AI Defense Applications

Easily manage your organization's generative AI applications by entering details of AI-powered apps and their connected AI model endpoints. This streamlined process ensures seamless integration, enabling efficient oversight and enhanced functionality across your AI ecosystem.

It is divided into two key sections:

  • 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.

Applications

To get started with creating a protective layer with AI Defense, you'll need to Add Application and connect them to their respective AI model endpoints. You can select:

  • Gateway: AI Gateway acts as an intermediary to manage, monitor, and protect AI interactions. The gateway acts as a filter and security checkpoint for all AI traffic, ensuring safe and compliant operations.

  • API: APIs allow applications to interact programmatically with the AI Defense system, enabling seamless communication and enforcement of policies.


Note

When creating an application, you will need to select a Connection type, which refers to the enforcement mechanism for your guardrail policies.

You'll need to map your applications to AI Defense and connect them to their corresponding AI model endpoints. This integration enables AI Defense to monitor and secure the underlying models that power your applications.

To add an application to AI Defense:

  1. Click Applications on the left navigation pane. Click Add application button on the right top corner of the page.

  2. On the Add application dialogbox, enter the Name for the application, Connection type (API or Gateway) and Description you would like to map. The Description is optional, you can add details if required. Click Continue.

API:

  1. The application is created and now you can add a connection. Click Add Connection on the right top corner of the Applications page.

  2. In the Add connection pane, enter connection name, click Add connection. Click Add API Key.

  3. In the Add API Key pane, enter the Token name, select Expiration date and click Generate API token.

  4. Once the token is generated, make a note of the API key, and click Add API Key.


Note

For more information on API key, see our AI Defense API Document.

Gateway:

  1. The application is created and now you can add a connection. Click Add Connection on the right top corner of the Applications page. Enter Connection name and select the dropdown for Endpoint. In case, no endpoints are added. Click Add endpoint.

  2. Click Add connection.


Note

The connection guide provides a cURL command to update the proxy URL, ensuring that all AI interactions are effectively monitored.

Filter Application List

You can filter the applications list view by clicking the settings icon on the right top corner of the table. You can select from:

  • Name

  • Description

  • Connection type

  • Connections

Click Apply. This changes the columns displayed in the table.

Add Endpoint

An endpoint is a crucial connection point that allows AI Defense to interact with, monitor, and secure the AI models your applications rely on.

By adding an endpoint, you provide AI Defense with the necessary details to communicate with the AI model.

To add a new endpoint:

  1. On the Add/manage Endpoints dialogbox, click Add.

  2. In the Add endpoint dialogbox:

    1. Select Model provider from the dropdown list.

    2. Select Endpoint from the dropdown list.

  3. Click Add at the bottom of the dialogbox.

Connections

The Connections section focuses on managing the individual endpoints associated with your listed applications. It provides tools to configure and oversee these endpoints, ensuring seamless and secure communication between your applications and their connected AI models.

Filter Connections List

You can filter the connections list view by clicking the settings icon on the right top corner of the table. You can select from:

  • Name

  • Connection type

  • Endpoints

  • Models

  • Application

  • Policy

  • Status

  • Last active

Click Apply. This changes the columns displayed in the table.

Connection Guide

You can access the Connection Guide by clicking on the three dots in the same row as the Name of the application.

AI Defense provides two primary methods for integrating applications: API Method and Gateway Method. These methods enable developers to seamlessly secure and monitor AI interactions based on organizational requirements.

The connection guide provides step-by-step instructions to implement both methods:

  • API Method: Developers can follow detailed API documentation, including endpoint definitions, authentication steps, and examples of integrating Guardrails and monitoring policies. The connection guide provides you with details of the added API key.

  • Gateway Method: The guide outlines network or proxy configurations required to route traffic through the AI Gateway, ensuring seamless and secure application integration. The connection guide provides you with all the details of the connection and endpoint. You can edit the cURL code to add to your proxy server.