# AI Visibility Tracker (GEO): ChatGPT, Gemini, Perplexity, Grok (`trueline-data/ai-search-visibility`) Actor

Ask ChatGPT, Perplexity, Gemini, Claude and Grok, with live web search, the questions your buyers ask. See if your brand is named, its place in the list, the competitors named with it, how it is described, and the sites the AI cited.

- **URL**: https://apify.com/trueline-data/ai-search-visibility.md
- **Developed by:** [Trueline Data](https://apify.com/trueline-data) (community)
- **Categories:** AI, SEO tools
- **Stats:** 3 total users, 2 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

$80.00 / 1,000 ai answers

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 Visibility Tracker (GEO): ChatGPT, Gemini, Perplexity, Grok

When buyers ask an AI "what is the best \_\_\_?", does it name you? This tool asks ChatGPT, Perplexity,
Gemini, Claude and Grok your buyers' real questions, with live web search on, and tells you:

- **Are you named?** Yes or no, for every question and every AI.
- **Where in the list?** Your number in the AI's list (1st, 2nd, 3rd…).
- **Who is named with you?** Your competitors, and the order everyone was named in.
- **How are you described?** Positive, neutral or negative, with a short reason, plus the sentence
  the AI wrote about you.
- **Which websites did the AI use?** Every cited link and domain, and whether your own site was one
  of them. These are the pages to get your brand onto.
- **A summary per AI:** how often you are named, your average place, and share of voice against
  each competitor.

### Why this one

- **Five AI engines in one run**, each with live web search, so you see what they say today.
- **Ask more than once.** AI answers change between asks. Set `runsPerPrompt` to 3 and you see how
  often you are named, not one lucky answer.
- **You pay only for answers you get.** A failed answer is listed with its reason and not charged.
  The summary is free.

### Input

| Field | What it does |
| --- | --- |
| `prompts` | The questions your buyers ask, one per line. |
| `brand` | Your brand name. |
| `brandAliases` | Other spellings that also count. |
| `brandDomains` | Your websites, to see when the AI cites you. |
| `competitors` | Names to track next to yours. |
| `engines` | Any of `chatgpt`, `perplexity`, `gemini`, `claude`, `grok`. Default: the first three. |
| `runsPerPrompt` | 1 to 5 asks per question per AI. |
| `analyzeSentiment` | Judge the tone about your brand (default on). |

```json
{
  "prompts": ["What are the best field service software tools for a small plumbing company?"],
  "brand": "Housecall Pro",
  "brandDomains": ["housecallpro.com"],
  "competitors": ["Jobber", "ServiceTitan", "Workiz"],
  "engines": ["chatgpt", "perplexity", "gemini"]
}
```

### Output

One row per answer, then one `summary` row (also saved as `SUMMARY` in the run's key-value store).

Real rows from a test run on 17 October 2026 (some fields left out to keep it short):

```json
[
  {
    "type": "answer",
    "prompt": "Best scheduling app for HVAC contractors",
    "engine": "chatgpt",
    "status": "ok",
    "brandMentioned": true,
    "brandListPosition": 1,
    "brandRank": 1,
    "brandCited": true,
    "brandContext": "For most HVAC contractors, the best scheduling app is usually Housecall Pro or Jobber if you want a simple, reliable all-in-one tool for scheduling,",
    "mentionOrder": [
      "Housecall Pro",
      "Jobber"
    ],
    "citedDomains": [
      "capterra.com",
      "housecallpro.com"
    ],
    "sentiment": "positive",
    "sentimentReason": "Housecall Pro is recommended as the best scheduling app for most HVAC contractors."
  },
  {
    "type": "summary",
    "brand": "Housecall Pro",
    "overall": {
      "answers": 10,
      "brandVisibilityRate": 0.9,
      "brandCitedRate": 0.1,
      "avgListPosition": 1.75,
      "shareOfVoice": {
        "Jobber": 0.256,
        "Housecall Pro": 0.231,
        "ServiceTitan": 0.205,
        "FieldEdge": 0.205,
        "Workiz": 0.103
      },
      "sentiment": {
        "positive": 9
      }
    }
  }
]
```

### Pricing

Pay per AI answer returned. The summary row is free.

### How it works

Each AI is called through its official model with web search turned on. Answers come from the same
model families the assistants use; the consumer apps can add their own extras on top, so treat each
answer as what that AI says with a fresh search, not a copy of one person's chat window.

# Actor input Schema

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

One question per line, written the way a buyer would type it into ChatGPT.

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

The name to look for in the answers.

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

Spellings that also count, like HousecallPro or HCP.

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

Domains like housecallpro.com. Used to tell you when the AI cites your own site as a source.

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

Names to track next to yours: who is named, in what order, and share of voice.

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

Which assistants to ask. Each uses live web search.

## `runsPerPrompt` (type: `integer`):

AI answers change from one ask to the next. Asking 3 times shows how often you are named, not just once.

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

Positive, neutral or negative, with a short reason. Only for answers that name you.

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

Keep the full text of every AI answer in the results. Turn off for smaller results.

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

How many answers to get at the same time. 5 is fine for most runs.

## Actor input object example

```json
{
  "prompts": [
    "What are the best field service software tools for a small plumbing company?",
    "Best scheduling app for HVAC contractors"
  ],
  "brand": "Housecall Pro",
  "brandDomains": [
    "housecallpro.com"
  ],
  "competitors": [
    "Jobber",
    "ServiceTitan",
    "Workiz"
  ],
  "engines": [
    "chatgpt",
    "perplexity",
    "gemini"
  ],
  "runsPerPrompt": 1,
  "analyzeSentiment": true,
  "includeAnswerText": true,
  "maxConcurrency": 5
}
```

# Actor output Schema

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

No description

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

No description

# 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 = {
    "prompts": [
        "What are the best field service software tools for a small plumbing company?",
        "Best scheduling app for HVAC contractors"
    ],
    "brand": "Housecall Pro",
    "brandDomains": [
        "housecallpro.com"
    ],
    "competitors": [
        "Jobber",
        "ServiceTitan",
        "Workiz"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("trueline-data/ai-search-visibility").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 = {
    "prompts": [
        "What are the best field service software tools for a small plumbing company?",
        "Best scheduling app for HVAC contractors",
    ],
    "brand": "Housecall Pro",
    "brandDomains": ["housecallpro.com"],
    "competitors": [
        "Jobber",
        "ServiceTitan",
        "Workiz",
    ],
}

# Run the Actor and wait for it to finish
run = client.actor("trueline-data/ai-search-visibility").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 '{
  "prompts": [
    "What are the best field service software tools for a small plumbing company?",
    "Best scheduling app for HVAC contractors"
  ],
  "brand": "Housecall Pro",
  "brandDomains": [
    "housecallpro.com"
  ],
  "competitors": [
    "Jobber",
    "ServiceTitan",
    "Workiz"
  ]
}' |
apify call trueline-data/ai-search-visibility --silent --output-dataset

```

## MCP server setup

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

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/G2ivPquxHFdKStz1m/builds/zM293Cih9mMGpiFjP/openapi.json