Simulate Google's Query Fan-Out to Find Your Content Gaps (Python)

A developer published a Python script that approximates Google's query fan-out by using Claude to generate likely sub-queries for a seed question, then splitting a target page into passages, embedding them with a small open-source model, and scoring each sub-query against its best-matching passage to produce a coverage report that surfaces content gaps first. The approach is motivated by Google's documentation that AI Overviews and AI Mode may issue multiple related searches across subtopics, and by Bing Webmaster Tools' AI Performance report exposing the grounding queries Copilot generates before citing pages. The author recommends running the generation step 3–5 times and merging results, since real fan-out is not deterministic.

When someone asks Google's AI Mode "what's the best way to host a Next.js app for a small team?", Google doesn't run one search. It splits the question into sub-questions and runs those in parallel. Google calls this query fan-out . Its docs say AI Overviews and AI Mode "may use a 'query fan-out' technique, issuing multiple related searches across subtopics and data sources, to develop a response" Search Central https://developers.google.com/search/docs/appearance/ai-features . Microsoft lets you see this happening. Bing Webmaster Tools' AI Performance report lists grounding queries , the background queries Copilot generated before citing your pages. They're shorter and more specific than what users type. That changes what "covering a topic" means. Your page isn't competing for one query. It's competing for 5–15 machine-generated ones, and every sub-question you skip is a retrieval you hand to someone else. You can't see Google's real fan-out. But you can approximate it closely enough to find gaps. Here's a script that does exactly that. seed question ──► LLM generates likely sub-queries │ your page ──► split into passages ──► embed │ for each sub-query: best-matching passage + score │ coverage report gaps first Two parts: pip install anthropic pydantic sentence-transformers requests beautifulsoup4 export ANTHROPIC API KEY=... I'm using Claude for generation and a small open-source embedding model for scoring. Both are swappable. Structured output keeps this clean: we ask for a typed list and get a validated Python object back, with no regex over model text. python fanout.py from typing import Literal import anthropic from pydantic import BaseModel class SubQuery BaseModel : query: str intent: Literal "definition", "comparison", "how-to", "pricing", "constraint", "alternative", "follow-up" class FanOut BaseModel : sub queries: list SubQuery client = anthropic.Anthropic PROMPT = """You are simulating the query fan-out step of an AI search engine. Given a user's question, list the 12 short web searches the engine would most likely run in parallel to build a complete, trustworthy answer. Cover different facets: definitions, comparisons, pricing, constraints size, budget, region, stack , how-to steps, alternatives, and the follow-up a careful user would ask next. Write each one the way a search engine would short, keyword-like , not as a full sentence. User question: {question}""" def fan out question: str - list SubQuery : response = client.messages.parse model="claude-opus-5-5", max tokens=16000, output config={"effort": "low"}, this is a simple task; keep it cheap messages= {"role": "user", "content": PROMPT.format question=question } , output format=FanOut, return response.parsed output.sub queries Run it on a real question: for sq in fan out "best way to host a Next.js app for a small team" : print f" {sq.intent:11} {sq.query}" comparison vercel vs netlify vs cloudflare pages nextjs pricing vercel pro pricing per seat 2026 constraint nextjs self hosting docker small team how-to deploy nextjs app router to cloudflare constraint nextjs ISR support hosting providers alternative nextjs hosting without vercel follow-up nextjs hosting cold starts serverless ... Generated output varies between runs. That's fine. Run it 3–5 times and merge the results, because real fan-out isn't deterministic either. AI systems retrieve passages , not whole pages. We'll split by headings and paragraphs, keeping each heading attached to its text so the passage still makes sense on its own. python passages.py import requests from bs4 import BeautifulSoup def page passages url: str, min words: int = 25 - list str : html = requests.get url, timeout=20, headers={"User-Agent": "fanout-audit/1.0"} .text soup = BeautifulSoup html, "html.parser" for tag in soup "script", "style", "nav", "footer", "header", "aside" : tag.decompose root = soup.find "main" or soup.find "article" or soup.body passages, heading = , "" for el in root.find all "h1", "h2", "h3", "p", "li", "td" : text = " ".join el.get text " ", strip=True .split if el.name in "h1", "h2", "h3" : heading = text continue if len text.split = min words: passages.append f"{heading}: {text}" if heading else text return passages Note that this reads the raw HTML , the way many AI fetchers do. If your content only appears after JavaScript runs, this returns almost nothing, and that's a finding in its own right see Part 9 . python coverage.py from sentence transformers import SentenceTransformer, util model = SentenceTransformer "BAAI/bge-small-en-v1.5" def coverage sub queries, passages : q emb = model.encode sq.query for sq in sub queries , normalize embeddings=True p emb = model.encode passages, normalize embeddings=True sims = util.cos sim q emb, p emb n queries, n passages rows = for i, sq in enumerate sub queries : best = int sims i .argmax rows.append { "query": sq.query, "intent": sq.intent, "score": float sims i best , "best passage": passages best :110 + "…", } return sorted rows, key=lambda r: r "score" gaps first python main.py import sys from fanout import fan out from passages import page passages from coverage import coverage question, url = sys.argv 1 , sys.argv 2 Merge a few runs to smooth out randomness. seen, subs = set , for in range 3 : for sq in fan out question : key = sq.query.lower if key not in seen: seen.add key subs.append sq passages = page passages url print f"{len subs } sub-queries · {len passages } passages\n" for r in coverage subs, passages : flag = "GAP " if r "score" < 0.55 else "weak" if r "score" < 0.68 else "ok " print f"{flag} {r 'score' :.2f} {r 'intent' } {r 'query' }" if flag = "ok ": print f" closest: {r 'best passage' }" python main.py "best way to host a Next.js app for a small team" https://your-site.com/blog/nextjs-hosting Illustrative output. Your numbers will differ. 33 sub-queries · 41 passages GAP 0.41 pricing vercel pro pricing per seat 2026 closest: Why we moved: Our bill grew faster than our traffic… GAP 0.47 constraint nextjs ISR support hosting providers closest: Deploying to Cloudflare: The adapter handles most… weak 0.61 follow-up nextjs hosting cold starts serverless ... ok 0.79 comparison vercel vs netlify vs cloudflare pages nextjs bge-small on English technical content. Calibrate them by checking a few passages yourself: find the score below which the "closest passage" clearly doesn't answer the question. If you want a reality check, compare your generated sub-queries with Bing's real grounding queries Bing Webmaster Tools → AI Performance, CSV export . Matching phrasing there is the closest thing to ground truth you'll get today. Coverage tells you whether your page can answer the sub-questions. It doesn't tell you whether AI engines actually do pick you. For that you need to run the real prompts across ChatGPT, Perplexity, Gemini and others over time and track who gets mentioned. We built Vista AI's AI rank tracker https://www.vistaai.io/features/ai-rank-tracker for that part. The script above is the free, local half of the loop: find gaps, fix them, then measure. The full script is ~120 lines. If you adapt it different embedding model, multilingual, or batch mode over a sitemap , share it in the comments. Next in the series: Track ChatGPT, Perplexity and Claude referrals properly.