Glossary · Answer engines and retrieval

token

The unit a model reads, roughly a word fragment. Token counts matter because markup, navigation and boilerplate consume the same budget as the content they surround.

Answer engines and retrieval

How a generated answer gets made, and what your page is competing for inside it.

AEO · GEO · AI visibility score · share of voice · prompt set · brand mention · RAG · grounding · training data · embedding · chunking · context window · hallucination · refusal · AI Overview · answer engine · citation · retrieval · hallucinated attribution · Hybrid search · Re-ranking · Passage ranking · Query fan-out · Chunk boundary · BM25 · cross-encoder · AI Mode · information gain · dense retrieval

← context window  ·  hallucination →

See it in the full glossary · 579 terms across 19 areas. Scan a site to see which of these apply to it.