# AI Search Visibility Tracker – ChatGPT & Google AI Mode (`rowfeed/ai-search-visibility-tracker`) Actor

Ask ChatGPT and Google AI Mode your customers' questions and see if your brand is mentioned, in which position versus competitors, and which sources are cited. Full answer, brands and sources per prompt. Pay per answer.

- **URL**: https://apify.com/rowfeed/ai-search-visibility-tracker.md
- **Developed by:** [Rowfeed](https://apify.com/rowfeed) (community)
- **Categories:** SEO tools, AI, Marketing
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $30.00 / 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 Search Visibility Tracker – ChatGPT & Google AI Mode

Ask ChatGPT and Google AI Mode the questions your customers ask, and see whether your brand shows up: mentioned or not, in which position versus your competitors, and which websites the AI cites as sources.
Schedule it daily or weekly to track your AI search visibility (GEO / AEO) over time, compare against competitors and find the pages that AI assistants trust.
Built for SEO and marketing teams, agencies reporting AI visibility to clients, founders and AI agents.

### What you get

For every prompt on every engine, one row with:

- **Your brand**: mentioned yes/no, position (1 = named first among your brand and competitors) and whether the answer links to your site.
- **Competitors**: which ones are named, each with position and citation.
- **Brands the AI highlighted** in the answer (ChatGPT).
- **Sources**: every cited website with domain, URL and title, so you see which pages to get featured on.
- **The full answer** as markdown, plus the web searches ChatGPT ran to write it.
- A link to ask the same question yourself.

Engines:

- **ChatGPT** – the answer a ChatGPT user sees, with web search, sources and brand highlights.
- **Google AI Mode** – Google's AI answer with its references.

### Example output row

A real ChatGPT answer (answer and sources shortened):

```json
{
  "prompt": "What is the best CRM for a small business? Recommend 5 options.",
  "engine": "chatgpt",
  "model": "gpt-6",
  "location": "United States",
  "language": "English",
  "brand": "HubSpot",
  "brand_mentioned": true,
  "brand_position": 1,
  "brand_cited": true,
  "competitors_mentioned": ["Pipedrive", "Salesforce", "Zoho CRM"],
  "tracked_brands": [
    {"brand": "HubSpot", "mentioned": true, "position": 1, "cited": true},
    {"brand": "Pipedrive", "mentioned": true, "position": 4, "cited": true},
    {"brand": "Salesforce", "mentioned": true, "position": 2, "cited": true},
    {"brand": "Zoho CRM", "mentioned": true, "position": 3, "cited": false}
  ],
  "brands_in_answer": ["HubSpot CRM", "Pipedrive", "Freshsales", "Less Annoying CRM"],
  "answer": "The best CRM for a small business is one that helps you manage contacts, track sales opportunities ... **My top recommendation for most small businesses is HubSpot CRM** ...",
  "answer_length": 9156,
  "sources_count": 10,
  "sources": [
    {"domain": "stacknpilot.com", "url": "https://www.stacknpilot.com/articles/best-crm-for-small-businesses-2026-7-top-picks-compared?utm_source=chatgpt.com", "title": "Best CRM for Small Businesses (2026): 7 Picks"}
  ],
  "search_queries": ["best CRM software for small business 2026 HubSpot Zoho Pipedrive Freshsales Salesforce pricing features"],
  "check_url": "https://chatgpt.com/?prompt=What%20is%20the%20best%20CRM%20for%20a%20small%20business%3F%20Recommend%205%20options.",
  "checked_at": "2026-10-16T18:01:05+00:00"
}
```

### Input

| Field | What it does |
|---|---|
| `prompts` | Questions your customers ask, up to 500. |
| `brand` | Your brand name or domain (`hubspot.com`). With a domain, a link to that site counts as cited. |
| `competitors` | Optional: up to 20 competitor names or domains. |
| `engines` | `chatgpt`, `google_ai_mode` or both. Default: ChatGPT. |
| `location` | Country the question is asked from, e.g. `United States`, `Germany`. |
| `language` | Language of the answer, e.g. `English`, `German`. |

### Pricing

Pay per event, no subscription:

- **$0.04 per AI answer** (one prompt on one engine). Launch price until 31 October 2026: $0.03.
- $0.001 per run start.

Examples at $0.04: 20 prompts on ChatGPT cost $0.80. 20 prompts on both engines cost $1.60. Tracking 10 prompts on ChatGPT every week costs about $1.75 a month.

You can cap the cost of a run with the maximum charge setting; the Actor only asks for the answers the budget covers.
Failed requests (provider errors, timeouts) are never charged. An answer is charged when the AI engine returned it, also in the rare case it contains no text (it then shows `answer_length: 0`, which counts as "not mentioned").
Live answers need a paid Apify plan (any plan); the pre-filled example works on the free plan.

### Track it every week

1. Fill in your prompts, brand and competitors, then click **Save as a new task**.
2. In the task, open **Schedules** and run it weekly (or daily).
3. Each run adds a dataset you can compare: share of prompts where your brand is mentioned, average position, and which sources the AI cites.

Tip: use 10–30 prompts that real customers ask, and keep them the same from week to week so the trend is meaningful.

### Good to know

- AI answers change from one ask to the next. For a stable picture, track the same prompts regularly and look at the trend, or ask important prompts more than once.
- Brand matching is by name (whole words, case-insensitive) and by domain. Use the spelling customers use, e.g. `Zoho CRM` or `monday.com`.
- `brand_position` is the order of first mention among your brand and the competitors you list.
- A run asks up to 5 questions at a time; each ChatGPT answer takes 20–60 seconds.
- Where the data comes from: the live answer ChatGPT gives a web user (with web search and sources) and Google's live AI Mode answer, collected through DataForSEO's licensed AI and SERP endpoints, so runs are not blocked.

### Related tools

- [Google Search Results API](https://apify.com/rowfeed/google-serp-api) – Google results with AI overview, People Also Ask and your domain's rank.
- [Competitor Keywords](https://apify.com/rowfeed/competitor-keywords) – every Google keyword a domain ranks for.
- [Keyword Search Volume](https://apify.com/rowfeed/keyword-search-volume) – monthly search volume, CPC and trend.

Not affiliated with OpenAI or Google.

# Actor input Schema

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

Questions your customers ask AI assistants, up to 500. Each prompt is asked on each engine.

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

Brand name or domain (e.g. hubspot.com). A domain also counts as cited when the AI links to it.

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

Optional: up to 20 competitor names or domains to compare against.

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

Which AI assistants to ask. Each prompt x engine is one answer.

## `location` (type: `string`):

Country the question is asked from (English name, e.g. Germany).

## `language` (type: `string`):

Language of the answer (English name).

## Actor input object example

```json
{
  "prompts": [
    "What is the best CRM for a small business?",
    "Which running shoes are best for flat feet?"
  ],
  "brand": "HubSpot",
  "competitors": [
    "Pipedrive",
    "Salesforce",
    "Zoho CRM"
  ],
  "engines": [
    "chatgpt"
  ],
  "location": "United Kingdom",
  "language": "German"
}
```

# Actor output Schema

## `results` (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 = {};

// Run the Actor and wait for it to finish
const run = await client.actor("rowfeed/ai-search-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 = {}

# Run the Actor and wait for it to finish
run = client.actor("rowfeed/ai-search-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 '{}' |
apify call rowfeed/ai-search-visibility-tracker --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,rowfeed/ai-search-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/IPEber6ZmqE2kQPfo/builds/ZUPBVFt5yMOZ1PtRk/openapi.json