RAG is a technique that makes AI models more accurate by giving them access to external data at the time they answer a question. Instead of relying only on what the model learned during training, RAG retrieves relevant documents from a database or knowledge base and includes them in the prompt. This means the AI can answer questions about your specific data — company documents, product catalogs, internal policies — without being fine-tuned. RAG is the most common pattern for building enterprise AI applications because it combines the model's language ability with your organization's proprietary knowledge.