study currently being undertaken by these authors. Finally, there are important ethical considerations in the development of AI technology, such as data protection for students [23].

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.

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. Treat the paper as background evidence until its population is verified in the full text. Do not assign an age-specific intervention or extend adult results to children. 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. Extract the participant ages or education stage, recruitment, task and comparator before selecting a local pilot. If these cannot be established, retain the paper for design discussion rather than age-band efficacy claims. 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

Lisa A Barker; Joel D Moore; Helmy A Cook. Generative Artificial Intelligence as a Tool for Teaching Communication in Nutrition and Dietetics Education—A Novel Education Innovation. Nutrients (2024-03-22). https://doi.org/10.3390/nu16070914

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.