Skip to main content
Generate text using one of your Agents. Unlike the standard Generate Text action, this action uses the Agent’s full configuration — including its Knowledge Base access, brand voice, instructions, and capabilities. Use this when you want the same quality and context-awareness you get from chatting with an Agent, but inside a Workflow step.
1

Add the action

In the Workflow builder, click + between blocks and select Generate Text with Cassidy Agent from the action library.
Action library with Generate Text with Cassidy Agent selected
Adding the Generate Text with Cassidy Agent action between blocks
2

Rename the action (optional)

Enter a descriptive name to make the action easier to identify and reference as a variable in later steps.
Renaming the action block
3

Select an Agent

Choose which Agent to use for this step. The Agent’s Knowledge Base access, instructions, and brand voice will all apply.
Agent selector dropdown
4

Write a prompt

Enter the prompt for the Agent. Reference variables from previous steps or the trigger using the # symbol to provide dynamic context.
Prompt field with variable references
5

Configure Structured Output Fields (optional)

If you need the AI to return data in a specific format with defined fields, set up structured outputs. This gives you named fields with specific data types you can reference individually in later steps.
Structured Output Fields configuration
6

Configure Conversation Memory (optional)

Enable Conversation Memory if you want the Workflow to retain conversation history and carry context across runs.
7

Adjust advanced model settings (optional)

Under Advanced Model Settings:
  • Temperature — Controls randomness. Lower values (e.g., 0.1) produce focused results; higher values (e.g., 1.0) produce more creative outputs. Default is 0.70.
  • Include Citations — Toggle to include Knowledge Base citations in the output.
Advanced Model Settings panel with temperature and citations
This action inherits Connectors and Capabilities from the selected Agent. To add tools like Data Analysis or Web Search, configure them on the Agent itself. If you need per-action control over connectors and capabilities, use the standard Generate Text action instead.