DL-061 · Case study
AI-powered warranty triage for an online appliance retailer
An online appliance retailer needed to organize warranty requests and reduce the amount of repetitive work handled by its support team.
- Client
- Name withheld
- Location
- United Kingdom
- Industry
- Home appliances and eCommerce
- Capabilities
- 01Audit03Build
01
Challenge
- Warranty requests arrived with incomplete product information and unclear fault descriptions.
- Agents repeatedly asked customers for serial numbers, receipts and photographs.
- Manufacturer warranty procedures varied across product categories.
02
Environment
- Shopify, Zendesk and manufacturer warranty databases.
- Customer-uploaded images, purchase records and service documentation.
- Third-party repair partners and return shipping workflows.
03
Intervention
- Built an AI-assisted intake workflow that collects structured issue descriptions.
- Matched requests to purchased products and applicable warranty rules.
- Introduced automated missing-information requests and case categorization.
- Routed potentially eligible cases to human agents with the relevant evidence attached.
04
Outcome
- More complete warranty cases at the point of human review.
- Less repetitive information collection for support agents.
- Consistent handling of warranty requests across product categories.
- 01CUSTOMER REQUESTZendesk→AI INTAKEStructured
- 02AI INTAKEStructured→WARRANTY CHECKPurchase / rules
- 03WARRANTY CHECKPurchase / rules→CLASSIFICATIONCase type
- 04CLASSIFICATIONCase type→AGENTDecision
Stack and services.
Stack02
Services used01
Tell us what has to work.
A senior engineer reads every brief. Describe the system, what it runs on today and what happens when it fails.
Discuss a project→