Agents

Agents define instruction-driven AI assistants with configurable models, tools, and controlled access to shared resources.

Below is the sample resource definition file for Agent:

{
  "rAgent": {
    "Type": "Agent",
    "Artifacts": {
      "Script": "develop/creation/agents/agentscript.py"
    },
    "Properties": {
      "AgentName": "cicd_test_agent",
      "Description": "Base agent fixture for CICD QA creation testing",
      "Instruction": "Answer with a short greeting and mention that this is the base agent.",
      "ModelId": "anthropic.claude-sonnet-4-20250514-v1:0",
      "AgentResponseType": "STREAM",
      "Tools": [
        {
          "ToolName": "cicd_tool",
          "ToolDescription": "Base tool for CICD QA agent fixture",
          "ToolParameters": []
        }
      ],
      "ResourceAccessMetadata": {
        "SharedLibrariesAccess": [],
        "KnowledgebaseAccess": [],
        "ParameterAccess": [],
        "GuardRails": [
          {
            "Id": {"!DependsOn": "rGuardrail.GuardRailId"},
            "Version": "DRAFT"
          }
        ]
      }
    }
  }
}

Note: Deployment dependencies

Agent has dependencies on Tag.

Dependent resources should not be deleted before the primary resource; attempting to do so may lead to failures or inconsistencies during the deletion process.

Referencing this Resource

Below are the common keys that can be used in the DependsOn function to retrieve details of this resource.

Supported Keys

Key	Description
AgentName	Returns the AgentName value of this resource
AgentId	Returns the AgentId value of this resource

For additional supported keys, refer to the API definition document for the respective resource type.

Example

To reference this schedule from another resource, use !DependsOn with logical name and property in the format <logicalResourceName>.<PropertyName>.

Example: {"!DependsOn": "rAgent.AgentId"}