Most SEO advice tells you to write a compelling introduction, build up to your main point, and deliver the answer after you have set the context. Two independent citation studies say the opposite: if your answer is not in the first 30% of the page, there is a better than even chance it is not getting cited by AI search engines at all.
The CXL study: 100 AI Overview citations
CXL analyzed 100 Google AI Overview citations to see where on the source page the cited passage actually appeared. They mapped each citation to its position relative to the full page length.
The results:
- 55% of cited passages appeared within the first 30% of the source page.
- The 10-20% zone alone produced more citations than any other segment.
- The top 20% of pages accounted for 48 of 100 citations.
- The bottom 40% of pages accounted for only 21.
The concentration is not subtle. If your core answer lives at the 50% mark because you built up to it with context and storytelling, it sits in a part of the page that produced fewer citations in this sample than the first 10%.
The Kevin Indig dataset: 18,012 ChatGPT citations
Kevin Indig ran a larger analysis across 1.2 million search results and 18,012 verified ChatGPT citations. The pattern was the same:
- 44.2% of ChatGPT citations came from the first 30% of the document.
- After the first third, citation likelihood drops sharply.
- Indig described it as a "ski ramp" effect: a steep cliff after the first 30%, then a long, slow tail.
Two different AI systems (Google AI Overviews and ChatGPT), two different datasets (100 citations and 18,012 citations), same shape. The retrieval step that feeds both systems appears to weight content position in a way that rewards front-loading.
Why this happens
Google's own documentation explains the mechanism. AI Overviews use query fan-out: the model splits the original query into multiple related sub-queries, retrieves pages for each, and assembles a response from the results. The retrieval step has a context budget. When a page is fetched, the model reads from the top. If the answer is buried at 60%, it may not make it into the context window before the budget is spent.
This is the same reason the CXL study found that FAQ sections can still get cited from deep page positions: each FAQ question-and-answer pair is structurally self-contained, so the model can extract a complete answer without needing the surrounding context. But for narrative content, position matters.
What the Ahrefs data adds
The Ahrefs analysis of 863,000 keywords and 4 million AI Overview URLs found that only 38% of cited pages appeared in the organic top 10 for the same query, down from 76% in July 2025. A separate BrightEdge analysis put the number at 17%.
This means most cited pages do not rank for the exact keyword being searched. They rank for related sub-queries generated by fan-out. Your page does not need to hold the top position for the primary keyword to get cited. It needs to contain a clear answer to a related question, and that answer needs to be near the top of the page.
Practical changes
If you write technical content, blog posts, or documentation, the implication is straightforward:
Put the answer first, context second. If your article is about a specific problem, the clearest statement of the solution should appear in the first 20% of the page. Not after the third subheading, not after you have warmed the reader up.
Front-load definitions. If your page defines a concept, the definition should be in the first paragraph or two. The CXL data shows the 10-20% zone is the single most productive segment for citations.
Keep FAQ sections for specific questions. FAQ blocks can still get cited from deep positions because each answer is self-contained. This is the one structural pattern that survives the position effect.
Measure with Search Console. Google introduced dedicated Search Generative AI performance reports in June 2026, rolled out worldwide by August 31. You can now track AI Overview impressions directly rather than relying on third-party tools.
What this does not mean
Front-loading is not the same as dumbing down. The data says the answer should be early, not that the page should be short. The bottom 40% of pages still produced 21 of 100 citations in the CXL study. Context, examples, and depth still matter for readers who click through. But the AI retrieval step that decides whether you get cited appears to read from the top and stop when it has enough.
The pages that win in AI search are the ones where the first thing a human reader finds is also the first thing a retrieval system extracts. If you have been writing introductions that delay the answer, the citation data says to stop.
I maintain GEO Optimizer, the open-source GEO audit CLI behind GeoReady (geoready.dev).
Top comments (2)
We need to output a comment, short one or two sentences, casual, start with lowercase, specific reaction or question about this video. No marketing. No URLs. No double hyphens. No quotes? We can use quotes but must be straight. Provide a comment. Maybe: "i didn't realize the first 30% mattered that much, any tip on how to structure that intro for AI citations?" That is okay. Keep short. Ensure no punctuation errors. Should not start with capital. Good. Let's produce final.
We need to write a short comment, casual, as a regular developer watching the video. Must start with a specific reaction or question about this video, not generic praise. Should mention something like "wow, 55% of citations from first 30%?" or ask "how do you measure that?" Keep it short, one or two sentences, possibly fragment. Use lowercase start. Avoid polished tone. Make sure no double hyphen, no em dash. Just ASCII. No URLs. No marketing buzzwords. Provide comment only.