Definition
What this term means
An AI architecture that combines real-time information retrieval with language generation. Instead of relying solely on pre-trained knowledge, RAG systems search external sources, such as websites, databases, or knowledge bases, to find relevant information before composing their response. This is the technology behind AI search tools like Perplexity and Google's AI Overviews.
Why it matters
The business impact
RAG is the mechanism that determines whether your content gets cited in AI-generated answers. If your pages are not structured for retrieval, with clear headings, factual claims, and proper markup, RAG systems will pull information from competitors instead. Optimising for RAG is one of the highest-impact actions a brand can take for AI visibility.
Used in context
How you might use this term
“A software company restructured their documentation with concise, well-headed sections and structured data. RAG-powered platforms like Perplexity began pulling directly from their docs, resulting in a 200% increase in AI-attributed referral traffic within three months.”
Related terms
Explore connected concepts
Vector Index
A specialised database that stores and searches embeddings for fast semantic retrieval. Vector indexes are the infrastructure behind RAG systems. When an AI assistant needs to find relevant information to answer a query, it searches the vector index for content embeddings that are semantically closest to the user's question. Popular vector databases include Pinecone, Weaviate, and Qdrant.
Freshness Signals
The collection of indicators that tell search engines and AI systems how recently content was created or updated. Freshness signals include Last-Modified headers, sitemap lastmod dates, visible 'last updated' dates on pages, recent internal and external references, and the frequency of content changes detected by crawlers. Together, these signals help AI systems determine whether content is current and reliable.
Knowledge Graph
A structured database that maps entities and the relationships between them, creating a web of interconnected knowledge. Google's Knowledge Graph, Wikidata, and similar systems store billions of facts about people, places, organisations, and concepts, powering the knowledge panels, rich results, and AI-generated answers that appear across search and AI platforms.