Retrieval-Augmented Generation (RAG)
Retrieval-augmented generation is a technique where a language model first retrieves relevant documents from an external source, then generates its answer grounded in that retrieved text, so the response reflects specific, citable material rather than the model recalling facts from its training weights alone.
RAG is how most modern answer engines work. When you ask a question, the system runs a retrieval step (usually a semantic search over an index of documents), pulls back the passages it judges most relevant, and feeds them to the model as context. The model then writes an answer that draws on those passages, which is why tools like ChatGPT, Perplexity, and AI Overviews can name sources and link to them: the source is literally in front of the model at generation time.
The practical consequence for a business is that being retrievable is the whole game. If your content is not in the index, or the retriever does not surface it for the relevant query, the model never sees it and cannot cite you, no matter how good your answer would have been. This is also why grounded answers tend to be more accurate than ungrounded ones: the model is summarising a real document instead of reconstructing a fact from memory.
RAG does not guarantee correctness, and it is worth being honest about that. The model can still misread a passage, blend two sources, or cite a page that does not actually support the claim. Retrieval quality also varies by query, so a page that gets cited for one phrasing can be invisible for another. For commerce, where buyers ask AI assistants to compare and recommend products, the gap is usually that real customer reviews exist but are not readable, corroborated, or indexed in a form a retriever will pull. Closing that gap is the work BetterReviews focuses on.