AI System for Classifying Service Notes by Technical Topic

The problem

Customer statements, service history and technician notes 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 fault topic and missing-question list 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 an indication involving the brakes, steering or safety, while an unsuitable workflow could lead to vehicle work based on an incorrect fault assessment.

What we set out to improve

• Time taken for the draft fault topic and missing-question list to be ready for specialist review
• Correct referral of records involving a brake, steering or safety indication to the appropriate specialist queue
• Record of suggestions corrected or rejected by the service technician

How the system works

1. 01 Retrieve customer statement, service history and technician note 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 fault topic and missing-question list
5. 05 Compare the draft with technical rules and authority limits
6. 06 Check for exceptions: an indication involving the brakes, steering or safety
7. 07 Obtain the service technician'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 customer statements, service history and technician notes
• Structured output that constrains fault-topic and missing-question fields according to technical rules
• An exception gate that separates indications involving the brakes, steering or safety from workflow processing
• An authorised queue that presents evidence and suggestions together for the service technician
• Duplicate transaction checks and a rollback record to address the risk of carrying out vehicle work based on an incorrect fault assessment

Where people stay involved

Data and security

Only fields required for the task are processed from customer statements, service history and technician notes. 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