# AI search citations: which sites the answers cite

**Use case:** 

Asks a ChatGPT model two category questions with web search and lists, for each answer, the domains it cites, every domain it read, the search queries it ran and whether your own site is cited. Use it to find the review sites, directories and publishers the assistant relies on in your market. The example uses an HR software brand; replace the brand, domains and prompts. Each check costs $0.09.

## Input

```json
{
  "brand": "Humaans",
  "brandDomains": [
    "humaans.io"
  ],
  "competitors": [
    "BambooHR | bamboohr.com",
    "Personio | personio.com"
  ],
  "prompts": [
    "Best HR software for small UK companies?",
    "What HR software should a 20-person company use for onboarding?"
  ],
  "engines": [
    "openai"
  ],
  "openaiModel": "gpt-6.1-terra",
  "anthropicModel": "claude-sonnet-5-5",
  "geminiModel": "gemini-3.8-flash",
  "maxSearches": 2,
  "maxChecks": 2,
  "includeAnswer": true,
  "compareWithPrevious": true
}
```

## Output

```json
{
  "engine": {
    "label": "Engine",
    "format": "text"
  },
  "prompt": {
    "label": "Prompt",
    "format": "text"
  },
  "citedDomains": {
    "label": "Cited domains",
    "format": "array"
  },
  "brandCitations": {
    "label": "Your pages cited",
    "format": "array"
  },
  "sourceDomains": {
    "label": "Domains read",
    "format": "array"
  },
  "searchQueries": {
    "label": "Searches run",
    "format": "array"
  },
  "searchCount": {
    "label": "Searches",
    "format": "number"
  }
}
```

## How it works

### 1. Sign up on Apify or log in

The AI Brand Visibility Monitor: ChatGPT, Claude & Gemini Mentions Actor is ready to run with the inputs already set for "AI search citations: which sites the answers cite". [Sign up or log in](https://console.apify.com/create-task-from-example/dWaMzDgIRQ6dHXKox) and you'll land in Apify Console with a copy of this exact task.

### 2. Start the "AI search citations: which sites the answers cite" task

The AI Brand Visibility Monitor: ChatGPT, Claude & Gemini Mentions Actor will start running based on the input automatically. You can also change all the input fields, like brand, brand domains, and more, to match your specific use case.

### 3. Receive the "AI search citations: which sites the answers cite" output

Monitor the progress in real time. You will be notified as soon as your dataset is complete and ready for review. Each result includes data such as engine, prompt, cited domains, and more.

### 4. Integrate into your workflow

The final output is delivered in JSON, CSV, or Excel format, ready to be plugged into your workflow. You can also [run the "AI search citations: which sites the answers cite" task via API](https://apify.com/localwire/ai-brand-visibility.md).

## FAQ

### What does the "AI search citations: which sites the answers cite" task return?

The "AI search citations: which sites the answers cite" task returns one record per check: engine, prompt, the cited domains, the citations on your own domains, the domains read, the search queries and the search count.

### Can the AI search citations task show Claude's or Gemini's sources?

Yes. Add anthropic or gemini to the engines field of the AI search citations task and raise maxChecks to prompts times engines. Each engine's answer is its own record and its own check.

### How do I run the "AI search citations: which sites the answers cite" task on a schedule or from code?

Copy the "AI search citations: which sites the answers cite" task to your Apify account, then add a schedule in Apify Console or start it with the Run task API endpoint. Results download as JSON, CSV or Excel.

## About this Actor

This example demonstrates how to use [AI Brand Visibility Monitor: ChatGPT, Claude & Gemini Mentions](https://apify.com/localwire/ai-brand-visibility.md) with a specific input configuration. Visit the [Actor detail page](https://apify.com/localwire/ai-brand-visibility.md) to learn more, explore other use cases, and run it yourself.


## How to integrate an Actor?

This Task's input is already configured above. Use it as-is rather than inventing a new one.

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 full API examples (JavaScript, Python, CLI, MCP, OpenAPI), see this Task's Actor page: https://apify.com/localwire/ai-brand-visibility.md

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`).