Agentic education · Learning science

Actionable companion · Learning design & outcomes

Learning with agency: ChatGPT (GPT-3.5) as an assistant tool in microbial pathogenesis studies in Sweden: a cross-sectional 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. Verify the participant population and task before transferring the findings.

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

Abstract ChatGPT (GPT-3.5) has entered higher education and there is a need to determine how to use it effectively. This descriptive study compared the ability of GPT-3.5 and teachers to answer questions from dental students and construct detailed intended learning outcomes. When analyzed according to a Likert scale, we found that GPT-3.5 answered the questions from dental students in a similar or even more elaborate way compared to the answers that had previously been provided by a teacher. GPT-3.5 was also asked to construct detailed intended learning outcomes for a course in microbial pathogenesis, and when these were analyzed according to a Likert scale they were, to a large degree, found irrelevant. Since students are using GPT-3.5, it is important that instructors learn how to make the best use of it both to be able to advise students and to benefit from its potential. Keywords: Artificial intelligence, Dental students, Educational personnel, Microbiology, Sweden

What kind of evidence is this?

Supporting AI learning science · Survey / observational study

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

This cross-sectional comparison study was conducted to compare the ability of GPT-3.5 and teachers to answer questions from dental students and construct detailed intended learning outcomes.

Limitations and uncertainty · source passage

There are limitations in the study concerning the small number of questions that were used to evaluate ChatGPT3.5’s capacity to reply correctly and guide students in the field. Most questions concerned basic microbiology or immunology, which are well-known fields for which replies may be easier than for a narrower subject such as oral microbiology. This was evident when GPT-3.5 was used to create new detailed intended learning outcomes. Furthermore, the instructions given to GPT-3.5 might have been incomplete, which could have influenced the outcome. When given proper instructions, we believe that GPT-3.5 can be useful and important for other subjects, both in teaching and learning.

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.

  • Specify a measurable learning objective, a comparator and a task without tool assistance before adopting a system.

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

Catharina Hultgren; Annica Lindkvist; Volkan Özenci; Sophie Curbo. ChatGPT (GPT-3.5) as an assistant tool in microbial pathogenesis studies in Sweden: a cross-sectional comparative study. Journal of Educational Evaluation for Health Professions (2023-11-22). https://doi.org/10.3352/jeehp.2023.20.32

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.