Relevance and position decide who gets cited first
252,000 controlled trials: appear early and answer the question, get cited.
Key numbers
- A controlled RAG testbed ran 252,000 paired trials across six LLMs, changing one content factor at a time.
- Topical relevance and list position are the biggest drivers of being cited first.
- Explicit pricing and recent timestamps help consistently; formatting-only edits do not.
Method and sample
A controlled RAG testbed: 252,000 paired trials, six LLMs, one content variable changed per trial.
What it means for brands
Ask one question first: does the page directly answer the customer's question? Then add price, specs and a recent update.
How SourceSight handles it
SourceSight's prompt library is built from how customers actually ask: find the question types you are missing from entirely, fix those pages, then re-run the same prompts and compare.
Limits
A synthetic RAG environment, not a live engine.
References
Run it on your own project
What the same prompts return across 10 engines is only knowable by running them.
Related research
What 2 million AI citations show: prompt-content match matters most, checklists matter less
Once you control for the domain, the usual AEO checklist (FAQ blocks, structured data, Core Web Vitals) reverses or collapses to zero — domain authority and prompt alignment dominate.
How engines work · 2026-10-07Whose side is the AI shopping assistant on? Change its role and the penalty for sponsored results disappears
The same sponsored listings get treated very differently once the prompt names the platform as the agent's principal — disclosure rules built for humans do not carry over.