Skip to main content

​
Interactive Web Insights Engine Overview

The Interactive Web Insights Engine enables AI-powered interactive web browsing. Unlike static web scraping, this engine can navigate dynamic websites, interact with page elements, and extract information from JavaScript-rendered content.

​
Engine Inputs

The Interactive Web Insights Engine Configuration has the following parameters:
  • url: required. The URL to navigate to and interact with.
  • action: required. Instructions describing what actions to perform on the page and what information to extract.
  • output_schema: required. JSON schema defining the structure of data to extract. Follows the standard JSON schema specification.
See Template Strings for dynamic parameter configuration.

​
Engine Output

The output will be a JSON value matching the structure specified in the output_schema. The output may also include a roe_references field containing screenshot references captured during browsing.

​
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 Interactive Web Insights Engine

3

Configure the engine

$ starts a template string
  • url: $url
  • action: $action
  • output_schema: Copy and paste the JSON schema below:
{
  "type": "object",
  "properties": {
    "title": {
      "type": "string",
      "description": "Main title or heading"
    },
    "summary": {
      "type": "string",
      "description": "Brief summary of the content"
    },
    "key_points": {
      "type": "array",
      "items": { "type": "string" },
      "description": "List of key points extracted"
    }
  },
  "required": ["title", "summary"]
}
4

Create the Agent

Hit the Create button.
5

Run a job

Create a new job and provide:
  • url: A webpage URL to interact with
  • action: Instructions like “Extract the main sections and key information from this webpage”

​
Use Cases

  • Dynamic content extraction: Extract data from pages that require JavaScript execution
  • Form interaction: Navigate through multi-step forms or wizards
  • Authenticated scraping: Access content behind login pages
  • Single-page applications: Extract data from React, Vue, or Angular applications
  • Interactive data gathering: Click through pagination, expand sections, or trigger data loads