AI System for Matching Customer Requirements with Technical Products

The problem

When the customer description, catalogue and compatibility rules are held in separate sources, their fields must be matched by hand before reasoned product candidates can be prepared.

The sales engineer must compare every reasoned product candidate with its source record; missing or conflicting evidence must not replace the final decision.

If identical dimensions that require different certifications are not set aside for review, an incompatible product could be quoted; the record must not proceed without a human decision.

What we set out to improve

• Time taken for draft reasoned product candidates and their supporting evidence to reach the sales engineer for review
• How records set aside for human review because identical dimensions require different certifications are resolved
• Number of suggestions corrected after identifying a risk that an incompatible product could be quoted

How the system works

1. 01 Retrieve the customer description, catalogue and compatibility rules from permitted sources using the record identifier
2. 02 Link source, date and version information to the shared work record
3. 03 Validate fields and units
4. 04 Prepare reasoned product candidates with their supporting evidence
5. 05 Check for an exception: identical dimensions require different certifications
6. 06 Have the sales engineer accept, revise or reject the suggestion
7. 07 Record the approved decision and its source in the processing log

Methods we used

• A source-identified common data schema for the customer description, catalogue and compatibility rules
• A decision structure that separates deterministic rules from AI suggestions
• A review screen showing reasoned product candidates alongside the underlying source evidence
• A mandatory human review queue when identical dimensions require different certifications
• An event identifier that prevents duplicate processing

Where people stay involved

Data and security

Only the fields required for this decision should be processed from the customer description, catalogue and compatibility rules. Access to the source systems must be authorised separately from the sales engineer role, and personal data, commercial information and technical secrets must not be passed into the model context unnecessarily. Reading, suggestions and human decisions must be logged separately.

Who this suits

Frequently asked questions