AI agents
Okta for AI Agents gives you the ability to discover and govern AI agents in your org so that you can make them a managed part of your digital workforce instead of a security risk.
Use the Okta Identity Security Posture Management (ISPM) console to find AI agents in your unmanaged and managed apps. You can also assess the agent ownership, its permissions, and the resources it can impact.
Users often grant OAuth 2.0 tokens and permissions to AI agents so they can act on their behalf in managed and unmanaged apps. IT and security teams may find it challenging to discover these AI agents, the level of access they were given, the actions they can take, and the risk they pose to the org's security posture.
ISPM helps you find AI agents in two ways:
-
Browser-captured OAuth signals
When you (super admin) configure the Okta Secure Access Monitor (SAM) plugin in your managed browser, it captures OAuth tokens that users grant to apps in real time. Okta analyzes these signals, tags AI-related grants, and surfaces them on the Browser OAuth grants page in the ISPM console.
-
Managed app integrations
After you (super admin) integrate a connector with ISPM and grant the necessary permissions, Okta automatically collects and analyzes metadata about AI agents from connected orgs and displays the results on the Discovered agents page in the ISPM console. You can get information about the agent's owner, its operational status in the managed app, the permissions it was granted, and more. Currently, ISPM can discover AI agents that were built using Salesforce Agentforce.
If the AI agent should continue operating in your org, you can register it in Okta or take appropriate remedial actions to revoke access.
See AI agents discovery in ISPM.