AI System for Routing Store Customer Requests to the Right Team

The problem

Store forms, receipt details and customer messages arrive from different systems and event logs, preventing the team from viewing each case on a single timeline.

As a result, source links may be lost while the request type and team recommendation are prepared, the case may be referred to the wrong team and the basis for a technical decision may remain unclear.

An incomplete workflow may overlook a health, safety or personal data matter, while an unsuitable workflow could expose a sensitive request to the wrong team.

What we set out to improve

• Time taken for the draft request type and team recommendation to be ready for specialist review
• Correct referral of records concerning health, safety or personal data to the appropriate specialist queue
• Record of suggestions corrected or rejected by the customer service manager

How the system works

1. 01 Retrieve store form, receipt detail and customer message data from authorised sources
2. 02 Verify the source, timestamp and record identifier
3. 03 Add the context of the relevant asset, user, store, vehicle or content
4. 04 Prepare a draft request type and team recommendation
5. 05 Compare the draft with technical rules and authority limits
6. 06 Check for exceptions: matters concerning health, safety or personal data
7. 07 Obtain the customer service manager's approval, correction or rejection
8. 08 Write the input, suggestion, change and final decision to the audit log

Methods we used

• Source- and time-traceable data extraction for store forms, receipt details and customer messages
• Structured output that constrains the request type and team recommendation fields according to technical rules
• An exception gate that separates matters concerning health, safety or personal data from workflow processing
• An authorised queue that presents evidence and suggestions together for the customer service manager
• Duplicate transaction checks and a rollback record to address the risk of exposing a sensitive request to the wrong team

Where people stay involved

Data and security

Only fields required for the task are processed from store forms, receipt details and customer messages. Source-system permissions are preserved, and personal, technical and security-sensitive data is minimised before being provided to the model. Every read, suggestion, human change and target-system action is written to the audit log.

Who this suits

Frequently asked questions