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
  • How it Works
  • When to Use
Agent StudioActionsCompound Actions

Progress Updates

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

Compound Action Patterns

Next
Built with

Progress updates let developers send real-time status messages to users during Action execution, improving transparency in conversational flows. Each Action supports an optional progress_updates map with two fields:

  • on_pending: Message shown when the action starts (e.g., “Fetching your data…”).
  • on_complete: Message shown when the action finishes (e.g., “Data fetched successfully.”).

These fields are optional. When you provide it, messages appear in the chat only if the Action runs in a conversational agent.

How it Works

1action:
2 action_name: fetch_user_details
3 output_key: user_data
4 input_args:
5 user_id: input.user_id
6 progress_updates:
7 on_pending: "Looking up your profile..."
8 on_complete: "Profile loaded!"
  • Conversational Agents: Users see both messages in the chat stream.
  • Ambient Agents (system-level): No messages are shown, even if configured—progress updates are ignored.

When to Use

Use progress updates for long-running or user-visible actions (e.g., API calls, file processing) in conversational bots to reduce perceived wait time. Skip them in backend-only or fast operations to avoid clutter.

Tip: Keep messages concise and action-oriented. Use templating for dynamic content:

1on_pending: "Downloading {{input.file_count}} files..."