Analysis of 8,609 AI responses finds user context can reshape brand recommendations, with measurable shifts in brand selection and geographic relevance.

ABINGDON, VA, UNITED STATES, September 23, 2026 /EINPresswire.com/ -- New research analyzing 8,609 AI responses has found that information an AI system knows about a user can influence which brands it repeatedly recommends, raising questions about how marketers measure brand visibility across AI platforms.

The study, The Personalization Gap: How a Model's Knowledge of the User Reshapes Brand Recommendations in Generative AI, was co-authored by Cassie Wilson Clark, AI search visibility consultant and host of Found in AI, and Joao da Silva, co-founder of friction AI. Researchers tested ChatGPT, Gemini, Claude and Perplexity across six personas, three consumer categories and 30 prompts in the UK, comparing history-free APIs, temporary logged-in sessions and accounts primed with user histories.

After accounting for normal response variation, ChatGPT showed 16.0 percentage points of history-associated brand-set divergence above the study's Volatility Floor. Gemini showed 33.3 percentage points, the largest effect among the four platforms tested. Perplexity showed a smaller effect of 7.2 percentage points. Claude showed no detectable history-associated change in its recurring brand set beyond normal volatility, although its search behavior changed when user context was introduced.

The researchers call the measurable difference between brands recommended with and without persistent user context the Personalization Gap.
“Marketers have been trying to measure AI visibility as though there is one version of the answer we're all competing to appear in,” Clark said. “Our research suggests that's becoming harder to defend. User context can become another variable, and geography was the clearest example we observed.”

Geography emerged as the clearest personalization dimension observed in the UK-based experiment. In history-primed accounts, researchers found a 6.6 percentage-point increase in UK/EU-origin brand share, a 4.9 percentage-point decrease in US-origin brand share and a 6.0 percentage-point increase in citations from .uk domains.

The findings suggest geographic relevance can influence which brands AI systems retrieve, cite and recommend, with implications for UK and European marketers competing for visibility against larger international brands. However, the results do not establish that localization will automatically improve AI visibility or that personalized recommendations consistently favor regional brands.

“AI systems aren't simply pulling from one universal list of the most authoritative brands,” Clark said. “If the context surrounding the person asking can influence the recommendation environment, then understanding your audience and your market becomes part of understanding AI visibility.”
The study also examined whether history-free measurement could reproduce brand recommendations observed in personalized accounts. Across 173 matched comparisons, API sampling recovered 79% of recurring brands observed in history-primed sessions, compared with 95% for temporary logged-in sessions at the same sampling depth.

The findings do not invalidate API-based AI visibility tools. Instead, they highlight the importance of sampling depth, collection methods, and user context when interpreting results. “A screenshot is evidence that an answer happened. It isn't a measurement system,” Clark said. “Marketers need to look for recurring patterns rather than treating every missing brand mention as a content problem.” For marketers investing in generative engine optimization (GEO), the findings suggest that audience research, regional relevance and measurement methodology should be considered alongside content and authority.

The nine-day study analyzed 8,609 AI responses across four platforms in the UK. Read the full research on Zenodo. Clark has also published a marketer-focused analysis, The Personalization Gap: What 8,609 AI Responses Tell Us About Brand Visibility, examining the implications for AI visibility measurement, localization, and audience research. Clark and da Silva discussed the experiment in the Sept. 22 episode of the Found in AI podcast.

About Cassie Clark Marketing

Cassie Clark is an AI search visibility consultant, content strategist, and host of the Found in AI podcast. Through Cassie Clark Marketing, she helps brands understand how they are discovered, represented, and recommended across AI search platforms and develops strategies that connect content, authority, and measurement to improve AI visibility.

About friction AI

friction AI helps companies understand how AI systems describe, compare, and recommend their brands. Co-founded by Joao da Silva, the company develops technology to measure and analyze brand visibility across generative AI platforms.

Cassie Clark
Cassie Clark Marketing
cassie@cassieclarkmarketing.com
Visit us on social media:
LinkedIn
YouTube