Human-in-the-Loop Approvals
Last Modified: 2026-11-19
Human-in-the-Loop Approvals
Some actions are important enough that a person should approve them before they run. A policy rule can be marked as needing approval; when an agent makes a call that matches that rule, the human-in-the-loop (HITL) queue lists the action for a human decision before it proceeds. Agent ID supports more than one elicitation mode for getting that decision from a human reviewer.
| Elicitation Mode | How It Works |
|---|---|
| In-tool approval prompt | The gateway pauses the call and shows an approval prompt directly in the person's AI tool (their MCP client). If they approve, the call goes ahead; if they decline, or do not respond in time, the call is blocked. |
| CIBA | The gateway sends an out-of-band push notification to the approver's CIBA-enabled identity-provider client; the approver clicks Yes or No independently of the agent's session. |
| The approver receives an emailed link to review and approve or deny the request outside the calling session. |
Note: If the AI tool cannot show an approval prompt, the call is blocked rather than allowed. Agent ID never lets a call through just because it could not ask.
Procedure
- On the Approval requests page, click the pending request.
- Review the requesting identity, the tool and resource it is calling, and any supporting context shown.
Results
The originating agent's call completes if approved, or is rejected if denied, and the decision is written to the audit log.
Related Articles
Agent ID Administration 1Number of Views RSA Agent ID Installation, Deployment, and Administration Guide 5Number of Views Agent ID Components 1Number of Views Agent ID Policies 1Number of Views Owner approvals are skipped if the owner previously approved at least one item in the request as a supervisor in RSA Ident… 74Number of Views
Trending Articles
Don't see what you're looking for?