Retrieval-augmented generation (RAG) plays a key role in enterprise adoption of generative and agentic AI by augmenting the model’s context at inference time with authoritative knowledge. Leading vendors have released the first generation of commercial RAG offerings — but given the inherent complexity of RAG architecture, getting RAG right requires extensive engineering efforts. This report provides best practices of RAG initiatives across indexing, retrieval, generation, and agent support, with examples of how pioneers have resolved their AI challenges through RAG engineering.