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.
Tentang alat
Google confirms yang AI fitur mungkin gunakan kueri fan-keluar, tetapi ini tidak disclose setiap langsung sub-kueri. “Generik” adalah terlihat heuristic; “calibrated” adalah model-dihasilkan approximation; hanya grounded provider respons mungkin menjadi marked “teramati.”
Kueri Halaman untuk retrieval competition (opsional) Terpisah halaman dengan ---Sumber---. Mulai ditempel block dengan Sumber: label, atau gunakan bare URL block. URL-hanya memblokir adalah diambil; ditempel konten tetap di browser. Gunakan Anda sendiri Gemini API key (opsional) Gemini API key key adalah dikirim secara langsung dari browser untuk Google dan tidak pernah dikirim untuk situs, disimpan, atau logged di sini. Google mungkin apply project quota atau charges. Jelas field ketika finished. Simulate fan-keluar dan competition
Kueri Fan-Keluar Simulator
Fitur
- Melakukan cakupan gap mean I seharusnya tambah baru section?
- Melakukan alat gunakan embeddings?
- Fitur Always-tersedia deterministik fan-keluar. Opsional langsung BYO-key Gemini approximation tanpa routing key melalui situs. Multi-halaman, per-sub-kueri lexical retrieval competition. Pemenang halaman dan chunk dengan terlihat mencocokkan ketentuan dan runner-up cakupan. Consensus versus corpus-unique claims, numbers, dan quotes dengan eksplisit originality dan mendukung caveats.
- Adalah ini kueri Google atau AI system sebenarnya digunakan?
- Tidak. Generik baris adalah deterministik template dan calibrated baris adalah model-dihasilkan approximation. alat memberi label provenance secara eksplisit dan tidak pernah presents salah satu tier sebagai teramati produk perilaku.
Cara kerja
Batasan Nyata jawaban systems dapat plan, pencarian, dan reformulate di ways ini simulator tidak dapat observe. Generik wording dapat menjadi awkward, classifications adalah keyword aturan, dan lexical mencocokkan misses synonyms dan deeper semantik equivalence. dihasilkan baris dapat juga menjadi irrelevant untuk halaman’s maksud. Treat peta sebagai editorial brainstorming aid, tidak bukti dari peringkat atau inclusion di AI jawaban. Apa terjadi untuk my Gemini API key? Tidak always. Tambah material hanya ketika sub-kueri adalah relevan untuk halaman’s tujuan dan Anda dapat jawaban ini accurately. Memory-led, off-maksud, atau redundant baris dapat menjadi diabaikan. Home › Alat › Kueri Fan-Keluar Simulator
Batasan
- Apa adalah kueri fan-keluar?
- Apa simulasi menunjukkan generik — terlihat deterministik template, tidak provider perilaku. calibrated — model-dihasilkan approximation untuk ini jalankan, berlabel sebagai Gemini atau Workers AI provenance. Jenis — aturan-berdasarkan maksud label seperti sebagai comparative, kebaruan, atau definitional. Jawaban mode — heuristic guess yang task adalah memory-, retrieval-, alat-, atau mixed-led. Covered / Gap — apakah strongest lexical chunk reaches 55% kueri-term cakupan threshold.
- Simulate surrounding sub-kueri AI jawaban mesin mungkin riset dan periksa apakah Anda halaman covers mereka.
- Ini tetap di password field untuk ini tab dan adalah dikirim secara langsung dari Anda browser untuk Google di x-goog-api-key permintaan header. situs tidak terima, store, log, atau persist ini. Google API usage dapat consume Anda project quota atau incur charges di bawah Anda Google akun.
Pertanyaan umum
Gratis, tanpa pendaftaran. Peta riset pertanyaan sekitar kueri, label bagaimana mereka adalah dihasilkan, lalu periksa lexical cakupan terhadap Anda konten.
Bagaimana untuk gunakan ini Masukkan utama kueri Anda inginkan untuk explore. Optionally tempel halaman’s teks atau HTML untuk tambah lexical cakupan periksa. Optionally masukkan Anda Gemini API key untuk langsung Google permintaan. Jika tidak alat tries dibatasi situs model dan jatuh kembali untuk deterministik generik atur. Pilih Simulate fan-keluar, pertahankan hanya relevan sub-kueri, lalu tinjau gaps terhadap strongest halaman chunk sebelum editing.
Kueri fan-keluar adalah gunakan dari multiple related searches atau retrieval tasks untuk bantuan jawaban lebih luas prompt. Pencarian providers mungkin gunakan ini, tetapi tepat sub-kueri untuk langsung jawaban adalah generally tidak exposed.
Bagaimana adalah halaman cakupan calculated?
Karena tidak ada sumber teks adalah yang diberikan, setiap baris says untuk tempel halaman konten daripada daripada inventing cakupan percentage.
halaman adalah split menjadi chunks dan ranked secara lokal dengan lexical retrieval. Cakupan adalah share dari kueri ketentuan represented di strongest chunk; baris adalah marked covered di 55 percent atau lebih tinggi.
Bagaimana ini berfungsi fallback expands entered kueri dengan four tetap riset shapes, menghapus duplicates, dan classifies setiap baris dari terlihat keywords. Dengan key, browser mengirim kueri-hanya prompt secara langsung untuk Gemini 3.5 Flash dan parses satu sub-kueri per baris. Jika yang gagal, dibatasi Workers AI jalur adalah attempted sebelum generik fallback. Untuk cakupan, yang diberikan konten adalah diekstrak, chunked di roughly 300 tokens dengan overlap, ranked lexically, dan dibandingkan dengan 55% threshold. Dihasilkan baris adalah approximations; tidak ada provider’s privat kueri log adalah accessed.
Unduh hasil CSV