Vector Search
Finding results by similarity in meaning rather than exact words.
Technical Term
Full explanation
Vector search is a search method that finds results by comparing embeddings for similarity in meaning, rather than matching exact keywords.
Traditional keyword search works by matching the literal words in a query against the literal words on a page. Vector search instead converts the query and every candidate document into embeddings, then finds whichever documents sit closest to the query in that mathematical space, a comparison of meaning, not text.
This is one of the reasons AI-mediated discovery behaves differently from classic search. A page can be the best answer to a question and never surface under keyword matching if it phrases things differently to how people ask; vector search is built specifically to close that gap.
Why this matters
It is how retrieval systems find relevant material even when the source never used the buyer's exact wording.
Example
A buyer searches for "why isn't my brand showing up in ChatGPT answers." A page titled "AI Visibility Measurement" that never uses the word "ChatGPT" can still surface for that query under vector search, because the underlying concepts are close in meaning even though the wording differs.
Where this sits
Vector Search belongs to AI & Search Infrastructure, one of the seven layers of the Aingworth Glossary. The technical vocabulary behind the interfaces. Useful for understanding how the systems work, without becoming the center of the conversation.
Related terms
Ready to see where your brand stands?
Start with the free diagnostic to see which condition of the Recognition Triangle is leaking, or read the frameworks these terms belong to.