> ## Documentation Index
> Fetch the complete documentation index at: https://docs.roe-ai.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Data Analysis

> Performs AI-powered multimodal data analysis with web research and context source integration.

## Data Analysis Engine Overview

The Data Analysis Engine is an agentic workflow that intelligently orchestrates document/image extraction with optional web research and context source querying. The agent reasons about the best approach to extract information based on the provided instruction and content.

## Engine Inputs

The Data Analysis Engine Configuration has the following parameters:

* **text**: *optional.* Text content to extract information from. Leave blank to extract from images only.
* **images**: *optional.* Image URLs or file IDs (comma/newline/whitespace separated). Leave blank to extract from text only.
* **instruction**: *optional.* Instructions describing what to extract or analyze from the provided content.
* **output\_schema**: *required.* JSON schema defining the structure of data to extract. Follows the standard [JSON schema specification](https://json-schema.org/).
* **context\_sources**: *optional.* Define context sources (Snowflake, ClickHouse, Zendesk, etc.) for the agent to query during analysis.

<Note>At least one of **text** or **images** must be provided.</Note>

See [Template Strings](/agents/input-definition#template-strings) for dynamic parameter configuration.

## Engine Output

The output will be a JSON value matching the structure specified in the **output\_schema**.

## Example Usage

<Steps>
  <Step title="Create an Agent">
    Click on the "Add Agent" button in the top right corner of the Agents page.

    <Frame>
      <img src="https://mintcdn.com/roeai/qeWYCF2quzHQHhsD/images/add-agent.png?fit=max&auto=format&n=qeWYCF2quzHQHhsD&q=85&s=b3e1ec9b816ed1e57cb1ecfa53ff4288" width="1920" height="1045" data-path="images/add-agent.png" />
    </Frame>

    Enter a name and an optional description of your Agent.
  </Step>

  <Step title="Select the Data Analysis Engine" />

  <Step title="Configure the engine">
    <Info>\$ starts a template string</Info>

    * **text**: \$text
    * **images**: \$images
    * **instruction**: Analyze the data and extract key insights
    * **output\_schema**: Copy and paste the JSON schema below:

    ```json theme={null}
    {
      "type": "object",
      "properties": {
        "summary": {
          "type": "string",
          "description": "Summary of the analysis"
        },
        "key_findings": {
          "type": "array",
          "items": { "type": "string" },
          "description": "List of key findings"
        },
        "recommendations": {
          "type": "array",
          "items": { "type": "string" },
          "description": "Recommended actions"
        }
      },
      "required": ["summary"]
    }
    ```
  </Step>

  <Step title="Create the Agent">
    Hit the **Create** button.
  </Step>

  <Step title="Run a job">
    Create a new job and provide the data to analyze.
  </Step>
</Steps>

## Capabilities

The Data Analysis Engine has access to multiple tools:

* **Extraction**: Process text and images directly
* **URL Finder**: Search for relevant URLs
* **Web Extraction**: Scrape and extract from web pages
* **Perplexity Search**: Conduct web research
* **Context Source Queries**: Query connected Snowflake, ClickHouse, or Zendesk sources

## Use Cases

* **Business intelligence**: Generate insights from business data with web enrichment
* **Document analysis**: Extract structured data from documents and images
* **Research synthesis**: Combine provided data with web research
* **Multi-source analysis**: Integrate data from context sources with provided content
* **Report generation**: Create automated data reports and summaries