Native fanout observer
Query strings and sources exposed by a named provider API in one dated run.
Free AI Query Fanout Tool
See the web-search queries OpenAI or Gemini exposes for your topic.
No signup · 20 runs in 24 hoursLOCAL HISTORY
Saved on this device
This browser only · up to 20 results · automatically deleted after 30 daysSaved results remain available on this device until you delete them or they are automatically removed after no more than 30 days.
No saved results yet.
0 runs selected
01 / THE IDEA
Why does an AI search for more than your keyword?
When you ask ChatGPT, Gemini or another AI a question and it searches the web, your single question can become a group of narrower searches. “Which SEO tools suit a small business?” might lead to searches about pricing, features, comparisons and user experience. That split is called AI query fanout.
ai-fanout.com runs a bounded web-search request through OpenAI or Gemini. It then shows only the queries and sources that the selected provider exposes in that run. The tool does not inspect private chats or claim to know every internal search made by a consumer chat interface.
Simplified exampleWhich SEO tools suit a small business?
- 01SEO tools for small businesses
- 02compare SEO tool pricing
- 03easy SEO tools for beginners
- 04SEO tools for keyword research
One possible fanout for explanation. A real run may expose different or fewer searches.
StartA keyword or short question
Choose country and language to match your market.
AI fanoutUp to 8 exposed searches
You see only queries OpenAI or Gemini exposes in the run.
SourcesWebsites behind the searches
A source is connected to a query only when the provider supplies that link.
SaveOptional on your device
Keep up to 20 results for no more than 30 days.
How your question becomes an AI fanout.
The run follows one clear chain: you ask a question, the selected model breaks down the information need, searches the web and shows the search paths it exposed.
- 01Enter a topic
Use a keyword or short question of up to 60 characters.
- 02Choose a model
Select OpenAI or Gemini and add country and language if useful.
- 03Start the AI search
The selected model decides which web searches it needs for your topic.
- 04Review the fanout
Inspect the exposed queries, cited sources and run details.
What does a fanout result actually show?
The result contains three kinds of information. They belong together but mean different things: the query names the subtopic searched, the source names a website used, and the search action counts the search event.
- Search query
- The exact search phrase OpenAI or Gemini exposed in this run.
- Source
- A website named in the result. It is not a ranking or automatic recommendation.
- Search action
- One model search event. It may include several queries at once.
An observation, a search idea and a search metric are not the same.
The tool labels where a result came from. That lets you keep researching when a dataset is missing without inventing demand or hidden provider data.
Query fanout generator or simulator
Modelled research directions without web search. Useful for brainstorming, but not observed provider queries.
SEO coverage and keyword metrics
Use volume, CPC or difficulty only when a keyword source has data for the named market and date. Missing remains unknown, not zero.
05 / AI FANOUT FOR SEO
Turn AI fanout into a better page.
A fanout reveals new research paths, but not every query needs its own URL. First identify the user question behind it and check whether an existing page can already answer it well.
Use fanout for SEO- 01Improve an existing page
When the audience, topic and next step stay the same.
- 02Create a new page
When the query has its own user job, evidence and next decision.
- 03Research first
When sources are weak or the query is only a hypothesis about demand.
- 04Ignore it
When it is only a wording variant, an outlier or irrelevant to your offer.
06 / KEEP WORKING WITH THE QUERIES
ai-fanout.com, SEO Fanout and Crawl Foundry are operated by Matthias Ramahi. The links form one shared workflow and are not independent recommendations.Your fanout is the start of the SEO work.
The queries reveal possible topics and user questions. The next step is deciding whether they justify a new page, an additional section or no change at all.
07 / COMPARE MODELS
OpenAI and Gemini create different fanouts.
Run the same keyword with the same country and language in both models. You can then compare which search questions and sources appear in one result or both.
Understand AI fanout comparisonsCountry and language change the AI fanout.
An English and a German fanout are not simply translations. The selected country can also bring different products, prices, rules or local providers into focus.
Test country and language09 / FANOUT OVER TIME
Why AI fanout queries change.
Search results, available websites and models change over time. Even two nearby runs can therefore expose different searches. Treat each result as a dated snapshot, not a permanent keyword set.
Why fanout results changeTest AI fanout for free with clear limits.
For OpenAI, the web results read by the model also count as input tokens. That is why the input number can be much larger than your keyword. Free use is limited so the tool remains available to everyone.
500maximum output tokens
20 stimeout per run
20free runs per connection in 24 hours
30 daysmaximum local retention
ai-fanout.com does not permanently store your input or the full result. The visible result stays on your device only when you choose Save. Displayed costs are estimates; the provider's bill is final.
11 / AI FANOUT GUIDES
Understand AI query fanout and use it for SEO.
The guides explain fanout queries, sources, model comparisons, changing results and practical SEO decisions. Dated examples show what individual runs actually look like.