Agentic education · Learning science

Actionable companion · Feedback & scaffolding

Learning with agency: Artificial Intelligence Chatbots as Virtual Patients in Dental Education: A Constructivist Approach to Classroom Implementation

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. Health-professions learning must be distinguished from K–12 instruction.

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

ABSTRACT Introduction Advances in artificial intelligence (AI) have led to new possibilities for AI role‐play in classroom settings, where generative pre‐trained transformers (GPTs) and chatbots can potentially simulate interactions with patients. This pilot study aimed to design an AI role‐play activity underpinned by constructivist principles, implement the activity in a classroom setting, and evaluate the students' engagement with the activity and usability of the interface. Materials and Methods The AI role‐play was designed based on a patient presenting to a dental teaching hospital in pain. It comprised two interconnected chatbots intended to simulate a patient consultation and clinical supervisor discussion. The chatbots were built using the open‐source framework Streamlit and powered by Chat GPT‐4. Second and final‐year students from an oral health degree were recruited through convenience sampling. Classroom observations were recorded and final‐year students participated in a usability questionnaire to gain insights into their engagement, technical challenges, and suggestions for improvement. Data usage and token costs were collected to assess the AI chatbot's feasibility. Results Educator observations noted that AI role‐play facilitated peer discussion, highlighted gaps in history‐taking, and promoted peer learning. Usability survey feedback (n = 14) suggested that students perceived the AI role‐play as authentic and relevant to clinical practice, with 86% strongly agreeing it aligned with real‐world dental scenarios. The screen design, navigation, and multimedia integration were highly rated. The approximate costs for the activities were $13.17 (USD) for approximately 20 queries, per 20 students. Conclusion This study presents a descriptive analysis of the implementation of an AI role‐play within the early phases of a design‐based research framework. AI role‐play activities can be implemented in a classroom setting and are perceived as useful for students to apply skills in taking a pain history. While results showed promise for scalability and authentic learning, future research evaluating the impact of the implementation of these activities on student learning should be explored.

What kind of evidence is this?

Conversational & pedagogical agents · Survey / observational study

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

We employed a design‐based research (DBR) approach, which allows for iterative cycles of design, implementation, and evaluation of educational interventions in real‐world classroom settings [29]. We opted for DBR due to its emphasis on the systematic design and redesign of educational interventions, particularly ones involving technology. This study represents the first few iterations of the activity, where we describe the initial piloting and testing of the AI role‐play in a classroom setting and design improvements to optimise the activity, establishing a foundation knowledge for subsequent cycles of refinement and evaluation.

Limitations and uncertainty · source passage

However, a significant challenge for AI tutors involves “hallucinations” from large language models (LLMs): incorrect or nonsensical responses that deviate from factual accuracy. This issue often stems from limitations in the model's training data, misinterpretation of user input, or incomplete and ambiguous inputs [18].

Design the system before the pilot

Define whether the agent asks questions, gives hints, explains or assesses. Test hallucinated feedback, excessive praise, misleading confidence and responses when the learner is confused. A conversational interface alone does not establish autonomous agency.

  • Give feedback on the learner’s reasoning, then fade hints. Record whether the learner can complete the next task without that scaffold.
  • Measure engagement separately from achievement. Check whether novelty-driven participation persists and whether it translates to independent performance.
  • 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

  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

Bree Jones; Aditya Desu; Christopher D. F. Honig. Artificial Intelligence Chatbots as Virtual Patients in Dental Education: A Constructivist Approach to Classroom Implementation. European Journal of Dental Education (2025-06-03). https://doi.org/10.1111/eje.13135

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.