AI Search Visibility Tracker: ChatGPT & Gemini Brand Mentions (LLM SEO, GEO, AEO)

Find out whether ChatGPT and Gemini mention and recommend your brand, how you rank against competitors, and which websites AI cites when it answers your buyers' questions. It's an AI visibility and LLM SEO tool for generative engine optimization (GEO) and answer engine optimization (AEO). One run gives you a share-of-voice report. Schedule it weekly to track AI brand mentions over time.

More buyers now ask AI assistants instead of Google. If ChatGPT names three competitors and not you, that's a lost lead you never see in your analytics. This Actor measures it.

Try it: the prefilled Notion example (2 buyer prompts × 2 engines × 1 sample = 4 answers) costs $0.16.

What you get

• Visibility rate: % of AI answers that mention your brand.
• Share of voice: your mentions vs your competitors'.
• Rank: where you appear in the answer (1 = named first), among tracked brands and among all brands the AI names.
• Sentiment: positive / neutral / negative / mixed, plus a one-line summary of how the AI describes you.
• Citations: which domains ChatGPT cites, and whether your own site is one of them.
• Gap prompts: questions where competitors are mentioned and you are not. These are your content priorities.
• Discovered competitors: brands the AI recommends that you didn't list.
• Trend tracking: give runs a tracking name and the report shows the change since the last run.
• HTML report ready to share with your team or client, plus every answer as a dataset row (JSON, CSV, Excel).

How to use it

1. Enter your brand, optionally with your website: Notion | notion.com | notion.so.
2. Add competitors, one per line: Confluence | atlassian.com.
3. Add the questions your buyers ask (without your brand name), or just describe your category and the Actor writes the questions for you.
4. Run. Open the REPORT in the key-value store, or download the dataset.

To track over time, set Tracking name (e.g. notion-weekly) and add an Apify schedule.

Example input

{
  "brand": "Notion | notion.com | notion.so",
  "competitors": ["Confluence | atlassian.com", "Coda | coda.io", "ClickUp | clickup.com"],
  "category": "team wiki and documentation software",
  "autoPromptCount": 10,
  "engines": ["chatgpt-search", "gemini-knowledge"],
  "samplesPerPrompt": 2,
  "trackingName": "notion-weekly"
}

Example output (one dataset row per answer)

{
  "prompt": "What is the best wiki and docs tool for a remote startup team?",
  "engine": "chatgpt-search",
  "brandMentioned": true,
  "brandRank": 2,
  "brandRankAmongAllBrands": 2,
  "brandSentiment": "positive",
  "brandDescription": "Flexible all-in-one workspace, praised for ease of use",
  "brandCited": false,
  "mentionedInOrder": ["Confluence", "Notion", "Coda"],
  "otherBrands": ["Slab", "Slite"],
  "citedDomains": ["g2.com", "zapier.com", "atlassian.com"],
  "answer": "…full answer text…"
}

The run also saves SUMMARY (JSON with all metrics, per engine and per prompt) and REPORT (HTML) to the key-value store.

Engines

Engine	What it measures
ChatGPT with web search	Answers from OpenAI's API with live web search, the closest equivalent of what ChatGPT says when it searches. Includes the sources it cites.
ChatGPT model knowledge	What OpenAI's model says without searching: how it perceives your brand from training data.
Gemini model knowledge	The same for Google's Gemini.

Answers come from the official APIs, so runs are reliable and never blocked. API answers closely track the consumer apps but are not identical, because the apps add personalization, memory and their own system prompts. Treat results as a consistent benchmark you can compare over time and against competitors.

Pricing

You pay per AI answer analyzed. Sentiment, brand extraction, prompt generation and the report are included. Failed answers are not charged.

Run	Answers	Cost at $0.04 per answer
10 prompts × 1 engine	10	$0.40
10 prompts × 2 engines	20	$0.80
25 prompts × 2 engines × 2 samples	100	$4.00
Weekly tracking of the above for a month	400	$16.00

Set a spending limit on the run and the Actor stops before exceeding it.

Tips

• Write prompts like a buyer: "best X for Y", "alternatives to [category]", "which X is cheapest for…". Don't put your brand in the prompt.
• Use 2–3 samples per prompt. AI answers vary between runs; more samples give steadier numbers.
• List every domain you use in the brand field (e.g. Notion | notion.com | notion.so) so the Actor can tell when AI cites your site.
• Names that are common words (Monday, Notion, Linear) can match ordinary text. Add the domain as an alias: Monday | monday.com.

FAQ

Why doesn't this match what I see in ChatGPT? ChatGPT personalizes answers and changes them between sessions. This Actor asks the same way every time, which makes it a fair benchmark for trends and competitor comparison.

Which models are used? A current OpenAI model with web search, and a current Gemini model. You can override both in the Advanced section.

Why no Gemini web search? Google's terms for Gemini answers grounded in Google Search restrict storing and analyzing them, so this Actor uses Gemini's model knowledge only.

Can I call it from code, Make, Zapier or n8n? Yes, like any Apify Actor: via the API, the official integrations, or as an MCP tool for AI agents.

Is my data shared? Your brand, competitors and prompts are sent to the AI providers' APIs to generate answers, and stored in your own Apify storage.

Use it from AI agents (MCP)

This Actor works with the Apify MCP server. Ask your agent, for example: "Check how often ChatGPT and Gemini recommend Notion vs Confluence for team-wiki questions." The agent can find this Actor, read its input schema and run it, with a spending cap set through maxTotalChargeUsd.

FAQ

What does a run cost? You pay per AI answer analyzed. A quick 2-prompt × 2-engine check is 4 answers. Set a spending limit on the run and the Actor stops at it.

Why do results change between runs? AI answers vary. Set Samples per prompt to 2–3 for more stable numbers, and use a Tracking name to follow trends.

Is this GEO / AEO (generative engine optimization)? Yes. Use the gap prompts and cited domains to decide which content to create and where to get mentioned.

Something broke? Open an issue on the Issues tab. We monitor it daily.

FAQ

How do I track brand mentions in ChatGPT? Enter your brand, your competitors and the questions buyers ask. The Actor asks ChatGPT (with web search and from model knowledge) and Gemini, then measures whether, where and how you're mentioned.

Which AI engines are supported? ChatGPT with web search, ChatGPT model knowledge and Gemini model knowledge, through the official APIs. Perplexity, Claude and Google AI Overviews are not included.

Do I need my own OpenAI or Gemini API key? No. API costs are included in the per-answer price.

How much does it cost? $0.04 per AI answer analyzed. Failed answers are free.

Code examples

Python and Node.js scripts for running this tracker through the API are on GitHub: https://github.com/kendallcoding202/google-ads-transparency-api-examples.

Related

• Google Ads Transparency Center Scraper: see every Google ad your competitors run.