customer_support · finance · workflow
Coinbase builds LLM-powered Conversational Coinbase Chatbot (CBCB) to handle tens of thousands of customer support queries monthly
Coinbase's customer query volume surged to tens of thousands per month, with traffic spiking during crypto bull runs, requiring a system that could personalize responses using real-time account data while maintaining compliance.
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 · Customer query arrives
Customer queries covering topics like account restrictions, platform policies, recent transactions, and unique Coinbase product features arrive for processing.
Tools used
LLMML modelknowledge bases
Outcome
CBCB handles tens of thousands of customer support queries monthly, delivering faster answers without live agent wait times and freeing CX agents to focus on more complex issues.
What failed first
Standard commercial and open-source LLMs lacked the Coinbase-specific context needed to accurately address account restrictions, platform policies, and unique product features.
Results
Time savedtens of thousands
Grounding & classification
Source type: technical build writeup
23 fields verified against source quotes.
chatbotconversational airagsupport agentknowledge basesupport ticketfailure mode describednamed customerproduction runtime claimedtools describedworkflow describedfinancial servicesemployee productivityresponse time reductiontechnical build writeupcustomer supportautonomous resolutionrag answering