What it does
A triage automation for a D2C brand. Return requests and reviews from the store and marketplaces are read for the reason: size, colour, damage, quality or changed mind. Simple returns inside the policy are approved straight away with an exchange offered first; damage and high-value orders go to the operations lead. Every reason is counted per product, so recurring problems show up in a weekly report.
The problem
Returns were handled one email at a time, refunds took a week, and nobody connected the complaints in reviews with the reasons for returns. The same sizing problem cost money for months.
Approach
Policy rules decide the easy cases: within the return window, unused, not a final-sale item. Customers are offered an exchange or store credit before a refund. Damage claims and orders above a set value always go to a person. Reviews and returns share one reason list, so the product team sees one picture.
- Input
- AI step
- Rules or code
- Person decides
- Result
Screens
Swipe sideways to see the whole screen.
Client work is shown under confidentiality agreements: no client names, and screens are recreated with sample data.
Stack
- Store and marketplace integrations
- Gemini API
- Policy rules
- Weekly reports
Impact
Typical for systems like this.
