Evidence, prompts, checklists, and practical interpretation for assessment, feedback, scoring, and teaching materials.
Curator note
Current evidence suggests AI may support first-draft generation of assessment materials, but quality, alignment, and validity claims depend heavily on human review.
Subquestions
AI can produce rapid first drafts of MCQs when given input such as source content, learning objectives, item format. AI should not be treated as an autonomous item writer. The current evidence supports human-in-the-loop item development, not unsupervised use in summative or high-stakes exams.
More info and selected evidenceAI can produce structured first drafts of key-feature questions when given a clinical problem, candidate level, patient age group, clinical situation, site of care, and a reference guideline. AI should not be treated as an autonomous KFQ writer. The current evidence supports human-in-the-loop KFQ development, not unsupervised use in summative or high-stakes exams.
More info and selected evidenceAI can produce rapid first drafts of Script Concordance Test (SCT) items when given a structured prompt, target learner level, clinical topic, and assessment focus. AI should not be treated as an autonomous SCT writer. The current evidence supports human-in-the-loop SCT development, not unsupervised use in summative or high-stakes assessment.
More info and selected evidenceAI can generate first drafts of Concordance of Professional Judgment items across a locally defined ethics framework using a structured zero-shot prompt.
More info and selected evidenceContribute
If you have or know a source article, prompt, guide, or practical tool related to this question area, you can suggest it for review. Suggested sources are curated before inclusion; not every submission will be added, especially when a source is already covered by an included synthesis such as a systematic review or does not fit the scope.