customer_support · saas · workflow
Building a context-sensitive AI assistant with RAG: Lessons from building Vectorize's in-product documentation assistant
Vectorize users had to leave the product UI to visit the docs site, creating disruptive context-switching, while the in-product Intercom chat was not always staffed and some users were reluctant to ask for help.
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 · User clicks Ask AI in UI
When the user clicks on 'Ask AI', a chat window appears at the top right of the screen.
Tools used
VectorizeGroqLlama 3.1 70BReactreranking model
Outcome
Vectorize built a context-sensitive AI assistant embedded directly in the product UI, powered by a self-improving multi-source RAG pipeline. Topic-aware retrieval and reranking improved response quality, and anti-hallucination prompting prevented the LLM from fabricating answers.
Results
Cost replacedlower cost
Grounding & classification
Source type: technical build writeup
24 fields verified against source quotes.
chatbotknowledge searchragchat transcriptknowledge basesupport ticketbuilder submittednamed customerproduction runtime claimedtools describedworkflow describedsoftwareaccuracy improvementtechnical build writeupcustomer supportrag answering