AI System for Checking Subscription Change Requests

The problem

In day-to-day operations, plan details, billing periods and customer requests 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 an eligibility and impact summary is prepared, leading to repeated checks and uncertainty about the basis for the decision.

Incomplete automation may overlook a refund, tax or contract exception, while poorly controlled automation creates a risk of incorrect charges or disrupted access.

What we set out to improve

• Time taken for the draft eligibility and impact summary to be ready for review
• Accurate routing of records with a refund, tax or contract exception to the correct specialist queue
• Recording of suggestions amended or rejected by the customer operations specialist

How the system works

1. 01 Retrieve plan, billing-period and customer-request 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 a draft eligibility and impact summary
5. 05 Compare the draft with business rules and source records
6. 06 Exception check: a refund, tax or contract exception applies
7. 07 Customer operations specialist 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 the plan, billing period and customer request
• Structured output that restricts the eligibility and impact-summary fields through business rules
• An exception gate that separates cases with a refund, tax or contract exception
• A queue that shows the source and suggestion together for the customer operations specialist
• Duplicate-processing and rollback records to manage the risk of incorrect charges or disrupted access

Where people stay involved

Data and security

Only the fields required for the task are processed from the plan, billing period and customer request. 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