aiAgentGuardrailCreate

Create a new Guardrail in the AI Agent Registry.

Description: This mutation creates a new guardrail associated with the authenticated user's account.

Input Parameters (AiAgentGuardrailCreateInput):

• providerAccountId: ID! - Required. Provider account ID in the AI Agent Registry system to which the guardrail will be linked.
• externalId: ID - Optional. External ID for the guardrail.
• version: String - Optional. Version of the guardrail.
• name: String - Required. Name of the guardrail.
• description: String - Optional. Description of the guardrail.
• configurationJson: String - Optional. The JSON configuration for the guardrail detailing its policies and operational parameters.
• status: AiAgentGuardrailStatus - Optional. The operational status of the guardrail (e.g., ENABLED, DISABLED).
• agentVersionIds: [String!] - Optional. Agent version IDs associated with this guardrail.
• tags: [AiAgentTagInput!] - Optional. Tags for categorization.

Response:

• Returns the newly created AiAgentGuardrail object.

Example Request:

mutation {
  aiAgentGuardrailCreate(input: {
    providerAccountId: "aws_account_id_12345",
    externalId: "guardrail123",
    version: "1.0",
    name: "Data Privacy Guardrail",
    description: "Prevents access to sensitive data.",
    configurationJson: "{ \"priority\": \"high\", \"category\": \"data-processing\" }",
    status: ENABLED,
    agentVersionIds: ["v1", "v2"],
    tags: [
      {
          key: "security",
          value: "high"
      }
    ]
  }) {
    id
    externalId
    name
    description
    configurationJson
    status
    tags {
      key
      value
    }
    agentVersions {
      id
      name
      version
    }
    auditData {
      createdByUserId
      createdTime
      modifiedByUserId
      modifiedTime
      updatedByOrigin
      updatedAtProviderTime
    }
  }
}

aiAgentGuardrailCreate(
  input: AiAgentGuardrailCreateInput!
): AiAgentGuardrail

Arguments

aiAgentGuardrailCreate.input ● AiAgentGuardrailCreateInput! non-null input agent-control-tower

Type

AiAgentGuardrail object agent-control-tower

Represents a guardrail in the AI Agent Registry system that defines policies and operational parameters for AI agents.

Guardrails are security and compliance mechanisms that control AI agent behavior by enforcing rules, filtering content, and ensuring adherence to organizational policies.