datagrit › Data › Google AI Overview Citation & Brand Tracker

Google AI Overview Citation & Brand Tracker

Track which sources and domains Google AI Overview cites for each search query, with brand mentions and organic rank in one row.

Google AI Overview Citation & Brand Tracker checks a list of Google search queries and tells you, for each one, whether Google shows an AI Overview, which sources it cites and in what order, whether your brand is named in the answer, and where your domain ranks in the organic results. Every query becomes one flat row you can export as JSON, CSV or Excel, call through the Apify API, or feed into n8n, Make and AI agents through MCP.

It is built for SEO and content teams, agencies and brand owners who want to measure visibility inside AI answers (often called AEO or GEO) instead of only in the ten blue links.

Why track AI Overview citations?

• Measure AI visibility. See for which queries your domain is cited, at which citation position, and for which queries a competitor is cited instead.
• Watch your brand in the answer text. Brand names are counted inside the AI Overview text, so you can tell a mention without a link from a citation.
• Compare AI and organic rank. The same row shows your first organic position, so pages that rank but are never cited stand out.
• Report by market. Set the country and language and run the same list for several markets on a schedule to build a trend.
• Feed content planning. The full AI Overview text and the list of cited pages show what Google considers a good source for a topic.

Output fields

Each row contains the query, market, aiOverviewPresent, aiOverviewText, citationCount, citedDomains, citations, the tracked domain fields (trackedDomainCited, trackedDomainsCited, bestCitationPosition, trackedDomainOrganicRank), the brand fields (brandMentioned, brandsMentioned, brandMentionCount), organicResults, sourceUrl and scrapedAt. Tracking fields are null when you did not set domains or brands.

A status row has found: false, a reason (noResults or fetchFailed) and a message; it is not charged.

How reliable is the data?

aiOverviewPresent: false means the results page Google returned for that request had no AI Overview; the row still carries the organic results. Google decides per request whether to show an AI Overview, so a query can flip between checks, which is why the Actor is meant to run on a schedule. An unreadable page is requested up to three times before it becomes a free fetchFailed row. The run message counts how many AI Overviews were found, how many had parsed citations and how many queries had organic results. If Google changes its page layout, the run fails with a message instead of delivering wrong rows: a page that carries citation records or the AI Overview disclaimer ("AI responses may include mistakes") but no AI Overview container is treated as unreadable, and a run that parses no organic results from any page stops with an error. Queries without an AI Overview (local, navigational and result queries often have none) and AI Overviews without source links are normal and never fail a run.

Is it legal to scrape Google results?

The Actor reads publicly visible search result pages without logging in and without bypassing access controls. You are responsible for using the data in line with applicable laws and the terms of the service. If you find an issue, open it in the Issues tab.

Output fields

Every result is one flat record, so it drops straight into a spreadsheet, a database or a CRM.

Sample record

{
  "query": "what is kubernetes",
  "gl": "us",
  "hl": "en",
  "found": true,
  "aiOverviewPresent": true,
  "aiOverviewText": "Kubernetes is an open-source system for automating deployment, scaling and management of containerized applications.",
  "citationCount": 7,
  "citedDomains": [
    "kubernetes.io",
    "redhat.com"
  ],
  "citations": [
    {
      "position": 1,
      "url": "https://kubernetes.io/docs/concepts/overview/",
      "domain": "kubernetes.io",
      "site": "Kubernetes"
    }
  ],
  "trackedDomainCited": true,
  "trackedDomainsCited": [
    "kubernetes.io"
  ],
  "bestCitationPosition": 1,
  "brandMentioned": true,
  "brandsMentioned": [
    "Kubernetes"
  ],
  "brandMentionCount": 4,
  "organicResultCount": 9,
  "trackedDomainOrganicRank": 2,
  "organicResults": [
    {
      "position": 1,
      "title": "Kubernetes",
      "domain": "kubernetes.io",
      "displayedUrl": "https://kubernetes.io"
    }
  ],
  "reason": "fetchFailed",
  "message": "Google did not return a readable results page for this query after several attempts.",
  "sourceUrl": "https://www.google.com/search?q=what+is+kubernetes&hl=en&gl=us",
  "scrapedAt": "2026-10-08T08:00:00.000Z"
}

Input

Call it from your code

Run the Actor and get the results in one request. Replace YOUR_APIFY_TOKEN with the token from your Apify account settings.

curl -X POST "https://api.apify.com/v2/acts/datagrit~google-ai-overview-citation-tracker/run-sync-get-dataset-items?token=YOUR_APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"queries":["how to lower blood pressure","what is kubernetes","best running shoes for flat feet","how does a heat pump work","is intermittent fasting safe","what causes inflation","how to learn python fast","symptoms of vitamin d deficiency","how to start a vegetable garden","what is a roth ira","how to remove a stripped screw","what is a good credit score"],"trackedDomains":["kubernetes.io","mayoclinic.org"],"brandNames":["Kubernetes"],"maxItems":14}'

import { ApifyClient } from 'apify-client';

const client = new ApifyClient({ token: process.env.APIFY_TOKEN });
const run = await client.actor('datagrit/google-ai-overview-citation-tracker').call({
  "queries": [
    "how to lower blood pressure",
    "what is kubernetes",
    "best running shoes for flat feet",
    "how does a heat pump work",
    "is intermittent fasting safe",
    "what causes inflation",
    "how to learn python fast",
    "symptoms of vitamin d deficiency",
    "how to start a vegetable garden",
    "what is a roth ira",
    "how to remove a stripped screw",
    "what is a good credit score"
  ],
  "trackedDomains": [
    "kubernetes.io",
    "mayoclinic.org"
  ],
  "brandNames": [
    "Kubernetes"
  ],
  "maxItems": 14
});
const { items } = await client.dataset(run.defaultDatasetId).listItems();
console.log(items.length, items[0]);

from apify_client import ApifyClient
import os

client = ApifyClient(os.environ["APIFY_TOKEN"])
run = client.actor("datagrit/google-ai-overview-citation-tracker").call(run_input={
  "queries": [
    "how to lower blood pressure",
    "what is kubernetes",
    "best running shoes for flat feet",
    "how does a heat pump work",
    "is intermittent fasting safe",
    "what causes inflation",
    "how to learn python fast",
    "symptoms of vitamin d deficiency",
    "how to start a vegetable garden",
    "what is a roth ira",
    "how to remove a stripped screw",
    "what is a good credit score"
  ],
  "trackedDomains": [
    "kubernetes.io",
    "mayoclinic.org"
  ],
  "brandNames": [
    "Kubernetes"
  ],
  "maxItems": 14
})
items = client.dataset(run["defaultDatasetId"]).list_items().items
print(len(items), items[0] if items else None)

Frequently asked questions

Guide

How to track which sources Google AI Overview cites for your queries — Check a list of Google queries for AI Overview citations, brand mentions and organic rank, per country, in Python or cURL and without a browser.

Related Actors