Applications

Track your organization's generative AI applications in AI Defense by registering each AI-powered application and its connected AI model endpoints. You'll register these details in two sections of the AI Defense management console:

Applications: This section lists all the AI-powered applications within your organization. Each application entry provides essential details, such as the application name, associated policies, and its status. This enables quick identification and management of applications in alignment with organizational goals and compliance requirements.
Connections: This section lists the individual endpoints linked to the listed applications. This section allows you to configure and manage endpoints, ensuring secure and efficient communication between applications and their AI models. Key functionalities include assigning guardrails, applying policies, and monitoring endpoint activity for enhanced security and operational control.

Together, these sections provide a comprehensive framework for monitoring, managing, and securing AI-powered applications and their integrations.

Here’s a table highlighting the differences between an Application and a Connection in AI Defense:

Aspect	Application	Connection
Definition	A grouping of multiple connections for better management.	A specific LLM endpoint or LLM traffic that is protected or tested.
Purpose	Organizes related connections under a single entity.	Applies an Runtime policy or Validation to an LLM.
Policy Assignment	Policies are not directly applied to applications.	Each connection can have one Runtime policy applied.
Scope	Broad, encompassing multiple connections.	Specific to a single LLM endpoint or traffic flow.
Flexibility	Helps manage and structure policies across multiple LLM endpoints.	Acts as an enforcement point where policies are executed.
Relationship	Contains multiple connections.	Belongs to a single application.

See Manage AI Applications to set up your applications and connections.