Whenever you're ready, walk me through how you'd approach this.
How would you design a RAG pipeline for a customer support chatbot at Citi?
Explain the end-to-end architecture, including document ingestion, chunking, indexing, retrieval, ranking, prompt construction, generation, citations, and escalation. Address security, authorization, freshness, latency, evaluation, hallucination prevention, monitoring, and failure recovery. State assumptions explicitly where requirements are unspecified.