AI System for Preparing Part Candidates from Vehicle Information

The problem

Vehicle identifiers, parts catalogues and service requests 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 compatible part candidate list is 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 conflict in the model year or engine code, while an unsuitable workflow could lead to an incompatible part being ordered.

What we set out to improve

• Time taken for the draft compatible part candidate list to be ready for specialist review
• Correct referral of records with conflicting model years or engine codes to the appropriate specialist queue
• Record of suggestions corrected or rejected by the parts specialist

How the system works

1. 01 Retrieve vehicle identifier, parts catalogue and service request 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 compatible part candidate list
5. 05 Compare the draft with technical rules and authority limits
6. 06 Check for exceptions: a conflict in the model year or engine code
7. 07 Obtain the parts specialist'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 vehicle identifiers, parts catalogues and service requests
• Structured output that constrains compatible part candidate fields according to technical rules
• An exception gate that separates conflicts in the model year or engine code from workflow processing
• An authorised queue that presents evidence and suggestions together for the parts specialist
• Duplicate transaction checks and a rollback record to address the risk of ordering an incompatible part

Where people stay involved

Data and security

Only fields required for the task are processed from vehicle identifiers, parts catalogues and service requests. 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