// AI & automation · Home Textile Retailer
Not a decision tree — an assistant that knows the catalogue
Most storefront chat is either a rules-based tree that frustrates people or a support inbox nobody staffs at 11pm.
- Catalogue knowledge
- Size, material, room fit, care
- Settings
- Brand voice is configuration
- 2 rules
- No competitor, no outbound link
Situation
Neither option helps the customer who knows what room they are furnishing but not which product fits it.
Pointing them at a category page does not answer the question.
Approach
A conversational assistant sits on the storefront and answers with knowledge of the actual catalogue — size, material, room suitability, care.
It moves the conversation toward a specific product rather than a category page.
Brand voice, tone and product framing are configuration, not hard-coded, which is what let a second brand deploy on the same codebase without a fork.
Result
Two rules are enforced at the model boundary: never mention a competitor, never link outside the store.
Beyond correctness that is a commercial requirement — an assistant that helpfully sends a customer elsewhere is worse than no assistant at all.
Technology
Planning something similar?
Let’s pin down scope and timeline together.