ChatGPT Search Can Pre-Select Brands Before Retrieval, Research Shows

ChatGPT's in-chat search process can surface brand preferences before it has retrieved web results. Research tracking the system's fan-out queries, the sub-queries used to investigate a prompt, found that vendor names sometimes appear at the opening stage.

Separate experiments also found that the language of a query and the user's exit location can materially change which commercial brands ChatGPT recommends. That does not mean every ChatGPT answer is predetermined, or that a brand mention is proof of a fixed ranking rule.

It does mean that AI search visibility is shaped by more than the pages retrieved for a single query. For businesses trying to appear in product recommendations, category alignment, language and market context may influence whether the brand is considered at all.

What the evidence says about brand selection in ChatGPT search

Radyant's open fan-out dataset, based on 615 buying questions and 3,842 ChatGPT fan-out runs collected from August 11 to 17, 2026, found that 28.6% of opening fan-out queries named a vendor. The reported confidence interval was 25.6% to 31.6%. In the remaining roughly 71.4% of runs, the opening query did not name a vendor.

The pattern is more complex than a simple list of preferred brands. When a brand appeared in an opening fan-out query, multiple brands often appeared in the same run. Radyant also found that a brand could appear in a final answer without appearing in any sub-query in that run, at rates ranging from 9% to 29%.

Fan-out visibility is therefore a useful signal, but not a complete explanation for why a business is named in an answer. Independent B2B SaaS analyses have identified recurring fan-out patterns, including searches for an official brand page, documentation, domain-restricted pages and multi-brand comparisons. Those analyses repeatedly observed brands such as Braze, MoEngage, Iterable and Insider being selected in relevant category queries.

The practical interpretation is that ChatGPT can draw on established brand-category associations while forming its search plan.

A separate arXiv study of query language and exit IP in commercial recommendations tested logged-out ChatGPT and API runs across languages and countries. Across 234 runs, the researchers found that top recommendations were unstable even for identical runs. They also found that query language and exit location acted as separate factors in brand selection: English queries tended to feature global brands, while other languages and local connections could favor domestic brands or replace global names altogether.

Observed condition	What the research found	Visibility implication
Opening fan-out query names a vendor	28.6% of Radyant's tracked opening queries named a vendor.	A brand can enter the search process before retrieved results are presented.
Opening fan-out query names no vendor	About 71.4% of tracked opening queries did not name a vendor.	Pre-selection is measurable but not universal.
Language and exit location change	The arXiv study found that language and location strongly affected which brands were recommended.	Testing one English-language result cannot represent every market.

Why this is a visibility issue, not just a search-ranking issue

Traditional search optimization often starts with a results page and asks which sources rank. Generative search adds an earlier stage: the system may decide which concepts, sources or brands to investigate before it composes its answer.

A company that is absent from that initial framing may still be found through retrieval or named in the final response, but it may have fewer routes into the answer. This matters particularly for commercial prompts such as requests for software recommendations, alternatives or the best provider in a category.

In these contexts, a model's existing association between a category and a known set of vendors can shape comparison queries. Retrieved pages remain relevant, but they operate alongside the model's choice of what to look for.

The evidence also argues against treating a single prompt as a reliable audit. Identical runs can produce different leading recommendations, and results can vary by language and exit location. A favorable mention in one test does not establish durable visibility. Equally, one missed mention does not prove a business is permanently excluded.

How businesses can test and respond

The goal is not to try to reverse-engineer a hidden rule from a handful of chats. Instead, businesses should measure whether their brand is consistently associated with the category and markets that matter to them. A structured test can reveal patterns that a one-off conversation misses.

Useful steps include:

• Test a set of realistic buying, comparison and alternative-to prompts, rather than only searching for your own brand name.
• Repeat prompts across multiple runs and record both cited answers and, where observable, fan-out queries.
• Run relevant tests in the languages and locations where you sell, because those variables can alter recommendations.
• Review whether your site and public materials clearly connect the brand to the specific category, use cases and terminology customers use.
• Build content that supports several plausible discovery paths, including official product pages, clear documentation and category-focused explanations.

Clear category signals are especially important for less established brands. The research does not show a guaranteed method for becoming pre-selected, and businesses should not assume that adding a phrase to a page will alter ChatGPT's internal planning.

But consistent, authoritative material that explains what a company offers and where it fits gives AI systems clearer evidence when they do retrieve and synthesize information.

AI search visibility is becoming a measurable business channel, not an assumption. Scalevise can help you assess how your brand appears across realistic AI recommendation prompts, languages and market contexts, then turn the findings into practical content and visibility priorities.

Use the Scalevise AI Visibility and GEO Checker to identify where your business is being surfaced, overlooked or compared with competitors, and start an AI visibility scan.

Frequently Asked Questions

Does ChatGPT always choose brands before searching?

No. Radyant's dataset found vendor names in about 28.6% of opening fan-out queries, while roughly 71.4% named no vendor at that stage.

Can a brand appear in a ChatGPT answer without appearing in fan-out queries?

Yes. Radyant found that brands appeared in final answers without appearing in any sub-query in the same run 9% to 29% of the time.

Do language and location affect ChatGPT's commercial recommendations?

Yes. The cited arXiv study found that query language and exit IP strongly influenced which brands were named, with local brands sometimes replacing global ones.

What is the most practical way to audit AI search visibility?

Test realistic category, recommendation and comparison prompts repeatedly across the relevant languages and locations, then track which brands and sources appear over time. For measurement approaches and why analytics alone can miscount AI-driven discovery, consider how to audit AI search visibility.

Conclusion

The available research shows that ChatGPT search can incorporate brand associations before retrieval, while final recommendations remain variable and influenced by language and location. Businesses should treat AI search visibility as an ongoing measurement problem.

Repeated, market-specific testing and clear category-focused information provide a more defensible response than relying on a single AI answer.