Creates an online evaluation configuration for continuous monitoring of agent performance. Online evaluation automatically samples live traffic from CloudWatch logs at specified rates and applies evaluators to assess agent quality in production.
Request body
A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If you don't specify this field, a value is randomly generated for you. If this token matches a previous request, the service ignores the request, but doesn't return an error. For more information, see <a href="https://docs.aws.amazon.com/AWSEC2/latest/APIReference/Run_Instance_Idempotency.html">Ensuring idempotency</a>.
The name of the online evaluation configuration. Must be unique within your account.
The description of the online evaluation configuration that explains its monitoring purpose and scope.
The Amazon Resource Name (ARN) of the IAM role that grants permissions to read from CloudWatch logs, write evaluation results, and invoke Amazon Bedrock models for evaluation. If the configuration references evaluators encrypted with a customer managed KMS key, this role must also have <code>kms:Decrypt</code> permission on the KMS key. The service validates this permission at configuration creation time. For more information, see <a href="https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/evaluations-encryption.html">Encryption at rest for AgentCore Evaluations</a>.
Whether to enable the online evaluation configuration immediately upon creation. If true, evaluation begins automatically.
A map of tag keys and values to assign to an AgentCore Online Evaluation Config. Tags enable you to categorize your resources in different ways, for example, by purpose, owner, or environment.
Response
Success
The Amazon Resource Name (ARN) of the created online evaluation configuration.
The unique identifier of the created online evaluation configuration.
The timestamp when the online evaluation configuration was created.
The status of the online evaluation configuration.
The execution status indicating whether the online evaluation is currently running.
The reason for failure if the online evaluation configuration creation or execution failed.