Definition
RAG is the pattern of retrieving documents relevant to a question and giving them to a model as context before it writes an answer. Most answer engines that show sources are doing some form of this.
Why it matters
It explains why passage quality beats page quality. The retriever selects chunks, so a strong page whose relevant chunk is buried in a wall of text can lose to a thinner page with one clean, on-topic passage.
How to measure it
Read the passages that were actually cited from your site rather than assuming the whole page was read. If the cited passage is not the one you would have chosen, that is the editing task.