What is RAG?
TL;DR
RAG (Retrieval-Augmented Generation) is a technique where AI models search for and retrieve relevant information from external sources before generating an answer.
Last updated: 2026-03-09
Definition#
Retrieval-Augmented Generation (RAG) is a technique that combines an LLM with a search system. Instead of relying only on what the model learned during training, RAG lets the model look up current, relevant information before generating its answer.
Here is how it works: a user asks a question. The system searches a database of documents or the web for relevant content. The most relevant results are fed into the LLM as context. The LLM then generates an answer based on both its training and the retrieved content, often citing the sources it used.
RAG is the technology behind AI-powered search engines like Perplexity, Google AI Overviews, and ChatGPT's Browse feature. It is why these tools can answer questions about current events and specific products — they retrieve your web content in real time.
Why It Matters for AI Readiness#
RAG is the reason your website content can appear in AI answers. When an AI system uses RAG, it searches for sources to cite. If your site is well-structured, authoritative, and accessible to crawlers, it is more likely to be retrieved and cited.
This is why factors like content quality, bot access, and schema markup matter so much. They determine whether your content survives the retrieval step and gets presented to the LLM.
Related Concepts#
RAG connects LLMs to live web data. The retrieval step uses AI Crawlers and search indexes. The generation step produces AI Citations that link back to your content.
Related Pages
Was this page helpful?