Learning center
Plain explanations of how AI search works: the models, the ranking, the crawlers and how a brand ends up in an answer.
What is AI search?
AI search is search where a language model reads pages from a search index and writes one answer with citations, instead of returning a ranked list of links.
What is a large language model (LLM)?
A large language model is a neural network trained on large amounts of text to predict the next token. That one skill is what lets it answer questions, summarize pages and write AI search answers.
What is retrieval-augmented generation (RAG)?
Retrieval-augmented generation fetches relevant documents at the moment of a question and gives them to a language model, so the answer is written from current sources instead of from training data alone.
How does AI search choose which sources to cite?
AI search picks its sources in stages. A search index returns candidate pages, a ranking step scores passages against the question, and the model cites the passages it used while writing.
What is AI visibility?
AI visibility is how often, and how prominently, AI answers mention or cite a brand for the questions its customers ask. It is measured by running a fixed set of prompts across AI platforms and recording the results over time.
What are AI crawlers?
AI crawlers are bots run by AI companies to fetch web pages for model training, for live search answers, or on behalf of a user. Each has its own user agent and can be allowed or blocked separately.
