| _key | core | string | |
| account_id | core | string | |
| agent_arn | core | string | The Amazon Resource Name (ARN) of the agent. |
| agent_collaboration | core | string | The agent's collaboration settings. |
| agent_collaborator_summaries | core | json | A list of collaborator summaries. |
| agent_id | core | string | The unique identifier of the agent. |
| agent_name | core | string | The name of the agent. |
| agent_resource_role_arn | core | string | The Amazon Resource Name (ARN) of the IAM role with permissions to invoke API operations on the agent. |
| agent_status | core | string | The status of the agent and whether it is ready for use. The following statuses are possible: <ul> <li> CREATING – The agent is being created. </li> <li> PREPARING – The agent is being prepared. </li> <li> PREPARED – The agent is prepared and ready to be invoked. </li> <li> NOT_PREPARED – The agent has been created but not yet prepared. </li> <li> FAILED – The agent API operation failed. </li> <li> UPDATING – The agent is being updated. </li> <li> DELETING – The agent is being deleted. </li> </ul> |
| agent_version | core | string | The version of the agent. |
| agent_version_summaries | core | json | A list of objects, each of which contains information about a version of the agent. |
| client_token | core | string | A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see <a href="https://docs.aws.amazon.com/AWSEC2/latest/APIReference/Run_Instance_Idempotency.html">Ensuring idempotency</a>. |
| created_at | core | timestamp | The time at which the agent was created. |
| custom_orchestration | core | json | Contains custom orchestration configurations for the agent. |
| customer_encryption_key_arn | core | string | The Amazon Resource Name (ARN) of the KMS key that encrypts the agent. |
| description | core | string | The description of the agent. |
| failure_reasons | core | array<string> | Contains reasons that the agent-related API that you invoked failed. |
| foundation_model | core | string | The foundation model used for orchestration by the agent. |
| guardrail_configuration | core | json | Details about the guardrail associated with the agent. |
| idle_session_ttl_in_seconds | core | int64 | The number of seconds for which Amazon Bedrock keeps information about a user's conversation with the agent. A user interaction remains active for the amount of time specified. If no conversation occurs during this time, the session expires and Amazon Bedrock deletes any data provided before the timeout. |
| instruction | core | string | Instructions that tell the agent what it should do and how it should interact with users. |
| memory_configuration | core | json | Contains memory configuration for the agent. |
| orchestration_type | core | string | Specifies the orchestration strategy for the agent. |
| prepared_at | core | timestamp | The time at which the agent was last prepared. |
| prompt_override_configuration | core | json | Contains configurations to override prompt templates in different parts of an agent sequence. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/advanced-prompts.html">Advanced prompts</a>. |
| recommended_actions | core | array<string> | Contains recommended actions to take for the agent-related API that you invoked to succeed. |
| tags | core | hstore | |
| updated_at | core | timestamp | The time at which the agent was last updated. |
