# AI Brand Visibility Tracker (ChatGPT, Perplexity, Claude) (`devotee/ai-brand-visibility-tracker`) Actor

Ask ChatGPT, Perplexity and Claude the questions your customers ask, and measure whether your brand is mentioned, how high it ranks against competitors, and whether your site is cited.

- **URL**: https://apify.com/devotee/ai-brand-visibility-tracker.md
- **Developed by:** [Thomas Peckham](https://apify.com/devotee) (community)
- **Categories:** AI, SEO tools, Marketing
- **Stats:** 3 total users, 2 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $50.00 / 1,000 chatgpt checks

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## AI Brand Visibility Tracker

Find out whether **ChatGPT, Perplexity and Claude** recommend your brand when customers ask them for advice — and whether they cite your website.

Give the Actor your brand, your competitors, and the questions your customers ask. It sends each question to each AI assistant with live web search turned on, then measures:

- **Mentioned** — does the answer name your brand (or any of its aliases)?
- **Position** — in what order were you mentioned relative to the competitors you track? (1 = first)
- **Cited** — does the answer link to your website?
- **Share of voice** — your share of all brand mentions across the run, per engine and overall.

### Example use cases

- Track "generative engine optimization" (GEO) progress month over month.
- See which competitors AI assistants recommend instead of you, and which pages they cite.
- Compare engines: you may be visible in Perplexity and absent from ChatGPT.
- Schedule weekly runs and alert on drops.

### Input

| Field | What to enter |
|---|---|
| Brand name | e.g. `Acme` |
| Brand aliases | Other names: product names, abbreviations |
| Brand domains | Your sites, e.g. `acme.com` (subdomains count too) |
| Competitors | One per line, optionally with aliases and domains: `Globex \| Globex Corp \| globex.io` |
| Prompts | Up to 50 questions your customers ask, e.g. "What's the best invoicing tool for freelancers?" |
| AI engines | Any of ChatGPT, Perplexity, Claude |
| Country | Optional two-letter code to localize search (ChatGPT, Claude) |

Prompts are sent exactly as written. Leave your brand out of them to measure organic visibility.

### Output

One dataset row per prompt per engine:

```json
{
  "prompt": "What's the best invoicing tool for freelancers?",
  "engine": "perplexity",
  "model": "perplexity/sonar",
  "brand": { "name": "Acme", "mentioned": true, "mentionCount": 2, "position": 2, "cited": true, "citedUrls": ["https://acme.com/pricing"] },
  "competitors": [{ "name": "Globex", "mentioned": true, "mentionCount": 1, "position": 1, "cited": false, "citedUrls": [] }],
  "citations": [{ "url": "https://acme.com/pricing", "title": "Pricing", "domain": "acme.com", "entity": "Acme" }],
  "searchQueries": ["best invoicing tool freelancers"],
  "answer": "…full answer text…",
  "usedOwnApiKey": false,
  "checkedAt": "2026-10-17T12:00:00.000Z",
  "error": null
}
```

A run summary (mention rate, citation rate, average position and share of voice per brand, overall and per engine) is saved to the key-value store as `OUTPUT`.

### Pricing

Pay per check (one prompt answered by one engine). Failed checks are not charged. Set a maximum charge per run to cap spending; the Actor stops before starting checks your limit can't cover.

**Use your own API keys** (optional, in the input) to pay a much lower per-check price; the AI provider then bills you directly for its usage.

### How it works and its limits

- Answers come from each provider's **official API** with web search enabled. API answers are close to, but not always identical to, what people see in the consumer apps, which can personalize results.
- AI answers vary from run to run. For trends, use several prompts and compare runs over time rather than relying on a single answer.
- Mention matching is whole-word and case-insensitive; add aliases for alternative spellings.

### Data sources and terms

This Actor only calls official, documented APIs, within their terms:

| Engine | API |
|---|---|
| ChatGPT | OpenAI Responses API with the `web_search` tool |
| Perplexity | Perplexity Agent API with the `web_search` tool |
| Claude | Anthropic Messages API with the web search tool |

It does not scrape any website, log in anywhere, or collect personal data.

# Actor input Schema

## `brand` (type: `string`):

The brand to look for in AI answers.

## `brandAliases` (type: `array`):

Other names the brand goes by (product names, abbreviations). Matching is case-insensitive and whole-word.

## `brandDomains` (type: `array`):

Your websites. A citation pointing to one of these (or a subdomain) counts as the brand being cited.

## `competitors` (type: `array`):

One per line. Optionally add aliases and domains separated by |, e.g. "Confluence | Atlassian Confluence | atlassian.com".

## `prompts` (type: `array`):

Questions your customers might ask an AI assistant (up to 50 per run). Each prompt is sent unchanged to every selected engine, with web search on. Don't name your brand in the prompt unless you want to test branded queries.

## `engines` (type: `array`):

Which assistants to ask. Each prompt × engine is one billed check.

## `country` (type: `string`):

Optional two-letter country code (e.g. US, GB, DE) to localize web search where the engine supports it (ChatGPT, Claude).

## `includeAnswerText` (type: `boolean`):

Store each engine's full answer in the dataset.

## `models` (type: `object`):

Advanced, own API keys only: override the model per engine, e.g. {"chatgpt": "gpt-5.5"}. Ignored for engines that use the built-in keys.

## `maxConcurrency` (type: `integer`):

How many checks run at the same time.

## `openaiApiKey` (type: `string`):

Use your own key: ChatGPT checks then bill at the lower own-key price and API usage goes to your OpenAI account.

## `perplexityApiKey` (type: `string`):

Use your own Perplexity key.

## `anthropicApiKey` (type: `string`):

Use your own Anthropic key.

## Actor input object example

```json
{
  "brand": "Notion",
  "brandDomains": [
    "notion.so",
    "notion.com"
  ],
  "competitors": [
    "Confluence | atlassian.com",
    "Coda | coda.io",
    "Obsidian | obsidian.md"
  ],
  "prompts": [
    "What is the best note-taking app for small teams?"
  ],
  "engines": [
    "perplexity"
  ],
  "includeAnswerText": true,
  "maxConcurrency": 4
}
```

# Actor output Schema

## `results` (type: `string`):

One row per prompt per engine: mentions, position, citations and the answer text.

## `summary` (type: `string`):

Mention rate, citation rate, average position and share of voice per brand, overall and per engine.

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "brand": "Notion",
    "brandDomains": [
        "notion.so",
        "notion.com"
    ],
    "competitors": [
        "Confluence | atlassian.com",
        "Coda | coda.io",
        "Obsidian | obsidian.md"
    ],
    "prompts": [
        "What is the best note-taking app for small teams?"
    ],
    "engines": [
        "perplexity"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("devotee/ai-brand-visibility-tracker").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {
    "brand": "Notion",
    "brandDomains": [
        "notion.so",
        "notion.com",
    ],
    "competitors": [
        "Confluence | atlassian.com",
        "Coda | coda.io",
        "Obsidian | obsidian.md",
    ],
    "prompts": ["What is the best note-taking app for small teams?"],
    "engines": ["perplexity"],
}

# Run the Actor and wait for it to finish
run = client.actor("devotee/ai-brand-visibility-tracker").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "brand": "Notion",
  "brandDomains": [
    "notion.so",
    "notion.com"
  ],
  "competitors": [
    "Confluence | atlassian.com",
    "Coda | coda.io",
    "Obsidian | obsidian.md"
  ],
  "prompts": [
    "What is the best note-taking app for small teams?"
  ],
  "engines": [
    "perplexity"
  ]
}' |
apify call devotee/ai-brand-visibility-tracker --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,devotee/ai-brand-visibility-tracker"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/mJtVrz8hj8BgzrLfU/builds/1zfLFUaVcNL1sXoHL/openapi.json