Query Fan-Out Simulator
Free, no signup. Map the research questions around a query, label how they were generated, then check lexical coverage against your content.
Separate pages with ---SOURCE---. Start a pasted block with SOURCE: label, or use a bare URL block. URL-only blocks are fetched; pasted content stays in the browser.
Use your own Gemini API key (optional)
The key is sent directly from this browser to Google and is never sent to this site, stored, or logged here. Google may apply project quota or charges. Clear the field when finished.
Requests are processed by our server and are not stored after processing. Generic sub-queries and pasted-source competition run locally. The query may be sent to the selected AI path for optional calibration; URL-only sources are fetched through the protected text endpoint. Pasted source text is not sent for calibration. Anonymous run-level outcome counters may be used for aggregate research; URLs, domains, IPs, and identifiers are never included, and no statistic is released below 100 runs.
Sample report Deterministic generic example
For canonical tags with no page text, the local generator always returns five unique rows:
canonical tags · generic · entity-expansion · mixed
What is canonical tags? · generic · definitional · mixed
canonical tags benefits and limitations · generic · entity-expansion · mixed
canonical tags vs alternatives · generic · comparative · mixed
How to choose canonical tags · generic · implicit · mixed
Because no source text was supplied, every row says to paste page content rather than inventing a coverage percentage.
How to use it
- Enter the main query you want to explore.
- Optionally paste a page’s text or HTML to add a lexical coverage check.
- Optionally enter your Gemini API key for a direct Google request. Otherwise the tool tries the bounded site model and falls back to the deterministic generic set.
- Select Simulate fan-out, keep only relevant sub-queries, then review gaps against the strongest page chunk before editing.
Site passport Local context for this saved site
Local data
Saved targets, named lists, and recent check summaries remain only in this browser.
Rate this tool
What the simulation shows
- generic — a visible deterministic template, not provider behavior.
- calibrated — a model-generated approximation for this run, labeled as Gemini or Workers AI provenance.
- Type — a rule-based intent label such as comparative, freshness, or definitional.
- Answer mode — a heuristic guess that the task is memory-, retrieval-, tool-, or mixed-led.
- Covered / Gap — whether the strongest lexical chunk reaches the 55% query-term coverage threshold.
How it works
The fallback expands the entered query with four fixed research shapes, removes duplicates, and classifies each row from visible keywords. With a key, the browser sends a query-only prompt directly to Gemini 3.5 Flash and parses one sub-query per line. If that fails, the bounded Workers AI path is attempted before the generic fallback. For coverage, supplied content is extracted, chunked at roughly 300 tokens with overlap, ranked lexically, and compared with a 55% threshold. Generated rows are approximations; no provider’s private query logs are accessed.
Features
- Always-available deterministic fan-out.
- Optional direct BYO-key Gemini approximation without routing the key through this site.
- Multi-page, per-sub-query lexical retrieval competition.
- Winning page and chunk with visible matching terms and runner-up coverage.
- Consensus versus corpus-unique claims, numbers, and quotes with explicit originality and support caveats.
Limitations
Real answer systems can plan, search, and reformulate in ways this simulator cannot observe. Generic wording can be awkward, classifications are keyword rules, and lexical matching misses synonyms and deeper semantic equivalence. A generated row can also be irrelevant to the page’s intent. Treat the map as an editorial brainstorming aid, not evidence of ranking or inclusion in an AI answer.
AI answers may continue to reflect cached or previously retrieved material for days to weeks after a fix. Recheck over time before treating an unchanged answer as proof that the fix failed.
Frequently asked questions
What is query fan-out?
Query fan-out is the use of multiple related searches or retrieval tasks to help answer a broader prompt. Search providers may use it, but the exact sub-queries for a live answer are generally not exposed.
Are these the queries Google or an AI system actually used?
No. Generic rows are deterministic templates and calibrated rows are a model-generated approximation. The tool labels provenance explicitly and never presents either tier as observed product behavior.
How is page coverage calculated?
The page is split into chunks and ranked locally with lexical retrieval. Coverage is the share of query terms represented in the strongest chunk; a row is marked covered at 55 percent or higher.
Does a coverage gap mean I should add a new section?
Not always. Add material only when the sub-query is relevant to the page’s purpose and you can answer it accurately. Memory-led, off-intent, or redundant rows can be ignored.
Does the tool use embeddings?
No. The current coverage check uses BM25/cosine-style lexical components and reports that embeddings were not evaluated. Semantic coverage can therefore be missed when a passage uses different wording.
What happens to my Gemini API key?
It stays in the password field for this tab and is sent directly from your browser to Google in the x-goog-api-key request header. The site does not receive, store, log, or persist it. Google API usage can consume your project quota or incur charges under your Google account.
Feature requests for Query Fan Out
Upvote what you want most. New ideas can be submitted from the floating Feedback menu; requests appear here once approved, and the most-wanted rise to the top.
You won't be emailed about that request anymore.
Loading…
➕ Request a feature
New requests are reviewed before they appear here.
Sobre a ferramenta
Grátis, sem cadastro. Mapa o research questions around um consulta, rótulo como they foram gerado, então verificação lexical coverage against seu conteúdo.
Simulate o surrounding sub-queries um AI answer engine pode research e verificação whether seu página covers them.
Recursos
- Features Always-available determinístico fan-out. Optional direto BYO-key Gemini approximation sem routing o chave por este site. Multi-page, per-sub-query lexical retrieval competition. Winning página e chunk com visible correspondente termos e runner-up coverage. Consensus versus corpus-unique afirmações, numbers, e quotes com explicit originality e sustentam caveats.
- Como usar Enter o main consulta você want para explore. Optionally paste um page’s texto ou HTML para adicione um lexical coverage verificação. Optionally enter seu Gemini API chave para um direto Google solicitação. Caso contrário o ferramenta tries o limitado site model e falls back para o determinístico generic set. Selecione Simulate fan-out , mantenha somente relevant sub-queries, então revisão gaps against o strongest página chunk antes editing.
- O página é split em chunks e ranked locally com lexical retrieval. Coverage é o participação de consulta termos represented em o strongest chunk; um linha é marked covered em 55 percent ou higher.
- Como funciona O fallback expands o entered consulta com four fixed research shapes, removes duplicates, e classifies cada linha de visible keywords. Com um chave, o navegador sends um query-only prompt diretamente para Gemini 3.5 Flash e parses um sub-query por line. If que fails, o limitado Workers AI caminho é attempted antes o generic fallback. Para coverage, fornecido conteúdo é extracted, chunked em roughly 300 tokens com overlap, ranked lexically, e comparado com um 55% threshold. Gerado linhas são approximations; Não provider’s privado consulta logs são accessed.
Como funciona
Consulta fan-out é o usar de várias related pesquisa ou retrieval tasks para help answer um broader prompt. Pesquisa providers pode usar isso, but o exato sub-queries para um ativo answer são generally não exposed.
Limitações
- Limitations Real answer systems pode plan, pesquisa, e reformulate em ways este simulator cannot observe. Generic wording pode ser awkward, classifications são keyword rules, e lexical correspondente misses synonyms e deeper semantic equivalence. Um gerado linha pode also ser irrelevant para o page’s intenção. Trate o mapa como um editorial brainstorming aid, não evidência de classificação ou inclusion em um AI answer.
- Não. O atual coverage verificação usa BM25/cosine-style lexical components e relatórios que embeddings foram não avaliado. Semantic coverage pode therefore ser missed quando um passage usa different wording.
Perguntas frequentes
O que é consulta fan-out?
consulta fan-out é o usar de múltiplos relatdo searches ou retrieval tasks para help resposta a broader prompt. pesquisa providers may usar ele, but o exatos sub-queries para a ao vivo resposta are generalmente não exposto.
Are estes o consultas Google ou um IA sistema na verdade usado?
O resultado é uma leitura dos dados de entrada, não uma garantia de comportamento de um mecanismo externo. Valide a conclusão com uma amostra real e com a documentação correspondente.
Como é página coverage calculatdo?
o página é divisão em blocos e rankdo localmente com lexical retrieval. Coverage é o participação de consulta termos representdo em o strongest bloco; a linha é marcado coverdo em 55 por cento ou higher.
faz a coverage gap significar I should add a novo seção?
não sempre. Add material apenas quando o sub-query é relevant para o página’ purpose e você pode resposta ele accuratemente. Memory-ldo, off-intent, ou redundant linhas pode be ignordo.
faz o ferramenta usar embeddings?
não. o atual coverage verificar usa BM25/cosine-style lexical components e relata que embeddings were não evaluatdo. Semantic coverage pode therefore be missdo quando a passage usa diferente wordndo.
What happens para my Gemini API key?
ele stays em o password campo para esta aba e é enviado diretamente de seu navegador para Google em o x-goog-api-key solicitação cabeçalho. o site faz não receive, store, log, ou persist ele. Google API usage pode consume seu project quota ou incur charges em seu Google conta.