Author: Chris Han

Cross-engine AI visibility consensus turns engine agreement into root-cause evidence. What 1,204 tracked step changes across 8 AI engines reveal about causes.

Which sources cited across AI engines overlap? We tracked 607,318 citations on 8 platforms: just 1.9% of URLs win six or more. See the five shared traits.

What actually improves AI visibility? A 630,000-run null test found 56% of reported AEO wins sit inside normal noise. Learn the evidence bar that proves cause.

How long for AI to update answers after an edit? A 312-edit panel with daily sampling gives per-engine medians, false-negative rates by check date, and the exact day a null result becomes real evidence.

AI visibility sample size, settled with real numbers: 23,040 tracked answers show why 200 prompts × 3 runs beats 20 × 30. Get the math and copy the design.

An AEO holdout test isolates what actually moved your AI citations. Four single-brand control designs, noise-floor data from 63 tests, sizing tables, and a six-week protocol.

Multi-turn AI search visibility decays fast: across 1,200 tracked buying chats, only 19% of turn-1 brands survived to turn 8. See how to measure and fix it.

AI search query refinement is the ordered stack of constraints buyers add in one chat. Learn the six rungs, why price kills most brands, and how to run a 45-minute audit.

Buyers asking about the AI downsides of my product get answers from review sites, not vendor pages. 4,320 tracked chats show which sources decide the answer — and how to fix it.

Conversation-level AI visibility metrics score a whole chat, not one prompt: first-mention turn, turn survival, final-recommendation share. Tested on 1,286 conversations.