TRV-2026-3034Version 1 · Published

Saved · see the current record

Why this version exists

Certified into the record

The exact text we saved

This is the version exactly as it was saved, character for character. The SHA-256 hash below is a 64-character code worked out from that text. Run the same text through SHA-256 and you get the same code; change a single letter and the code comes out completely different. Each version also stores the previous version’s hash, which chains them together so no version can be swapped out quietly.

TRUVACE RECORD VERSION
record: TRV-2026-3034
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-11-18T18:01:55.488849Z
status: published
lens: g_space
sector: education
headline: Beyond the tool: what a course-aligned AI assistant reveals about student learning in microbiology
dek: 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…
gain_title: In a University of Sydney microbiology and immunology unit of 500 to 800 students, logs from more than 1300 conversations with a Cogniti-based AI assistant revealed cohort-level knowledge gaps and recurring terminology errors mid-semester, which teachers fed back to the class.
problem_title: (none)
trace_subject: (none)
gain_reading: In a University of Sydney microbiology and immunology unit of 500 to 800 students, logs from more than 1300 conversations with a Cogniti-based AI assistant revealed cohort-level knowledge gaps and recurring terminology errors mid-semester, which teachers fed back to the class.
gain_evidence: Across more than 1300 conversations, the logs revealed cohort-level knowledge gaps and recurring terminology errors mid-semester. | The gaps were fed back to the class through an interactive revision resource used in lectures.
problem_reading: (none)
problem_evidence: (none)
quick_read: Teachers of a second-year medical microbiology and immunology unit at the University of Sydney, with 500 to 800 students, gave students a course-aligned AI assistant built on the Cogniti platform. It offered scenario-based short-answer practice with feedback tied to a rubric.

Across more than 1300 conversations, the logs showed knowledge gaps across the cohort and recurring terminology errors partway through the semester. Teachers used the findings to build an interactive revision resource for lectures.

An exploratory analysis found small positive correlations between practice-oriented use of the assistant and final short-answer marks, though the authors say this should be interpreted cautiously.
limitation: The link between practice-oriented use of the assistant and final short-answer marks was exploratory, small and correlational, so the authors say it should be interpreted cautiously.
tag: Evidence-backed gain
key_points: The assistant was built on The University of Sydney's Cogniti platform and aligned to the course. | Students practised scenario-based short-answer questions and received rubric-referenced feedback. | More than 1300 conversations were analysed, revealing cohort-level gaps and recurring terminology errors mid-semester. | Exploratory analysis found small positive correlations between practice-oriented use and final short-answer marks. | Insights could be obtained through no-code platform summaries, method-led coding with basic programming, or specialist computational analysis. | The authors also discuss adapting the approach where no equivalent platform exists.
rundown: The unit enrolled 500 to 800 students. The AI assistant gave them practice scenarios and feedback against a marking rubric, and its conversation logs became a way to see what the whole class found difficult.

Three analysis routes were described, requiring different technical skill: the platform's own no-code summaries, method-led coding with basic programming, and specialist computational analysis. This lets teachers without data expertise still use the logs.

Findings were returned to students through an interactive revision resource used in lectures. The reported link between practice-oriented use and final short-answer marks was small and exploratory.
sources:
- peer_reviewed | Microbiology Australia | https://doi.org/10.1071/ma26055 | 2026-11-18
prev: 0000000000000000000000000000000000000000000000000000000000000000
SHA-256 hash
0d9195edb8701f4f97f8cd8c0cb805a1305382d92fc922383935651d3d0c2b3f
Previous version’s hash
0000000000000000000000000000000000000000000000000000000000000000
Check this record hasn’t been altered
How to check it yourself, without trusting this page

Download any version from /api/record/TRV-2026-3034 and hash its canonical field yourself, for example with shasum -a 256. You should get its content_hash. Each version’s text also ends with prev:and the hash of the version before it (version 1 points to 64 zeros). If anyone had changed a single character of any version after it was saved, those hashes wouldn’t line up.