Skip to main content
Version: V12

Summarize Tool

Use the Summarize tool to enable AI-powered workflows to generate concise summaries of content. When you connect this tool to an AI node, the AI model can dynamically summarize videos, documents, transcripts, and other text-based content based on user requests and workflow context.

In this article, you learn how to add, configure, and test the Summarize tool in your workflow.

Concept​

The Summarize tool is a tool node that provides AI models with the ability to generate summaries from content in your VIDIZMO library. Unlike regular workflow nodes that execute in sequence, this tool is invoked by an AI node only when the model determines that summarization is needed.

Key capabilities:

  • Content summarization - Generate concise summaries from videos, documents, transcripts, and other text-based content
  • Configurable detail level - Control summary length and depth to match your use case
  • Context-aware output - Produce summaries that account for the user's original question and conversation context
  • Multi-format support - Summarize content from transcripts, captions, document text, and descriptions

Understand how the tool works​

This section explains how the Summarize tool operates within a workflow and how it connects to other nodes.

Tool connectors​

In the Workflow Designer, nodes use colored connectors to indicate the type of connection and data flow. The Summarize tool uses the green connector, which is specific to tool nodes.

Execution flow​

When a workflow runs, the Summarize tool operates in this sequence:

  1. The AI node receives user input from the chatbot.
  2. The AI model analyzes the input and determines whether summarization is needed.
  3. If summarization is needed, the AI invokes the Summarize tool through the green connector.
  4. The tool processes the content using the configured parameters and generates a summary.
  5. The summary is stored in the field specified in Output Field.
  6. The AI node accesses the summary and composes a response for the user.
┌─────────────┐      ┌─────────────┐      ┌──────────────────┐
│ User Query  │ ───► │  AI Node    │ ───► │  Summarize       │
└─────────────┘      └─────────────┘      │ (Green Connector)│
                            ▲              └──────────────────┘
                            │                       │
                            └── state.data.summary ◄┘

When to use this tool​

Use the Summarize tool when your workflow requires:

  • AI-driven summarization of long-form content such as video transcripts or documents
  • Condensed overviews of content items based on natural language requests
  • Summaries tailored to specific questions or topics within a larger piece of content
  • Quick content digests that help users understand material without reviewing the full source

Add the Summarize tool to your workflow​

Follow these steps to add the Summarize tool to your workflow canvas.

  1. Go to Portal Settings > Chatbot > Workflow.

  2. Select an existing workflow or create a new workflow.

  3. In the Node Library, expand the Tools category.

  4. Drag Summarize Tool onto the canvas.

Connect the tool to an AI node​

After you add the Summarize tool to the canvas, connect it to an AI node.

  1. Locate your AI node (such as an LLM node) on the canvas.

  2. Drag a connection line from the green connector to the input connector on the Summarize tool node.

  3. Release to create the connection. A green connector (●) indicates a successful tool connection.

NOTE: The green connector indicates that the tool is available to the AI node for on-demand invocation. The tool doesn't execute in sequence with other nodes, it executes only when the AI model decides to invoke it.

Configure the Summarize tool​

Select the Summarize node to open the Node Configuration Panel. You can configure the following options:

Description​

Instructions for the LLM on how and when to use this tool. The default description provides guidance including:

  • When to invoke summarization (user asks for a summary, overview, or digest)
  • How to interpret content input (transcripts, documents, descriptions)
  • Expected output format and length guidelines

The AI uses this description to determine when summarization is appropriate. For example, when a user asks "Give me a summary of this training video," the AI reads the description to understand it should invoke the Summarize tool with the video's transcript or description as input.

TIP: Keep the default description unless you need to customize the AI's summarization behavior for specific use cases.

Summarization parameters​

You can configure the following options:

  • Input Field: The text content to summarize. The AI typically populates this from retrieved content such as transcripts, document text, or descriptions. Use ${state.data.content_text} to reference content retrieved by other tools or nodes, or enter static text for testing.

All summarization parameters support Fixed (static value) and Expression (dynamic value using ${variable} syntax) input modes.

Model settings​

These optional settings let you override the default AI model used for summarization.

  • Model Provider: The AI provider to use for generating the summary. When left empty, the tool uses the default model configured for the workflow. Specify a provider when you need a particular model for summarization quality or cost reasons.

  • Model ID: The specific model identifier from the selected provider. When left empty, the tool uses the provider's default model.

  • System Prompt: Instructions that guide how the AI generates the summary. The default prompt provides general summarization guidance. Customize this when you need summaries in a specific format, tone, or focus area. For example, instruct the model to focus on action items, key decisions, or technical details.

  • Temperature: Controls the randomness of the generated summary. Lower values produce more focused and deterministic output. Higher values produce more creative and varied summaries. Default is 0.3.

  • Max Token Limit: The maximum number of tokens the model can generate in the summary response. Use this to control summary length and manage token consumption.

Output settings​

  • Output Field: Variable name where the summary is stored for use by other nodes. Click to select an existing variable or create a new one. The AI node and subsequent workflow nodes access results using ${state.data.<variable_name>}. For example, if you name it summary, access it as ${state.data.summary}.

Test the configuration​

After you configure the Summarize tool, test the workflow to verify correct behavior.

  1. Go to Portal Settings > Chatbot > Agents.

  2. Select the agent associated with your workflow, or create a new agent and assign your workflow.

  3. Open the chatbot interface in the portal.

  4. Enter a query that should trigger summarization. For example:

    • "Summarize this training video"
    • "Give me an overview of the onboarding document"
    • "What are the key points from the quarterly report?"

  5. Verify that the agent returns a coherent summary of the referenced content.

  6. Check that the summary length and detail match your configured parameters.

  7. If results don't match expectations, return to the Workflow Designer and adjust your configuration.

Best practices​

  • Pair the Summarize tool with the Search Mashup tool or Read Content tool so that the AI can first retrieve content and then summarize it in a single interaction.
  • Customize the System Prompt to control summary format and focus. For example, instruct the model to produce bullet-point summaries or to focus on action items.
  • Adjust Temperature based on your needs. Use lower values for factual, consistent summaries and higher values for more varied output.
  • Customize the tool description to focus summarization on specific content types relevant to your organization.
Did you find this article helpful?