AI System for Pre-Publication Product Image Checks

The problem

In day-to-day operations, product images and channel rules arrive in separate records and files, preventing the team from reviewing the same case in one place.

As a result, the link to the source can be lost while warnings about missing angles and quality issues are prepared, leading to repeated checks and uncertainty about the basis for the decision.

Incomplete automation may overlook unclear labelling or regulatory information, while poorly controlled automation creates a risk of publishing an incorrect listing.

What we set out to improve

• Time taken for the draft warnings about missing angles and quality issues to be ready for review
• Accurate routing of records with unclear labelling or regulatory information to the correct specialist queue
• Recording of suggestions amended or rejected by the catalogue editor

How the system works

1. 01 Retrieve product image and channel-rule data from an approved source
2. 02 Verify the source system, record identifier and freshness information
3. 03 Transform the fields into the target process schema
4. 04 Prepare draft warnings about missing angles and quality issues
5. 05 Compare the draft with business rules and source records
6. 06 Exception check: labelling or regulatory information is unclear
7. 07 Catalogue editor approval, amendment or rejection
8. 08 Write the input, suggestion, amendment and final decision to the audit log

Methods we used

• Source-traceable data extraction for product images and channel rules
• Structured output that restricts the missing-angle and quality-warning fields through business rules
• An exception gate that separates cases with unclear labelling or regulatory information
• A queue that shows the source and suggestion together for the catalogue editor
• Duplicate-processing and rollback records to manage the risk of publishing an incorrect listing

Where people stay involved

Data and security

Only the fields required for the task are processed from the product images and channel rules. Source-system permissions are preserved, and personal and commercially sensitive data is minimised before being passed to the model. Every read, suggestion, human amendment and write to the target system is logged.

Who this suits

Frequently asked questions