customer_support · finance · workflow
Lessons from launching Enterprise-grade GenAI solutions at Coinbase
Coinbase initially expected to optimize only between cost and accuracy when adopting GenAI, but encountered additional enterprise challenges including trust and safety, model availability, latency, and a rapidly shifting LLM landscape.
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 or employee submits request
Coinbase's customer-facing conversational LLM chatbot serves all US consumers as the entry point.
Tools used
CB-GPTAWS BedrockGCP VertexAIAzure GPTRAGChatGPTGoogle Gemini
Outcome
Coinbase built CB-GPT, a unified multi-cloud GenAI platform with RAG, guardrails, and agentic capabilities; several dozen use cases have been built by non-ML teams, and a customer-facing conversational LLM chatbot serving all US consumers launched in June 2024.
Results
Volumeseveral dozen use cases
Running sinceJune 2024
Source
https://www.coinbase.com/blog/lessons-from-launching-enterprise-grade-genAI-solutions-at-Coinbase
Grounding & classification
Source type: technical build writeup
25 fields verified against source quotes.
agentic workflowconversational aienterprise searchmulti agent workflowragknowledge basenamed customerproduction runtime claimedtools describedworkflow describedfinancial servicesemployee productivitytechnical build writeupback office opscustomer supportagentic task executionrag answering