Storm

Storm is Rival’s content-tagging engine. Unlike Function and MCP tools, a Storm tool has no handler code. Instead, you upload a topic file — a document that defines the topics, categories, or tags to classify against — and Storm reads incoming content against it and returns the tagged result.

When to use Storm

Use Storm to classify documents, tickets, or any text against a predefined taxonomy; tag large volumes of content automatically; apply consistent labeling without writing classification logic; and keep the taxonomy updatable without changing code. For general-purpose logic, use a Function tool (Python, JavaScript, or Lua) instead.

How a Storm tool runs

A run involves three things:

• A topic file — the asset defining what to tag against (your taxonomy).
• A source — a JSON payload or a digital asset containing the content to tag.
• A target — inline JSON output, or a digital asset to write the result into.

Event format

Text input to JSON output:

{
    "topic_file": "search terms or content string here"
}

Digital-asset input to digital-asset output:

{
    "topic_file": "assets/org-slug/my-dataset.csv",
    "source_asset_id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
    "target_asset_id": "f9e8d7c6-b5a4-3210-fedc-ba0987654321"
}

topic_file is always required. source_asset_id and target_asset_id are used when working with file-based digital assets.

Digital assets

Digital assets are files in the platform’s storage. For Storm you need the file reference (via the Copy Ref button) for topic_file, and the asset UUID for source_asset_id / target_asset_id.

Testing and configuration

Test in the Test panel of the Tool Editor: choose an input type (Text or Data Source), an output type (JSON or Data Outbound), and run. When creating a Storm tool you provide a digital_asset_id pointing to your topic file — required to save the tool.

Storm tools follow the same pricing, versioning, and publishing workflow as Function and MCP tools, and can’t be switched to another type after creation.