customer_support · saas · workflow
Vimeo prototypes a generative AI help desk chat using RAG over Zendesk articles
Vimeo's existing customer support options—ticket submission, Help Center search, and a third-party chatbot—failed to surface relevant, immediate answers to user queries, leaving customers frustrated and often redirected to submit a support ticket.
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 · Zendesk articles indexed in vector store
All published Help Center articles are scraped via Zendesk's Help Center API and indexed as embeddings into a vector store.
Tools used
ZendeskLangchainHNSWLibGoogle Vertex AI Chat BisonOpenAI ChatGPT 3.5 TurboOpenAI ChatGPT 4Azure OpenAI ChatGPT 3.5 Turbo
Outcome
The prototype demonstrated a resilient system capable of handling a broad range of customer support queries. Vimeo selected Google Vertex AI Chat Bison for its concise responses, cost effectiveness, and seamless Google Cloud authentication.
What failed first
The existing third-party chatbot failed to surface relevant answers and redirected users to tickets. During prototype development, ChatGPT models were found to hallucinate outdated or nonexistent Vimeo Help Center links based on stale training data.
Results
Cost replacedsome cost savings
Grounding & classification
Source type: technical build writeup
27 fields verified against source quotes.
chatbotconversational aiknowledge searchragsupport agentknowledge basefailure mode describednamed customersource backedtools describedworkflow describedmediasoftwarecustomer satisfactionresponse time reductiontechnical build writeupcustomer supportautonomous resolutionrag answering