Glossary · Technical
Embeddings
Numerical representations of text that capture meaning, letting a model measure how similar two pieces of content are without matching exact words.
What they are
An embedding turns a word, sentence or document into a list of numbers — a point in a high-dimensional space — positioned so that content with similar meaning ends up near other content with similar meaning. "Affordable laptop" and "budget notebook" land close together even though they share no words.
Why they matter for AI visibility
When an AI platform decides which pages are relevant enough to pull into an answer, it's often comparing the embedding of the user's question to embeddings of indexed content, not doing a keyword search. Content that's phrased close to how people actually ask questions is more likely to be matched and retrieved, regardless of whether it uses the exact terms in the query.
See more terms in the full glossary, or read the AI Visibility 101 guide for the full picture.