RAG
RAG, or retrieval-augmented generation, is the standard way AI search answers a question about the live web: search first, read the results, then write the answer using them.
In a little more detail
The name is engineering jargon for something simple. It is why publishing a clear page can change what AI search says within days, where changing what a model learned in training is not something you can do at all.
Related terms
- Retrieval: Retrieval is the step where AI search fetches live web pages in the middle of answering you, instead of relying only on what it already knows.
- Grounding: Grounding is tying an answer to real fetched sources rather than letting the model answer from memory.
- Training data: Training data is the enormous body of text AI search learned from before it was released, which is fixed, often months or years old, and cannot be edited by you.
See it on your own site
The scan reads your site the way AI search does and reports where you stand on this and sixteen other checks.