Skip to content

AI

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.

Client
Home Textile Retailer
Year
2026
Katalog bilgisiSize, material, room fit, care
AyarBrand voice is configuration
2 kuralNo 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 used

  • LLM
  • Shopify Storefront
  • Katalog Bağlama
  • Çok Marka Ayarı

What would a system like this do for you?

We audit your ad account and site, then hand you a written roadmap in five business days.