Retrieval-Augmented Generation (RAG) is an AI architecture that combines a large language model with a real-time retrieval step: when a query arrives, the system fetches relevant documents from a knowledge base and feeds them to the model as context before generating a response. This lets the model answer with up-to-date or proprietary information it was not trained on. Many AI search products — including Perplexity and enterprise chatbots — use RAG under the hood. For SEO, understanding RAG helps explain why well-structured, authoritative content is more likely to be retrieved and cited in AI-generated answers.