AI System for Preparing Course Exemption Files for Review

The problem

When transcripts, course content and credit information are held in different sources, staff must match fields manually before preparing a course match and missing evidence list.

The academic board rapporteur must compare every suggestion in the course match and missing evidence list with the source record; incomplete or conflicting evidence must not replace the final decision.

If courses with the same name but different learning outcomes are not set aside for separate review, an inadequate course could be treated as equivalent; the record must not proceed without a human decision.

What we set out to improve

• Time taken for the draft course match and missing evidence list, with its supporting evidence, to reach the academic board rapporteur for review
• Outcomes of records sent for human review because courses with the same name have different learning outcomes
• Number of suggestions corrected after identifying a risk that an inadequate course could be treated as equivalent

How the system works

1. 01 Retrieve the transcript, course content and credit information from permitted sources
2. 02 Verify field and document versions
3. 03 Prepare the course match and missing evidence list with supporting evidence
4. 04 Check the exception: courses with the same name have different learning outcomes
5. 05 Have the academic board rapporteur accept, correct or reject the suggestion
6. 06 Decision gate: exemption and the transfer of credits and grades
7. 07 Record the decision and its source separately

Methods we used

• A source-identified data schema for the transcript, course content and credit information
• A structure that separates deterministic rules from AI suggestions
• A screen showing the course match and missing evidence list alongside the supporting evidence
• A human review queue for courses with the same name but different learning outcomes
• A record identifier that prevents duplicate processing

Where people stay involved

Data and security

Only the necessary fields from the transcript, course content and credit information should be processed. Role-based access should be applied, and unnecessary identity, health, financial and internal institutional data should not be sent to the model. Source access, the AI suggestion and the academic board rapporteur's decision should be recorded separately.

Who this suits

Frequently asked questions