---
type: resource-type
title: Harness
description: aws resource type AWS::BedrockAgentCore::Harness
name: Harness
lexicon: aws
resource_type: AWS::BedrockAgentCore::Harness
---
`AWS::BedrockAgentCore::Harness`, a resource type of the aws lexicon.

## Properties

- `ExecutionRoleArn` (`string`, required): The ARN of the IAM role that the harness assumes when running.
- `HarnessName` (`string`, required): The name of the harness.
- `Model` (`Harness_HarnessModelConfiguration`, required): The model configuration for the harness.
- `AllowedTools` (`string[]`, optional): The tools that the agent is allowed to use.
- `Arn` (`string`, optional): The Amazon Resource Name (ARN) of the harness.
- `AuthorizerConfiguration` (`Harness_AuthorizerConfiguration`, optional): The inbound authorization configuration for authenticating incoming requests.
- `CreatedAt` (`string`, optional): The timestamp when the harness was created.
- `Environment` (`Harness_HarnessEnvironmentProvider`, optional): The compute environment configuration for the harness, including underlying runtime information.
- `EnvironmentArtifact` (`Harness_HarnessEnvironmentArtifact`, optional): The environment artifact for the harness, such as a custom container image.
- `EnvironmentVariables` (`Record<string, unknown>`, optional): Environment variables to set in the harness runtime environment.
- `HarnessId` (`string`, optional): The unique identifier of the harness.
- `MaxIterations` (`number`, optional): The maximum number of iterations the agent loop can execute per invocation.
- `MaxTokens` (`number`, optional): The maximum number of tokens the agent can generate per iteration.
- `Memory` (`Harness_HarnessMemoryConfiguration`, optional): The AgentCore Memory configuration for persisting conversation context.
- `Skills` (`Harness_HarnessSkill[]`, optional): The skills available to the agent.
- `Status` (`Harness_HarnessStatus`, optional): The current status of the harness.
- `SystemPrompt` (`Harness_HarnessSystemContentBlock[]`, optional): The system prompt that defines the agent's behavior.
- `Tags` (`Harness_Tag[]`, optional): Tags to apply to the harness resource.
- `TimeoutSeconds` (`number`, optional): The maximum duration in seconds for the agent loop execution per invocation.
- `Tools` (`Harness_HarnessTool[]`, optional): The tools available to the agent.
- `Truncation` (`Harness_HarnessTruncationConfiguration`, optional): The truncation configuration for managing conversation context.
- `UpdatedAt` (`string`, optional): The timestamp when the harness was last updated.
- `Version` (`string`, optional): The version of the harness. Incremented on every successful update.

## Attributes

- `Arn`
- `CreatedAt`
- `Environment.AgentCoreRuntimeEnvironment.AgentRuntimeArn`
- `Environment.AgentCoreRuntimeEnvironment.AgentRuntimeId`
- `Environment.AgentCoreRuntimeEnvironment.AgentRuntimeName`
- `HarnessId`
- `Memory.ManagedMemoryConfiguration.Arn`
- `Status`
- `UpdatedAt`
- `Version`