AI Defense Management API

The AI Defense Management API supports the following types of activities:

• AI Runtime management and monitoring:
  • Managing the AI applications and connections that are protected by AI Defense Runtime. (See Applications and Connections.)
  • Managing and applying AI Defense Runtime policies that enforce your safety and security rules to protect those applications and their users. (See Policies.)
  • Getting the results from the AI Defense Runtime monitoring so that you're alerted of violations. (See Events.)
• AI Validation to evaluate the safety and security of your AI agents, models, and applications. (See AIValidationAPI.)
• Model scanning and MCP scanning to check your model supply chain for security vulnerabilities. (See ScanManagerAPI".)

Note that the AI Defense management API does not provide runtime chat inspection for AI Runtime enforcement. For that, see instead the AI Defense Inspection API.