ThriveStack citedbyWinning AI Search: AI search optimization courseAll coursesOverviewLive demoBook a demoStart free
Lesson 5.3 · Research article

AI visibility tracking research:
Why the same prompt returns different brands

Fewer than 1 in 100 repeat runs return the same brands. That breaks rank tracking, but measurement still works. This report explains why AI engines answer differently almost every time, and gives the sample sizes and confidence intervals needed to measure AI visibility without fooling yourself.

80

unique completions from 1,000 identical prompts at temperature 0

ThriveStack citedby research
11%

source overlap between ChatGPT and Perplexity on the same prompt

ThriveStack citedby research
0.370

standard error of a single-run detection rate

ThriveStack citedby research
88%

of AI Mode citations absent from the organic top 10

ThriveStack citedby research

If the order changes, what stays steady?

Brands keep showing up, but their order keeps changing. Exact repeats are vanishingly rare, while how often a brand appears is consistent enough to act on.

Brands keep showing up, but their order keeps changing. Exact repeats are vanishingly rare, while how often a brand appears is consistent enough to act on.
Figure 1. From the ThriveStack citedby research article. Click through for the full chart and sources.

How do you use this in the course?

Use it in lesson 5.1, track a prompt baseline: measure visibility across many runs, never a single rank. Open the lesson →

How ThriveStack citedby helps

ThriveStack citedby turns this research into actions for your own brand: tracked prompts, ranked fixes and attribution to revenue.

Apply this to my brand →

Sources for this lesson

  1. AI visibility tracking research: why the same prompt returns different brands (ThriveStack citedby research, 2026) Full study

Figures were checked against each page on Nov 17, 2026. Vendor studies are labelled as vendor claims.

Go deeper
MapHover to open