What is Retrieval-Augmented Generation (RAG)?
A pattern where a model retrieves relevant documents first, then grounds its answer in them. Most AI search answers are RAG systems, which is why retrievable, chunkable pages get cited.
Related terms
Chunk Retrieval
The step in RAG where a system pulls the most relevant passages (chunks) from its index to feed the model. Pages with self-contained, fact-dense sections produce chunks that survive this selection.
Grounding
Tying a model’s answer to retrieved sources instead of pure parametric memory. Grounded answers cite pages, which turns citation readiness into visible referral and brand presence.
Grounding Source
A page an AI answer actually retrieved and based claims on. Becoming a grounding source requires being crawlable, topically relevant, and quotable at the passage level.
Answer Engine Optimization (AEO)
Answer Engine Optimization is the practice of structuring pages so answer engines and AI assistants can extract, trust, and quote them: a direct definition up top, scannable steps, quotable facts, and FAQ or Article schema behind them.
Generative Engine Optimization (GEO)
Generative Engine Optimization improves how often a brand or page is cited inside AI-generated answers. It combines classic SEO (crawlability, relevance) with quotability: clear facts, named entities, sources, and machine-readable structure.
AI Overviews
Google’s AI-generated summaries at the top of some results pages. They synthesize multiple sources and link to them, which can reduce clicks to publishers even when a page ranks well organically.