Skip to main content
Design actions the agent can invoke on demand during a live conversation. Each action can launch a visual flow where you can speak to the caller (Say) and call external APIs (API Request), then pass results back to the agent.

​
Overview

  • When it runs: On-demand based on caller intent (e.g. “check order status”).
  • Action definition: Provide name, description, and optional parameters the AI should collect from the caller.
  • Flow: Each action can launch a flow composed of nodes that speak and call APIs, returning variables the agent can use to respond.
Action names must be 1-63 characters and use only letters, numbers, underscores, or hyphens (e.g. check_order_status, CheckOrderStatus).
Name and Description is passed as context to the AI to better determine when to call the action. Ensure to provide as much context as possible here for the AI to better identify when to call this Action

​
Create a During-Call Action

  1. Open Studio → Build → AI Agents → Actions tab → During Call.
  2. Click “Create New Action” and configure:
    • Name and Description (clear, intent-focused wording helps the AI)
    • Parameters (optional):
      • Name, Description, Type (String, Number, List), Required flag
      • Use descriptions to specify format and examples the AI should gather
  3. Save the action, then choose Save & Edit Flow to open the Flow Builder.

​
Flow Builder

The flow defines what happens when this action is invoked. Drag nodes from the sidebar and connect them starting from the Start node.
  • Variables: You can reference variables from Pre-Call Actions and from previous nodes in the same flow. Saved values become available to subsequent nodes and to the agent when it speaks next.
  • Filler messages: Use a Say node to speak while an API request is in progress.

​
Say Node

Speak a message to the caller, with support for variables and language-specific content.
  • Message (Default): Main text to speak. Supports variables like {{firstName}}.
  • Language-specific messages: Optionally tailor messages per language. If not provided, the default message is used.
  • Variables support: Insert variables using the variable picker. You can use:
    • Pre-Call variables (e.g. contact details)
    • Variables created earlier in the flow
Use cases:
  • Provide confirmations, prompts, or interim updates while waiting on API calls.
  • Share results from previous nodes (e.g. “Your order {{orderId}} is on the way.”)

​
API Request Node

Call an external HTTP API and map response fields to variables. Configuration (same capabilities as Pre-Call API requests):
  • Method: GET, POST, PUT, DELETE, PATCH
  • URL: Static URL (e.g. https://api.example.com/orders/)
  • Query Params: Key-value pairs, variable-aware
  • Headers: Static or variable-aware (e.g. Authorization)
  • Body: JSON body for non-GET methods; variables supported
  • Auth Profile: Optional reusable credentials profile
  • Test Request: Use “Send” to preview response in Data or Meta tabs
Response handling:
  • Inspect the response preview, then map JSON paths to variables.
  • Saved variables become available to downstream nodes and to the agent’s next turn.
Entire response is added to the AI context unless restricted. Specify JSON paths to include only selected fields.
Tips:
  • Use a preceding Say node as a filler message while the request runs.
  • Keep payloads minimal and map only the fields you need.

​
Best Practices

  • Start with simple flows: Say -> API Request -> Say.
  • Use descriptive parameter names and clear descriptions to help the AI collect inputs reliably.