Skip to main content

​
URL Finder Engine Overview

The URL Finder Engine searches for the most relevant URLs using text-based Google Search, reverse image lookup via Google Lens, or both. It returns URLs with titles, snippets, and AI-scored relevance ratings.

​
Engine Inputs

The URL Finder Engine Configuration has the following parameters:
  • search_term: optional. Search engine query to find relevant URLs. Required if search_image is not provided.
  • search_image: optional. Image URL (http/https) or file identifier (file_*) for reverse image lookup using Google Lens. When provided, performs visual search.
  • description: required. Description of the target URLs to be included in the search results. Used to score relevance.
  • search_limit: optional. Maximum number of search results to analyze (default: 5, range: 1-100).
  • top_results: optional. Number of best matching URLs to return (default: 1, range: 1-100). Must be less than or equal to search_limit.
  • model: optional. The AI model to use for relevance scoring (default: gpt-5.1-2025-11-13).
At least one of search_term or search_image must be provided.
See Template Strings for dynamic parameter configuration.

​
Engine Output

The output is a structured list of discovered URLs with metadata: 
{
  "urls": [
    {
      "url": "https://example.com/page",
      "title": "Page Title",
      "snippet": "Brief description from search results",
      "score": 0.95
    }
  ]
}

​
Example Usage

1

Create an Agent

Click on the “Add Agent” button in the top right corner of the Agents page.
Enter a name and an optional description of your Agent.
2

Select the URL Finder Engine

3

Configure the engine

$ starts a template string
  • search_term: $search_term
  • description: Find the official product page for this item
  • search_limit: 10
  • top_results: 3
4

Create the Agent

Hit the Create button.
5

Run a job

Create a new job and provide a search term or image to find relevant URLs.

​
Use Cases

  • Product matching: Find product pages matching a description or image
  • Reverse image search: Find the source of an image using Google Lens
  • Web crawling: Discover relevant pages for further processing
  • Content discovery: Find pages matching specific criteria
  • Data pipeline input: Generate URL lists for batch processing with other engines