AI Visibility Tracker

AI Visibility Tracker is an Apify Actor that shows whether AI search engines mention and cite your brand. For each prompt it asks Google AI Overviews, Gemini and Claude the way a customer would. It then records whether your brand is named, its position against your competitors, how the answer describes you, which sites were cited, every other brand named, and what changed since your last run. It costs $0.05 per answer, plus $0.50 for an optional client-ready report.

Use it as an AI visibility / GEO tracking API:

• run it from the form or from code
• schedule it weekly to see changes over time
• let AI agents (Claude, ChatGPT, Cursor) use it through Apify's MCP server

Quick facts

• Engines:
  • Google AI Overviews, read from Google's results; overviews that load late are read in a real browser
  • Gemini with Google Search grounding
  • Claude with web search
• Per answer you get:
  • mentioned or not, with mention count and position among the brands you track
  • whether your site is cited, and at what position
  • which competitors are named or cited
  • sentiment, with a one-line summary of how you're described
  • every brand the answer names
  • the cited URLs and domains
  • the full answer
• A client-ready HTML report per run:
  • mention rate, citation rate, share of voice, average position and sentiment
  • results by engine, and brands compared side by side
  • a prompt-by-prompt grid
  • the sites AI engines cite most, and changes since the last run
• Hidden competitors: every company or product named in the answers is listed, including ones you don't track.
• Changes over time: each run is compared with the previous one, marking gained and lost mentions and citations per prompt and engine.
• Alerts: a Slack or Discord message (or JSON to Zapier, Make, n8n or any URL) when you gain or lose a mention or citation.
• No prompt list? Give it topics such as "team wiki software" and it writes realistic prompts for you.
• Price:
  • $0.05 per answer checked; $0.045 on Silver and $0.04 on Gold and above
  • $0.50 per report
  • answers that couldn't be checked are free

What can you do with it?

• Brands and marketing teams. See whether ChatGPT-style answers recommend you or your competitors for the questions your buyers ask. Then track whether your content and PR move the numbers.
• SEO and GEO agencies. Run one tracker per client: schedule weekly runs and send the report.
• PR and outreach. "Sites AI engines cite most" shows which publications and review sites the engines rely on, so you know where to get featured.
• Product marketing. Read how each engine describes you, what it praises and what it warns about, and which competitors it names first.

How to track your AI visibility

1. Click Try for free.
2. Enter your brand (for example Notion) and your domain (notion.so).
3. Add competitors as names or Name (domain.com), for example Obsidian (obsidian.md).
4. Add prompts: questions your buyers ask, such as best note-taking app for teams. Or add topics and let the Actor write the prompts.
5. Choose the engines and the country, then click Start.
6. Open the Visibility report under the run's Output, or download the data as JSON, CSV or Excel.
7. Schedule the run weekly. Each run is compared with the last, and the report lists what changed.

Input example

{
  "brand": "Notion",
  "domain": "notion.so",
  "competitors": ["Evernote (evernote.com)", "Obsidian (obsidian.md)", "Microsoft OneNote (onenote.com)", "Confluence (atlassian.com)"],
  "prompts": [
    "What is the best note-taking app for teams?",
    "Notion vs Obsidian for personal knowledge management",
    "Best wiki software for a startup"
  ],
  "topics": ["project documentation tools"],
  "promptsPerTopic": 5,
  "engines": ["google-ai-overviews", "gemini", "claude"],
  "country": "us"
}

Output example (one answer)

{
  "prompt": "What is the best note-taking app for teams?",
  "engine": "google-ai-overviews",
  "engineLabel": "Google AI Overviews",
  "status": "answered",
  "visibility": "cited",
  "brandMentioned": true,
  "brandRank": 1,
  "brandCited": true,
  "brandCitationRank": 1,
  "brandSnippet": "Notion is the best all-around note-taking and workspace app for teams due to its powerful real-time collaboration, flexible…",
  "brandsInOrder": ["Notion", "Microsoft OneNote"],
  "competitorsMentioned": ["Microsoft OneNote"],
  "competitorsCited": [],
  "sentiment": "positive",
  "sentimentSummary": "Best all-around note-taking and workspace app for teams with real-time collaboration, flexible databases, and custom wiki building.",
  "brandsNamed": ["Notion", "Zapier", "Microsoft OneNote", "Microsoft 365", "Fellow", "Apple Notes", "Google Keep"],
  "citedDomains": ["notion.so", "zapier.com", "pcmag.com", "youtube.com"],
  "citedUrls": ["https://www.notion.so", "https://zapier.com/blog/best-note-taking-apps/", "https://www.pcmag.com/picks/the-best-note-taking-apps"],
  "mentionChange": "unchanged",
  "citationChange": "unchanged",
  "previousCheckedAt": "2026-10-03T16:02:01.130Z",
  "answer": "Notion is the best all-around note-taking and workspace app for teams…",
  "checkedAt": "2026-10-03T16:07:42.591Z"
}

Output fields

Field	Description
prompt, engine, engineLabel, model, country	What was asked, and where
status	answered, or no_ai_overview when Google showed none for the prompt
visibility	cited, mentioned or absent
brandMentioned, brandMentions, brandRank	Whether and how often you're named, and your position among tracked brands by first mention (1 = named first)
brandCited, brandCitationRank, brandInSources	Whether a cited source is on your domain and at what position; whether your site was among the pages consulted
brandSnippet, sentiment, sentimentSummary	The sentence where you're named, and how the answer portrays you
brandsInOrder, mentionedBeforeBrand, competitorsMentioned, competitorsCited	How you compare with the competitors you track
brandsNamed	Every company or product the answer names, tracked or not
citedUrls, citedDomains, sourceCount	The sources the answer cites, and how many sites were consulted
mentionChange, citationChange, previousCheckedAt	gained, lost, unchanged or new against the last run
answer, answerLength	The full answer (switch off with "Include full answer text")

The Run summary (key-value store OUTPUT) holds the same totals as the report in JSON:

• rates by engine
• the competitor comparison
• the sites cited most
• the brands named most
• changes since the last run
• anything not checked, and why

Alerts when your AI visibility changes

Paste a Slack or Discord webhook URL into Alert webhook URL, then schedule the Actor weekly. After each run that gains or loses a mention or citation, you get a message like this:

AI visibility for Notion: mentioned in 92.9% (▲ 7.1 pts), cited in 14.3% (no change), share of voice 52% (▼ 0.6 pts).
▲ Mention gained in Claude: "What is the best project management tool for small teams?"
▼ Citation lost in Google AI Overviews: "Best wiki software for a startup"
Run and report: https://console.apify.com/view/runs/…

Any other URL (Zapier, Make, n8n or your own server) receives the same text plus the run summary as JSON. Choose After every run to get a message even when nothing changed.

How much does it cost?

Apify plan	Per answer checked	Report
Free and Bronze	$0.05	$0.50 per run
Silver	$0.045	$0.50 per run
Gold and above	$0.04	$0.50 per run

One answer is one prompt on one engine, so 20 prompts on 3 engines is 60 answers: $3, plus $0.50 for the report. Run weekly, that's about $14 a month per brand.

You're not charged when an answer couldn't be checked. That includes Gemini at its rate limit, a blocked search, or a run that hits its timeout. A prompt where Google shows no AI Overview is a checked answer, because "no overview" is itself a result. Switch off the report to skip its $0.50.

How the engines are asked

• Google AI Overviews: a Google search for the prompt in your country. AI Overviews that Google builds after the page loads are read in a real browser on residential IPs.
• Gemini: Gemini 2.5 Flash with Grounding with Google Search, the same grounding Google's own apps use.
• Claude: Claude Haiku 4.5 with Anthropic's web search tool, localised to your country.

AI answers vary between runs, users and locations. Treat one run as a sample and watch the trend over several weekly runs. Questions with a clear buying intent ("best X for Y", "X vs Y", "alternatives to X") show the most brand recommendations.

Use it with AI agents (MCP)

Add https://mcp.apify.com?tools=automationnation/ai-visibility-tracker to Claude, ChatGPT, Cursor or another MCP client and sign in with Apify. Then ask, for example: "Is our brand mentioned when people ask AI for the best CRM for small businesses? Compare us with HubSpot and Pipedrive."

Integrations and API

curl -X POST "https://api.apify.com/v2/acts/automationnation~ai-visibility-tracker/run-sync-get-dataset-items?token=YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"brand":"Notion","domain":"notion.so","prompts":["best note-taking app for teams"],"competitors":["Obsidian (obsidian.md)"]}'

Python and JavaScript: the apify-client package with Actor ID automationnation/ai-visibility-tracker. Send results to Google Sheets, Slack, email or a webhook through Apify integrations, or schedule the Actor weekly in Apify Console.

FAQ

Does it check ChatGPT and Perplexity? Not yet. They're planned. Today it checks Google AI Overviews, Gemini and Claude.

How is a mention detected? A whole-word match of your brand name and its other names. A name with capitals matches only with those capitals, so "Notion" isn't counted in "the notion of". Add product names as Other names for your brand. For competitors, add other names after " / ", for example Microsoft OneNote / OneNote; names like "Microsoft OneNote" also match "OneNote" automatically.

What does "position" mean? Your order among the brands you track, by first mention in the answer. #1 means you're named before every tracked competitor.

Is there a limit on Apify's free plan? Free-plan runs check up to 15 answers each, for example 5 prompts on 3 engines, so you can try the tracker. Paid Apify plans have no limit.

Can I keep separate histories for different clients? Yes. Runs with the same brand, domain and country are compared with each other. Set a Tracker name to keep a separate history per client or campaign.

Why is an answer missing from a run? It's listed under "Not checked" in the report and in OUTPUT with the reason, and it isn't charged. Usually an engine was busy or Google blocked every retry.

More from AutomationNation

• Google AI Overview Tracker: whether Google's AI Overviews cite your site, keyword by keyword, at scale.
• Google Trends Scraper & API: interest over time, by region and city, rising queries and Trending now.
• App Store Reviews Scraper and Google Play Reviews Scraper: app reviews with developer replies, for any app and country.

Questions or a missing feature? Open an issue on the Actor's Issues tab. Fixes usually ship within a day.