AI Governance

To manage AI deployments effectively, StackAI offers governance features like:

• Role-Based Access Control (RBAC): Define user permissions at granular levels, including access to the knowledge base and connections.

• Single Sign-On (SSO): Integrate with identity providers like Okta and Entra ID for user authentication and inheritance of groups and permissions.

• Project Publishing Controls: Restrict project publishing capabilities to authorized personnel, ensuring oversight.

• Centralized Monitoring: A unified dashboard allows administrators to monitor agent activities, usage metrics, and error logs in real-time.

Below are some of the most widely used governance features, developed in close collaboration with our customers.

Admin view – assigning users’ roles

Feature Access Control – disabling LLMs and adding default connections (i.e., the company’s API keys)

Advanced options to:

• Protect citations to ensure end users can only access content they are authorized to view.

• Enable SSO protection for all agents, allowing end-users to authenticate before use.

• Enforce admin review and publication for all agents.

Centralized view with all projects: usage, publishing controls, link to interfaces, etc.

Centralized view of all knowledge bases: access control, health status, metadata, etc.

Analytics tab per project to log all the executions. Information such as inputs, outputs, tokens consumed, latency, LLM used, and more is stored. The user can also disable logs – this has been proven useful for some highly sensitive workflows (e.g., defense).