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.
System StatusStart using Credal
  • Getting Started
    • Introduction
    • Quickstart
    • Video: Agent Building Basics
    • FAQs
  • Platform
      • Overview
      • Action Templates
      • Custom Names and Descriptions
      • Open Source Actions
      • Credentials and Security
      • Human Approval Options
      • Action Parameters
    • Bulk Analysis
LogoLogo
System StatusStart using Credal
On this page
  • Double checking action inputs
  • Coming Soon
PlatformGoverned Actions

Human Approval Options

Was this page helpful?
Edit this page
Previous

Action Parameters

Next
Built with

Double checking action inputs

In Credal, you can enable human approval for any action to ensure that action inputs are reviewed before execution. When human approval is turned on, you’ll always be prompted to double-check an action’s inputs to make sure they look correct before submitting. This provides an additional safety layer to prevent unintended operations. For control over what the AI can and can’t fill in on its own, see Action Parameters.

Additionally, administrators can enforce human approval at the organization level for specific actions through the System Connectors admin configuration panel. This ensures consistent governance and review processes across your entire organization for sensitive or critical actions.

Coming Soon

We’re actively developing additional human approval capabilities. If you’d like early access to any of these features, please contact us at support@credal.ai:

  • Organization-level HITL enforcement: Configure human approval requirements at the organization level to ensure consistent governance across all actions
  • HITL for MCP server actions: Extend human-in-the-loop approval flows to actions executed through imported MCP servers
  • Multi-user approval workflows with permissions escalation: Advanced workflows where multiple approvers can provision temporary or scoped access to resources, enabling complex cross-functional operations with granular permission grants
  • Version control and review workflows: GitHub-style review process for changes to agents and actions with branching, change approval from multiple reviewers, and version control before deploying updates