AI System for Preparing Learning Support Signals for Advisers

The problem

When course activity, attendance, submissions and authorised absence records are held in different sources, staff must match the fields manually before preparing a contextual support signal.

The academic adviser must compare every suggestion in the contextual support signal with the source record; missing or conflicting evidence must not replace the final decision.

If an authorised absence that explains reduced activity is not routed for separate review, the student could receive an unfair risk label; the record must not proceed without a human decision.

What we set out to improve

• Time taken for the draft contextual support signal and its supporting evidence to reach the academic adviser for review
• Resolution outcomes for records routed to human review because an authorised absence explains reduced activity
• Number of suggestions corrected after identifying the risk of giving a student an unfair risk label

How the system works

1. 01 Retrieve course activity, attendance, submissions and authorised absence records from authorised sources
2. 02 Verify field and document versions
3. 03 Prepare the contextual support signal with its supporting evidence
4. 04 Check the exception: an authorised absence explains reduced activity
5. 05 Have the academic adviser accept, correct or reject the output
6. 06 Decision gate: support, grade or student-status decision
7. 07 Record the decision and source separately

Methods we used

• A source-identified data schema for course activity, attendance, submissions and authorised absence records
• A structure that separates deterministic rules from AI suggestions
• A screen showing the contextual support signal alongside its supporting evidence
• A human review queue for cases where an authorised absence explains reduced activity
• A record identifier that prevents duplicate processing

Where people stay involved

Data and security

Only the necessary fields from course activity, attendance, submissions and authorised absence records should be processed. Role-based access must be applied, and unnecessary identity, health, financial and internal institutional data must not be sent to the model. Source retrieval, AI suggestions and the academic adviser's decision must be logged separately.

Who this suits

Frequently asked questions