Free BYOK demo
Watch AI fan your topic into its real questions.
AI engines don't search your keyword. They explode it into a spray of sharper sub-queries, search those, and synthesize the answer. This free query fan-out tool shows you the actual sub-queries, live, on your own Gemini key. Your key never touches our servers.
Straight answer
The hidden sub-queries decide whether you get cited.
An engine rarely searches your exact words. Ask it a question and it quietly expands that into a set of sharper sub-questions, searches those, and synthesizes the answer. Those hidden sub-questions, the fan-out, are what actually decide which pages get cited.
This shows you the real ones.Not an LLM imagining what people might ask, but the genuine queries Gemini grounded its answer in, pulled live from its own grounding metadata, plus Perplexity's related questions if you add a key.
It runs on your keys, in your browser. No account, no server round-trip, nothing stored. The honest way to see the layer every keyword tool is blind to.
A real fan-out in three steps
- 01Add
Your own API key
Paste a free Google AI Studio (Gemini) key, and optionally a Perplexity key for a second engine. Keys stay in your browser; requests go straight to Google and Perplexity, never to a GEO Toolbox server.
- 02Run
A real fan-out, live
Enter a topic. We read the actual sub-queries the engine fired while answering: Gemini's grounded searches, Perplexity's related questions. Real engine output, not an LLM guessing.
- 03Read
Queries, intents, divergence
Every query tagged Fired or Related, clustered into intents. With two engines you also get the divergence map: the intents both chase versus the whitespace only one explores.
More free tools
Got the questions? Make sure AI can read your answers.
Turn the fan-out into trackable prompts with Keyword → AI Prompts, then check the foundations: the AI-Readiness Score grades whether AI agents can reach and parse your site, and the AI Crawler Checker shows which of 34 AI crawlers your robots.txt blocks. New to the idea? Read what AI visibility is.
FAQ
Fan-out, keys and privacy — answered
- 01What is query fan-out?The step where an AI engine expands your question into multiple narrower sub-queries, searches those, and synthesizes the answer from the results. Google's AI Mode, Gemini, and Perplexity all do it. It matters because citations are won at the sub-query level: answer one sub-question well and you can get cited for a topic you'd never rank for as a head keyword.
- 02Do you see or store my API key?No. The key lives in your browser for the session and requests go straight to Google's (and Perplexity's) official endpoints. Nothing is proxied through or logged by our servers, and reloading the page clears it.
- 03Why only Gemini and Perplexity?CORS, browser security. Those two APIs allow direct calls from a browser; OpenAI's doesn't, so a genuinely serverless free demo can't include ChatGPT. The in-app version runs four engines from our servers, on our keys, and adds search volume, page-coverage checks, and the citation landscape.
- 04Is this the same as the paid AI Query Fan-Out feature?Same core idea, a slice of the depth. The free demo shows the real fan-out and the two-engine divergence map. The in-app feature adds more engines, real search volume, a check of how well a given URL already covers each intent, who AI currently cites for those queries, and a ranked content worklist.
- 05I ran it and got no queries. Why?Gemini only fans a topic out when it decides to ground its answer in a web search. Very broad or very personal prompts get answered from the model directly, with no sub-queries to show. Try a more commercial, search-like topic and you'll see the fan-out.
The full fan-out: four engines, volume, coverage, citations.
The in-app AI Query Fan-Out adds ChatGPT and Grok, real search volume, your page's coverage of each intent, the citation landscape, and a ranked content worklist, on our keys.