# AI Brand Visibility Tracker: ChatGPT, Perplexity, Gemini (`craplarp/ai-brand-visibility-tracker`) Actor

Track how often ChatGPT, Perplexity, Gemini, Claude and Grok mention and cite your brand vs competitors. Share of voice, rank, citations, sentiment, gaps and week-over-week changes. No API keys needed.

- **URL**: https://apify.com/craplarp/ai-brand-visibility-tracker.md
- **Developed by:** [Jahongir](https://apify.com/craplarp) (community)
- **Security:** Limited permissions
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $50.00 / 1,000 ai 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 — ChatGPT, Perplexity, Gemini, Claude & Grok

**Does AI recommend your brand — or your competitors?** More and more buyers ask ChatGPT, Perplexity, Gemini or Claude for recommendations instead of searching Google. This Actor asks those AI assistants the questions your customers ask and measures how often they **mention**, **rank** and **cite** your brand compared with competitors. It also tracks how that changes week by week.

✅ **No API keys needed** · ✅ Each AI uses its **own built-in web search** · ✅ **$0.05 per AI answer**, pay only for what you use

### What you get

| Metric | Meaning |
|---|---|
| **Mention rate** | % of AI answers that mention your brand |
| **Share of voice** | Your share of all brand mentions vs tracked competitors |
| **Average position** | Where you appear in the AI's list (1 = first brand named) |
| **Citation rate** | % of answers that link to **your website** as a source |
| **By engine** | All of the above separately for ChatGPT, Perplexity, Gemini, Claude, Grok |
| **Gaps** | Questions where competitors are recommended and you are not. Your GEO to-do list |
| **Sentiment** | How each AI describes you: positive / neutral / negative, with a one-line reason |
| **Top cited sources** | Which websites AIs trust in your category. Get featured there |
| **Change since last run** | Week-over-week movement when you run it on a schedule |

Plus a **visual HTML report** you can send to your boss or client, and every raw AI answer.

### Why it's more accurate than one-off checks

AI answers are **random**: ask ChatGPT the same question twice and you can get different brands. Set **Samples per prompt** to 3–5 and the tracker asks each question several times, so you get a real *probability* of being mentioned instead of a coin flip.

### How to use

1. Enter **your brand**, its domains, and **3–10 competitors** (`Asana, asana.com`, one per line).
2. Add the **questions your buyers ask**, e.g. *"best project management tool for small teams"*. Don't include your brand name. Or describe your **category** and let the Actor generate realistic questions.
3. Pick the **AI engines** and run.
4. Open the **Visual report** in the Output tab.
5. **Schedule it weekly** (Schedules → Create) to track trends. The *Change since previous run* section fills in automatically.

### Pricing (pay per event)

| Event | Price |
|---|---|
| AI check (one answer from one engine) | **$0.05** |
| AI check with your own OpenRouter key | $0.005 |
| Visibility report (once per run) | $0.05 |

**Example:** 10 prompts × 4 engines × 1 sample = 40 checks + report = **$2.05 per run**, about **$8.20/month** if you run it weekly. Sentiment analysis and prompt generation are free.

Set **Max cost per run** and the Actor never spends past it. It checks your budget *before* each AI call.

### Example answer record

```json
{
  "type": "answer",
  "engineName": "Perplexity",
  "prompt": "What is the best tool for team documentation?",
  "brandMentioned": true,
  "brandPosition": 2,
  "brandCited": true,
  "brandsMentionedInOrder": ["Confluence", "Notion", "Coda"],
  "competitorsMentioned": ["Confluence", "Coda"],
  "citations": [{ "url": "https://www.notion.so/product/wikis", "domain": "notion.so", "brand": "Notion" }],
  "sentiment": "positive",
  "sentimentReason": "Recommended as the most flexible option for growing teams.",
  "answer": "…full AI answer…"
}
```

The last dataset item (`type: "summary"`) holds the aggregated metrics, also saved as `OUTPUT` in the key-value store.

### Notes & limitations

- Answers come from each vendor's **API with native web search** (via OpenRouter), using current fast models by default (override in *Model overrides*). The consumer apps (chatgpt.com etc.) may personalise answers for logged-in users, so treat results as a strong, consistent signal rather than a pixel-perfect copy.
- Brand detection is exact-match on your brand name and aliases, so add common spellings as aliases.
- Use **User country** and **Answer language** to measure visibility in a specific market.

### FAQ

**Is this GEO / AEO / LLM SEO?** Yes. It's the measurement part of Generative Engine Optimization: find out where you stand, fix the gaps, track the results.

**Can AI agents use it?** Yes. It works through Apify's MCP server, and every output field is documented.

**Need another engine or metric?** Open an issue on the Issues tab. Fixes usually ship within 48 hours.

# Actor input Schema

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

The brand to track, exactly as people write it (e.g. Notion).

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

Other spellings or product names that count as a mention (e.g. Notion AI, notion.so).

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

Your website domains. A citation (source link) to these counts as 'cited' (e.g. notion.so, notion.com).

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

One competitor per line. Optionally add aliases and domains after commas: 'Asana, asana.com' or 'Microsoft Loop, Loop, loop.cloud.microsoft'.

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

Questions your buyers ask AI assistants. Don't name your brand — measure whether the AI brings it up by itself.

## `category` (type: `string`):

Describe what you sell (e.g. 'project management software for small teams'). Used to generate extra buyer questions automatically.

## `autoGeneratePrompts` (type: `integer`):

Number of additional realistic buyer questions to generate from the category (0 = off). Generation is free; each generated prompt is checked like the others.

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

Which AI assistants to ask. Each uses its own built-in web search.

## `samplesPerPrompt` (type: `integer`):

AI answers vary between runs. Asking the same question several times gives a reliable mention probability instead of a coin flip. Each sample is one check.

## `userLocation` (type: `string`):

Optional. Ask as a user from this country (e.g. Poland, United States) — affects which brands and sources AIs prefer.

## `answerLanguage` (type: `string`):

Optional. Ask the AIs to answer in this language (e.g. German). Leave empty to use the prompt's language.

## `analyzeSentiment` (type: `boolean`):

For answers that mention your brand, classify how it is described (positive / neutral / negative) with a one-line reason. Free.

## `compareWithPreviousRun` (type: `boolean`):

Remember results and show changes since the last run with the same brand, prompts and engines. Ideal with a weekly schedule.

## `openrouterApiKey` (type: `string`):

Optional. Bring your own OpenRouter key and pay the AI providers directly — checks are then charged at the much lower 'own key' price.

## `modelOverrides` (type: `object`):

Optional. Map engine to an OpenRouter model ID, e.g. {"chatgpt": "~openai/gpt-mini-latest"}. Defaults use each vendor's current fast model.

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

Parallel AI requests.

## Actor input object example

```json
{
  "brand": "Notion",
  "brandDomains": [
    "notion.so",
    "notion.com"
  ],
  "competitors": [
    "Asana, asana.com",
    "ClickUp, clickup.com",
    "Confluence, atlassian.com",
    "Coda, coda.io"
  ],
  "prompts": [
    "What is the best tool for team documentation and wikis?",
    "Best all-in-one workspace app for startups in 2026?"
  ],
  "autoGeneratePrompts": 0,
  "engines": [
    "chatgpt",
    "perplexity",
    "gemini",
    "claude"
  ],
  "samplesPerPrompt": 1,
  "analyzeSentiment": true,
  "compareWithPreviousRun": true,
  "maxConcurrency": 6
}
```

# Actor output Schema

## `report` (type: `string`):

HTML report: leaderboard, mention rate per AI engine, gaps, sentiment and top cited sources.

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

Aggregated metrics: mention rate, share of voice, citation rate, average position per brand and per engine, gaps and change since the previous run.

## `answers` (type: `string`):

Every AI answer with detected brands, position, citations and sentiment.

# 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": [
        "Asana, asana.com",
        "ClickUp, clickup.com",
        "Confluence, atlassian.com",
        "Coda, coda.io"
    ],
    "prompts": [
        "What is the best tool for team documentation and wikis?",
        "Best all-in-one workspace app for startups in 2026?"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("craplarp/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": [
        "Asana, asana.com",
        "ClickUp, clickup.com",
        "Confluence, atlassian.com",
        "Coda, coda.io",
    ],
    "prompts": [
        "What is the best tool for team documentation and wikis?",
        "Best all-in-one workspace app for startups in 2026?",
    ],
}

# Run the Actor and wait for it to finish
run = client.actor("craplarp/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": [
    "Asana, asana.com",
    "ClickUp, clickup.com",
    "Confluence, atlassian.com",
    "Coda, coda.io"
  ],
  "prompts": [
    "What is the best tool for team documentation and wikis?",
    "Best all-in-one workspace app for startups in 2026?"
  ]
}' |
apify call craplarp/ai-brand-visibility-tracker --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,craplarp/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/nPHcmOFz8g2S1bpnY/builds/Kz5TcN1fD7kQWgifO/openapi.json