AI System for Routing Student Requests to the Right Unit

The problem

When portal messages, student records and the service catalogue are held in different sources, staff must match fields manually before preparing a draft request category and unit assignment.

The student services coordinator must compare every suggestion in the draft request category and unit assignment with the source record; incomplete or conflicting evidence must not replace the final decision.

If a message containing several requests is not set aside for separate review, sensitive data could be sent to the wrong unit; the record must not proceed without a human decision.

What we set out to improve

• Time taken for the draft request category and unit assignment, with its supporting evidence, to reach the student services coordinator for review
• Outcomes of records sent for human review because a single message contains several requests
• Number of suggestions corrected after identifying a risk that sensitive data could be sent to the wrong unit

How the system works

1. 01 Retrieve the portal message, student record and service catalogue from permitted sources
2. 02 Verify field and document versions
3. 03 Prepare the request category and draft unit assignment with supporting evidence
4. 04 Check the exception: a single message contains several requests
5. 05 Have the student services coordinator accept, correct or reject the suggestion
6. 06 Decision gate: request ownership and the response to be provided
7. 07 Record the decision and its source separately

Methods we used

• A source-identified data schema for the portal message, student record and service catalogue
• A structure that separates deterministic rules from AI suggestions
• A screen showing the request category and draft unit assignment alongside the supporting evidence
• A human review queue for messages containing several requests
• A record identifier that prevents duplicate processing

Where people stay involved

Data and security

Only the necessary fields from the portal message, student record and service catalogue 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 student services coordinator's decision should be recorded separately.

Who this suits

Frequently asked questions