ChatGPT query fan-out studied across 15 million searches
Ahrefs researcher Louise Linehan analyzed 66.6 million free, logged-out GPT-5.6 Luna responses and their 15 million fan-out queries from August and September to map how ChatGPT actually retrieves information before generating an answer.
What the data shows
Only 14.4% of the 66.6 million responses triggered fan-out queries at all. That means the large majority of ChatGPT answers are generated without any real-time web retrieval. For operators building AI visibility strategies, the implication is direct: appearing in ChatGPT’s answers depends on factors beyond standard search indexing.
Why it matters for AI search visibility
Query fan-out is the mechanism ChatGPT uses to break a user’s prompt into sub-queries, retrieve sources, and synthesize a response. Understanding which queries actually trigger fan-out, and which do not, is the foundational question for anyone trying to measure or influence AI search presence. The full Ahrefs study covers the structure of those fan-out queries and what that pattern means for content strategy.
The full write-up is on the Ahrefs blog.
I’m founder of BizStack at Cagri Sarigoz LLC and a passionate advocate for entrepreneurs.
With over 14 years in tech, marketing, and AI, including my role as Head of SEO at CitizenShipper and co-founder of TaleBot at Intale AI, I’m dedicated to sharing genuine, useful product insights and tips.
At BizStack, I aim to cut through the digital noise to provide clear, actionable advice.
And more than all else, I’m a father to a (always) little girl and a husband.
Contact me at [email protected] for assistance.
