Why Gemini Cites You but ChatGPT Does Not: A 960-Answer Study

A page can appear in one AI service and be absent from another. Keep the results separate by engine before deciding what to change.

Your colleague finds the company in Gemini, while your ChatGPT answer recommends competitors. Neither observation automatically invalidates the other. The services may select different sources.

A Prefer study published on September 19, 2026 helps illustrate this issue. Its questions concern AI search, so the findings should not be treated as a benchmark for every industry.[1]

What differed across 960 answers?

On September 13, Prefer sent 80 questions to four engines three times each. Of 1,329 cited domains, 966 appeared in only one engine. A domain is the main part of a site's address—for example, agent-signal.ai.[1]

However, 23 of the 25 most-cited domains appeared in at least three engines. Some sources were shared widely; others appeared in just one service. The engines did not operate in completely separate source worlds.[1]

A citation points to a source. A brand mention is a name appearing in the answer. Record these separately: a company can be mentioned without a link to its website.

What this study does not establish

The researchers used APIs: interfaces through which software sends questions to AI. They did not collect 960 answers by operating the consumer ChatGPT interface. The repeated runs were close together, rather than daily observations.[1]

The study therefore does not tell you that your business underperforms in ChatGPT, or that three daily checks are sufficient. Its practical lesson is to preserve differences instead of hiding them inside one combined score.

The following is our proposed workflow, not a treatment proven by the study.

1. Choose a real buying question

Collect questions from sales calls and enquiries. Start with a question that searches for providers without naming your business. This helps you examine discovery by someone who does not already know you.

For a corporate training provider, an illustrative question is:

How should I choose beginner-friendly AI training for 20 employees, including support after the course?

Replace the conditions with those of your actual customers. Save the wording. If you change the question from lowest price to strongest ongoing support, treat it as a new question. Different recommendations would not be surprising.

2. Preserve the answer and its links

For an initial manual comparison, open ChatGPT and Gemini. Start a new conversation in each and submit the saved question. Keep follow-up conversations separate from these checks.

Record the following together. Include the model or feature where visible; do not invent settings that the interface does not expose.

Record	What it helps establish
Time and exact question	Whether the conditions match
Full answer	Why a provider or product was selected
Company name and known aliases	Whether the brand was mentioned
Links to your website	Which pages readers could visit
Search and execution status	Whether an answer was obtained and search was observed

This is an initial comparison. Tracking change requires repeated collection under consistent conditions and a history of results. Ongoing measurement tools reduce that manual work.

AgentSignal's AI citation view lets you examine results by AI service for registered questions. Read the captured answers and sources as well as the percentage. They provide clues about the information you may need to improve.

3. Read the answers where your page is missing

Open the cited pages and examine how they answer the question. The purpose is to identify missing information, not reproduce a competitor's article.

In the training example, useful conditions might include who provides post-course support, how long it lasts and whether there is an additional fee. If your company already offers that support but has not explained it, add verified details.

If your company does not provide the support that mattered to the recommendation, wording alone will not make it eligible. Consider the offer or a different customer need. Absence is not automatically a writing problem.

4. Compare each engine and question after the change

Record the URL, changes and publication date. Continue the same questions and examine results by engine.

As an illustrative calculation, links in three of ten successfully collected answers produce a 30% URL citation rate for those checks. This is not 30% of the market seeing your business. Keep failed executions separate from valid answers without a citation.

Mentions may rise while links do not. Links may rise without additional enquiries. Separate brand mentions, citations, visits and enquiries to identify the next improvement.

For Google's AI search features, readable important content and useful internal links remain part of the basic requirements. Eligibility does not guarantee inclusion.[2]

Begin with one question related to work you want to win. Record which engine recommended which page and why. That makes the comparison useful for improving information, rather than simply watching a score.