Brand AI Answers Tracker: check your brand visibility in ChatGPT

Does ChatGPT recommend your brand, or your competitor's? Ask it your customers' questions and get the full, dated answer, the sources it cited, and your rank against up to 5 competitors. Counted by code. No AI judging. Pay only for answers you get.

• The full answer, not a score. Every row keeps the complete ChatGPT answer, the exact model name and the time it was fetched (UTC).
• The sources it cited. See which websites ChatGPT used, and whether your own site is one of them.
• Your rank, counted by code. Who is mentioned first: you or your competitors? Whole-word matching, case insensitive, with your aliases. No language model "grades" your brand, so no invented sentiment.
• No minimum, no subscription. One question is enough. Failed or empty answers are never charged.

What one check looks like (real output, 15 Oct 2026)

{
  "checkedAt": "2026-10-15T06:57:23.569Z",
  "engine": "chatgpt",
  "model": "gpt-6-luna",
  "question": "best CRM software for small business",
  "brandMentioned": true,
  "brandRank": 1,
  "brandMentionCount": 7,
  "brandCitedAsSource": true,
  "brandShareOfVoice": 0.5833,
  "competitors": [
    { "name": "Salesforce", "mentioned": false, "rank": null },
    { "name": "Zoho", "mentioned": true, "mentionCount": 5, "rank": 2, "citedAsSource": true }
  ],
  "sources": [
    { "url": "https://www.hubspot.com/pricing/crm?tier=starter", "domain": "hubspot.com", "position": 1 },
    { "url": "https://www.pipedrive.com/en/pricing/professional-crm", "domain": "pipedrive.com", "position": 2 },
    { "url": "https://www.zoho.com/crm/zohocrm-pricing-calculator.html", "domain": "zoho.com", "position": 3 }
  ],
  "answerText": "**Best all-around for many small businesses: HubSpot** ... (full answer)"
}

Pricing

You pay per successful check: one question, one ChatGPT answer, fully analyzed. The exact price per check is shown on the Pricing tab of this page. 10 questions with 1 answer each = 10 checks. Empty or failed answers are free. Set a maximum cost per run in Apify and the Actor stops before going over it.

---

Who is it for?

• Marketing managers who want to know if AI assistants recommend their product.
• SEO and GEO specialists tracking "AI visibility" next to Google rankings.
• Agencies reporting AI share of voice to clients every week.
• Founders checking how ChatGPT compares them with bigger competitors.

How to use it in 5 steps

1. Enter your brand name (plus aliases and your website domain).
2. Add up to 5 competitors.
3. Write the questions your customers ask (for example "best CRM software for small business").
4. Click Start. The example input finishes in under a minute.
5. Read the Overview table, then the Run summary (presence rate, average rank, share of voice, most cited domains).

Input

Field	What it does	Default
brandName	Brand to track (whole word, case insensitive)	HubSpot
brandAliases	Other spellings that count as your brand	empty
brandDomain	Your domain, to detect when your site is cited	hubspot.com
competitors	Up to 5 competitor names	Salesforce, Zoho
questions	1 to 50 questions	2 examples
samplesPerQuestion	Ask each question 1 to 3 times (answers vary)	1
country	Approximate location sent to the web search	US
includeFullAnswer	Keep full answer text and all consulted URLs	true

Output: what each row contains

One row per question and answer.

Field	Meaning
checkedAt	When the answer was fetched (ISO 8601, UTC)
engine, model, searchMode	chatgpt, exact model name from the API, api_with_web_search
question, sampleIndex	The question and which repetition it is
status	ok, empty or error (only ok is charged)
brandMentioned, brandMentionCount	Is your brand in the answer, and how many times
brandRank	Order of first appearance among your brand and competitors (1 = first, null = absent)
brandFirstMentionChar	Character position of the first mention
brandCitedAsSource	Your domain (or a subdomain) is among the cited sources
brandInConsultedSources	Your domain is among all pages the search consulted
brandShareOfVoice	Your mentions divided by all tracked mentions in this answer
competitors	Same counts for each competitor
sources	Cited sources: url, title, domain, position
searchQueries	The web searches ChatGPT ran to answer
answerText	The complete answer (if includeFullAnswer)
note	Reminder that this is the official API with web search

The Run summary (key-value store record SUMMARY) adds, per engine: brand presence rate, average rank, cited-as-source rate, share of voice for every tracked name, competitor presence rates and the 10 most cited domains.

Honest limits

• This is the official OpenAI API with web search enabled, not the chatgpt.com interface. Answers can differ from what a person sees in the ChatGPT app, which also uses memory, personalization and other settings.
• AI answers vary from one run to the next. Use 3 answers per question to measure a rate instead of trusting one answer.
• Rank is among the names you track, not among every brand in the answer.
• A competitor counts as "cited as source" when a cited domain label equals its name (for example zoho.com for "Zoho").
• Not affiliated with OpenAI. ChatGPT is a trademark of OpenAI.

Schedule it every week

Use Apify Schedules to run the same input every Monday and build a history. Send results to Google Sheets, Slack, Make, Zapier or n8n with Apify integrations, or call the Actor from an AI agent through the Apify MCP server (turn off includeFullAnswer for a compact output).

FAQ

How do I check if ChatGPT mentions my brand?

Run this Actor with your brand name and the questions your customers ask. Each row tells you if your brand is mentioned, how many times, in which position compared with your competitors, and whether your website is cited as a source.

What is AI share of voice?

It is the share of mentions your brand gets compared with your competitors in AI answers. This Actor computes it per answer (brandShareOfVoice) and for the whole run (shareOfVoice in the summary), by counting names in the answer text.

How is this different from an AI visibility score?

A score is a number someone computed for you. This Actor stores the full answer, the date, the model and the cited sources, so you can check every number yourself.

Why is there no sentiment or tone score?

Because a tone score needs another AI to judge the answer, and that judgment can be wrong. Everything here is counted by code, so the same answer always gives the same numbers.

Does it track Perplexity, Gemini or Google AI Overviews?

Not yet. This version tracks ChatGPT through the official OpenAI API with web search. Other engines are planned.

Do I need an OpenAI API key?

No. The Actor uses its own access. You only pay the price per check shown on the Pricing tab.

What happens if an answer is empty or fails?

The row is saved with status set to empty or error and an errorMessage, and it is not charged.

Which country are the answers for?

The country you choose is sent to the web search as the approximate user location, which changes which pages the search finds.

Is it legal?

It uses the official OpenAI API under OpenAI's terms. It does not scrape chatgpt.com or any website, and it does not collect personal data: the input is brand names and questions.

Support

Found a bug or need another engine? Open an issue on the Issues tab. We answer every question within 6 hours.