customer_support · saas · workflow
How Wix's AI Site-Chat Redefines Chatbots with Adaptive Feedback and Dynamic Knowledge
Traditional AI chatbots built on LLMs cannot customize responses based on business owner preferences, offer no feedback mechanism for owners to teach the chatbot, and rely on static knowledge bases and fixed system prompts that do not adapt to unwritten domain knowledge.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Owner queries chatbot
The owner asks a question and receives a response from the chatbot.
Tools used
LLMsRAGCatBoostDDKI-RAG
Outcome
The DDKI-RAG system provides a more adaptive and dynamic approach to knowledge retrieval and prompt modification, allowing real-time learning and adaptability and leading to more accurate and context-aware chatbot responses.
What failed first
Traditional RAG systems have static knowledge bases and fixed prompts that cause outdated responses and user frustration, while LLMs used directly for classification suffer from overconfidence, hallucination, prompt fatigue, and high inference cost.
Results
Volumeimproved accuracy, efficiency, and user experience
Grounding & classification
Source type: technical build writeup
23 fields verified against source quotes.
chatbotconversational aidocument classificationragchat transcriptknowledge basefailure mode describedhuman review describednamed customersource backedtools describedworkflow describedsoftwareaccuracy improvementcustomer satisfactiontechnical build writeupcustomer supportextract classify routerag answering