What happens between a query and a citation?
New research from 17k queries and 354k pages reveals what actually gets your content cited by ChatGPT and what doesn't. From retrieval rank and heading structure to freshness and domain authority, find out what matters and what doesn't.

Webflow 5xed content refresh velocity and increased visibility across Google and ChatGPT
Chime went from being recommended in 24 to 68 priority questions
George Bonaci VP of Growth, Ramp
Nicole Baer, CMO, Carta
50% cut in production costs, thanks to the elimination of external agencies and manual tasks.
Marcio Arnecke, CMO, Apollo


What you'll walk away with
Rank is the dominant signal in AI search
A page at position 0 in ChatGPT's search results has a 58% chance of being cited. By position 10, that drops to 14%. A 4x gap driven by rank alone and even strong content can't overcome a weak position.
Your headings decide if AI cites you
Pages with headings that closely match the user's query are cited 41% of the time vs. 29% for weak matches. The relationship is monotonic: better heading match, more citations. Headings are the lever most teams are ignoring.
Focused pages beat comprehensive guides
Pages covering 26-50% of ChatGPT's fanout sub-queries get cited more than pages covering 100%. Be the best answer to one question, not an adequate answer to five.
Schema markup is still your hidden advantage
Pages with JSON-LD structured data are cited 38.5% of the time vs. 32.0% without. A +6.5pp advantage that holds regardless of word count, headings, or domain authority.
Long-form is losing. College-level writing is winning.
The sweet spot is 500-2,000 words. Pages over 5,000 words get cited less than pages under 500. Meanwhile, college-level writing (Flesch-Kincaid 16-17) is cited 21% more often than simple writing.

No hype. Real wins.

“The most successful marketing teams in the AI era will be those who build content for how the internet actually works. This isn’t a transition. It’s a transformation.”

“Velocity is the most important thing. If you’re not failing, you’re not moving fast enough or being creative enough.”
“AirOps has proven that AI can deliver real results for our clients, meeting our high quality bar, at scale.“
Built for the teams optimizing for AI search



