Before an AI answers a question with sources, it searches on its own. Three terms describe this step: Query Fan-Out, RAG and Grounding. Once you understand them, you know why some pages get cited in AI answers and others don’t.<\/p>\n\n\n\n
Here you get the whole process from prompt to source, each term explained on its own, and what it means for your content.<\/p>\n\n\n\n
On this page:<\/strong><\/p>\n\n\n\n When you ask an AI assistant a question with a search component, four steps run in the background. The terms sound technical, the logic behind them is simple: search first, then read, then answer.<\/p>\n\n\n\n In short: only what was retrieved beforehand makes it into the answer. And what gets retrieved is what the sub-searches find.<\/p>\n\n\n\n A question to an AI is often longer and more layered than a classic search query. That is why the AI does not search for the whole sentence. It splits it into sub-questions and searches for each one. Google described this in May 2025 for AI Mode<\/a>: the question is broken down into subtopics, and many searches run for them at the same time. For its deeper research feature Deep Search, Google speaks of “hundreds of searches”.<\/p>\n\n\n\n Google also explains fan-out with an example in its guide to AI features<\/a> from 2026: the question of how to fix a lawn full of weeds turns into searches on weed killers and on prevention.<\/p>\n\n\n\n For a founder asking about the right domain ending, it could look like this: the AI searches in parallel for the cost of an .ai domain, for the comparison of .de and .com, and for startups’ experiences. Each of these sub-searches has its own results.<\/p>\n\n\n\n The AI doesn’t search for your question. It searches for its sub-questions.<\/p>\n<\/blockquote>\n\n\n\n In short: you are not found for the one question someone asks, but for the sub-searches the AI turns it into. If you only cover half of a topic, you drop out of the remaining sub-searches.<\/p>\n\n\n\n On its own, a language model only knows its training data, i.e. texts up to a certain cut-off date. For current or very specific questions, that is not enough. Retrieval augmented generation, RAG for short, solves this: the model retrieves matching documents before answering and writes its answer on that basis.<\/p>\n\n\n\n The term was coined in 2020 by a team led by Patrick Lewis in the study Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks<\/a>. Today the principle is in almost every AI search, from ChatGPT to Perplexity.<\/p>\n\n\n\n Where the documents come from decides your chances. At Google the answer is clear: according to the guide<\/a>, AI search draws on the core ranking systems of Google Search. What is not found there is not available to the AI.<\/p>\n\n\n\n Grounding means: the AI bases its answer on the retrieved sources rather than only on what it learned. Only then does it show links to these sources, and only then are there citations.<\/p>\n\n\n\n Not every answer is grounded. For general questions the model can answer from its training, it often doesn’t search at all. For current questions, comparisons, prices or local providers, it almost always does.<\/p>\n\n\n\n Watch out: a mention from training knowledge and a citation from retrieval are two different things. For the first, what has been written about you over the years counts. For the second, what counts is whether your page is found today.<\/p>\n\n\n\n From my practice<\/p>\n\n\n\n At Placetel I looked at the sub-searches from 30 days in Peec: 75 prompts produced 3,180 different sub-searches. The most frequent was “site:placetel.de cloud telefonanlage preise” (cloud phone system prices). So the AI checks prices directly on the providers’ sites, and just as much at competitors like easybell, NFON and sipgate. Since then I deliberately keep pricing pages crawlable and make sure they show “from” prices as text, even where there used to be only a form or a demo request.<\/p>\n<\/div>\n\n\n\n Query fan-out means: the AI splits a question into several sub-searches, runs them at the same time and combines the results into one answer. Google uses the method in AI Mode.<\/p>\n\n\n\n RAG stands for retrieval augmented generation. Before answering, the language model retrieves matching content from a search or database and bases its answer on it.<\/p>\n\n\n\n RAG describes retrieving the content. Grounding describes the answer building on this content and referring to it. In practice the two terms are often used interchangeably.<\/p>\n\n\n\n Then the mention probably comes from the model’s training knowledge. Only what was retrieved at the moment of the answer gets linked.<\/p>\n\n\n\n Next in the handbook:<\/strong> An AI can only retrieve what its crawlers reach. Which AI bots exist and how to control them is shown in the next chapter: Allow or block AI crawlers<\/a>.<\/p>\n\n\n\n How AI search splits questions into sub-searches, retrieves content and grounds answers in sources: query fan-out, RAG and grounding explained.<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_wp_convertkit_post_meta":{"form":"-1","landing_page":"0","tag":"0","restrict_content":"0"},"footnotes":""},"categories":[124],"tags":[],"class_list":["post-11749","post","type-post","status-publish","format-standard","category-geo"],"yoast_head":"\n\n
The process: from prompt to source<\/h2>\n\n\n\n
PROMPT<\/span> \"Domain ending for my startup?\"<\/span> \u2502<\/span> \u25bc<\/span>QUERY FAN-OUT<\/span> \u251c\u2500 ai domain cost<\/span> \u251c\u2500 de or com<\/span> \u2514\u2500 domain ending startup<\/span> \u2502<\/span> \u25bc<\/span>RAG \u00b7 RETRIEVAL<\/span> matching pages from search<\/span> \u2502<\/span> \u25bc<\/span>GROUNDING<\/span> answer is based on sources<\/span> \u2502<\/span> \u25bc<\/span>ANSWER<\/span> text with citations<\/span><\/pre><\/figure>\n\n\n\nQuery fan-out: one question, many searches<\/h2>\n\n\n\n
75 PROMPTS<\/span> \u2514\u25b6 3,180 sub-searches<\/span> <\/span>MOST FREQUENT SUB-SEARCH<\/span> site:placetel.de<\/span> cloud telefonanlage preise<\/span>Peec AI, 28 Sep to 27 Oct 2026<\/span><\/pre><\/figure>\n\n\n\n\n
RAG: what the AI retrieves<\/h2>\n\n\n\n
GOOGLE AI MODE \u00b7 AI OVERVIEWS<\/span> Google index and ranking<\/span> <\/span>CHATGPT SEARCH<\/span> own crawler: OAI-SearchBot<\/span> <\/span>CONSEQUENCE<\/span> not findable, not retrieved<\/span><\/pre><\/figure>\n\n\n\nGrounding: when an answer gets sources<\/h2>\n\n\n\n
FROM TRAINING<\/span> learned up to the cut-off<\/span> \u2192 mention without a link<\/span> <\/span>FROM RETRIEVAL<\/span> live from search<\/span> \u2192 mention with a citation<\/span><\/pre><\/figure>\n\n\n\nWhat to do with it<\/h2>\n\n\n\n
\n
TOPIC<\/span> \u251c\u2500 sub-question A \u2192 section<\/span> \u251c\u2500 sub-question B \u2192 section<\/span> \u2514\u2500 sub-question C \u2192 section<\/span>every sub-search finds an answer<\/span><\/pre><\/figure>\n\n\n\nFAQ<\/h2>\n\n\n\n
What is query fan-out?<\/h3>\n\n\n\n
What does RAG mean?<\/h3>\n\n\n\n
What is the difference between RAG and grounding?<\/h3>\n\n\n\n
Why am I mentioned but not linked?<\/h3>\n\n\n\n
Sources<\/h2>\n\n\n\n
\n