Beyond the tool: what a course-aligned AI assistant reveals about student learning in microbiology
Year: 2026
Type: article
Abstract: Course-aligned artificial intelligence (AI) tutors are increasingly offered as learning support in higher education. Beyond providing practice and feedback, they may also help teachers identify gaps in understanding across a cohort. In a second-year medical microbiology and immunology unit of 500 to 800 students, a course-aligned AI assistant built on The University of Sydney’s Cogniti platform gave students scenario-based short-answer practice with rubric-referenced feedback. Its conversation logs turned out to be a diagnostic instrument. Across more than 1300 conversations, the logs revealed cohort-level knowledge gaps and recurring terminology errors mid-semester. An exploratory analysis also found small positive correlations between practice-oriented use of the assistant and final short-answer marks, although these findings should be interpreted cautiously. The gaps were fed back to the class through an interactive revision resource used in lectures. These insights could be obtained through three approaches requiring different levels of technical expertise: the platform’s own no-code summaries, method-led coding with basic programming, and specialist computational analysis. We also discuss how the approach can be adapted where no equivalent platform exists. The project highlights that a course-aligned AI assistant can provide valuable insight into cohort-level understanding of the subject.
Source: Microbiology Australia
DOI: 10.1071/ma26055
Institution: The University of Sydney
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: diamond
Funder: University of Sydney
OpenAlex ID: W7234826385
