For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
Logo
DeveloperAcademyCommunityStatus
ReferenceGuides
ReferenceGuides
  • Agent Studio
    • Overview
    • Quickstart Guides
    • Core Concepts
    • Conversation Process
    • Actions
      • LLM Actions
      • Built-in Actions
      • HTTP Actions
      • Script Actions
      • Compound Actions
        • Action
        • Switch
        • For Loop
        • Parallel
        • Return
        • Try Catch and Raise Error
        • Notify
        • Input Arguments
        • Progress Updates
        • Compound Action Patterns
        • Compound Action Data Bank
        • Compound Action Examples
        • Troubleshooting Compound Actions
    • Connectors
    • System Triggers
    • Agent Architect
    • Cookbooks
    • Development and Testing
    • AI Agent Marketplace
    • Developer Tools
  • Agentic AI
    • LLM Fundamentals
    • The Agentic Reasoning Engine
    • Memory Constructs
    • Conversational Context
    • Guardrails
    • Grounding and Hallucinations
    • Continuous Learning
    • LLMs & SLMs
    • Steerability Tools
    • Multilingual Support
  • Core Platform
    • User Identity
    • Moveworks Agent (On-Prem)
    • Approvals Engine
    • Entity Catalog
    • Moveworks Data Objects
    • Security Information and Event Management (SIEM) Logs Overview
DeveloperAcademyCommunityStatus
On this page
  • Setting Up Input Arguments
  • Available Data Types
  • Usage in Compound Actions
Agent StudioActionsCompound Actions

Input Arguments

||View as Markdown|
Was this page helpful?
Edit this page
Previous

Progress Updates

Next
Built with

Input arguments define the external data a Compound Action requires to run, sourced from plugin triggers (e.g., webhooks) or upstream callers like a conversation process. They act as entry points, ensuring workflows receive validated, typed inputs, think user email for personalization or ticket IDs for routing, before diving into steps. By declaring them upfront, you enable dynamic execution while enforcing structure, reducing runtime errors and easing integration.

In the Editor, you set up Input Arguments by pressing on the Input Args button.

Setting Up Input Arguments

Access the Input Args panel in the Compound Action Editor to add, edit, or remove them. Click the Input Args button in the editor header to open the panel. Each argument needs a name, data type, optional description, and required flag. Saving updates the config instantly.

  1. Create New: Click “Create New” to open a new form to create an argument.

  2. Define Details: Enter name (e.g., user_email), select the type, add a description, and toggle required.

Available Data Types

See Data Types to check the available types in compound actions.

Usage in Compound Actions

Inputs get stored in the data bank and flow into steps via data mapping (e.g., data.user_email in action args).

1steps:
2 - action:
3 action_name: validate_email
4 input_args:
5 email: data.user_email # From declared string arg
6 output_key: validation_result
7 - switch:
8 cases:
9 - condition: validation_result.valid == true
10 steps:
11 - notify:
12 recipient_id: data.user_id # Another input
13 message: '''Email confirmed!'''