Docs Home Pulumi IaC Pulumi ESC Pulumi Insights Pulumi Cloud Packages Tutorials
  1. Packages
  2. AWS
  3. API Docs
  4. bedrock
  5. AgentAgent
AWS v6.76.0 published on Tuesday, Apr 8, 2025 by Pulumi
pulumi/pulumi-aws

aws.bedrock.AgentAgent

Explore with Pulumi AI

AWS v6.76.0 published on Tuesday, Apr 8, 2025 by Pulumi
pulumi/pulumi-aws

Resource for managing an AWS Agents for Amazon Bedrock Agent.

Example Usage

Basic Usage

import * as pulumi from "@pulumi/pulumi";
import * as aws from "@pulumi/aws";

const current = aws.getCallerIdentity({});
const currentGetPartition = aws.getPartition({});
const currentGetRegion = aws.getRegion({});
const exampleAgentTrust = Promise.all([current, currentGetPartition, currentGetRegion, current]).then(([current, currentGetPartition, currentGetRegion, current1]) => aws.iam.getPolicyDocument({
    statements: [{
        actions: ["sts:AssumeRole"],
        principals: [{
            identifiers: ["bedrock.amazonaws.com"],
            type: "Service",
        }],
        conditions: [
            {
                test: "StringEquals",
                values: [current.accountId],
                variable: "aws:SourceAccount",
            },
            {
                test: "ArnLike",
                values: [`arn:${currentGetPartition.partition}:bedrock:${currentGetRegion.name}:${current1.accountId}:agent/*`],
                variable: "AWS:SourceArn",
            },
        ],
    }],
}));
const exampleAgentPermissions = Promise.all([currentGetPartition, currentGetRegion]).then(([currentGetPartition, currentGetRegion]) => aws.iam.getPolicyDocument({
    statements: [{
        actions: ["bedrock:InvokeModel"],
        resources: [`arn:${currentGetPartition.partition}:bedrock:${currentGetRegion.name}::foundation-model/anthropic.claude-v2`],
    }],
}));
const example = new aws.iam.Role("example", {
    assumeRolePolicy: exampleAgentTrust.then(exampleAgentTrust => exampleAgentTrust.json),
    namePrefix: "AmazonBedrockExecutionRoleForAgents_",
});
const exampleRolePolicy = new aws.iam.RolePolicy("example", {
    policy: exampleAgentPermissions.then(exampleAgentPermissions => exampleAgentPermissions.json),
    role: example.id,
});
const exampleAgentAgent = new aws.bedrock.AgentAgent("example", {
    agentName: "my-agent-name",
    agentResourceRoleArn: example.arn,
    idleSessionTtlInSeconds: 500,
    foundationModel: "anthropic.claude-v2",
});
Copy
import pulumi
import pulumi_aws as aws

current = aws.get_caller_identity()
current_get_partition = aws.get_partition()
current_get_region = aws.get_region()
example_agent_trust = aws.iam.get_policy_document(statements=[{
    "actions": ["sts:AssumeRole"],
    "principals": [{
        "identifiers": ["bedrock.amazonaws.com"],
        "type": "Service",
    }],
    "conditions": [
        {
            "test": "StringEquals",
            "values": [current.account_id],
            "variable": "aws:SourceAccount",
        },
        {
            "test": "ArnLike",
            "values": [f"arn:{current_get_partition.partition}:bedrock:{current_get_region.name}:{current.account_id}:agent/*"],
            "variable": "AWS:SourceArn",
        },
    ],
}])
example_agent_permissions = aws.iam.get_policy_document(statements=[{
    "actions": ["bedrock:InvokeModel"],
    "resources": [f"arn:{current_get_partition.partition}:bedrock:{current_get_region.name}::foundation-model/anthropic.claude-v2"],
}])
example = aws.iam.Role("example",
    assume_role_policy=example_agent_trust.json,
    name_prefix="AmazonBedrockExecutionRoleForAgents_")
example_role_policy = aws.iam.RolePolicy("example",
    policy=example_agent_permissions.json,
    role=example.id)
example_agent_agent = aws.bedrock.AgentAgent("example",
    agent_name="my-agent-name",
    agent_resource_role_arn=example.arn,
    idle_session_ttl_in_seconds=500,
    foundation_model="anthropic.claude-v2")
Copy
package main

import (
	"fmt"

	"github.com/pulumi/pulumi-aws/sdk/v6/go/aws"
	"github.com/pulumi/pulumi-aws/sdk/v6/go/aws/bedrock"
	"github.com/pulumi/pulumi-aws/sdk/v6/go/aws/iam"
	"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)
func main() {
pulumi.Run(func(ctx *pulumi.Context) error {
current, err := aws.GetCallerIdentity(ctx, &aws.GetCallerIdentityArgs{
}, nil);
if err != nil {
return err
}
currentGetPartition, err := aws.GetPartition(ctx, &aws.GetPartitionArgs{
}, nil);
if err != nil {
return err
}
currentGetRegion, err := aws.GetRegion(ctx, &aws.GetRegionArgs{
}, nil);
if err != nil {
return err
}
exampleAgentTrust, err := iam.GetPolicyDocument(ctx, &iam.GetPolicyDocumentArgs{
Statements: []iam.GetPolicyDocumentStatement{
{
Actions: []string{
"sts:AssumeRole",
},
Principals: []iam.GetPolicyDocumentStatementPrincipal{
{
Identifiers: []string{
"bedrock.amazonaws.com",
},
Type: "Service",
},
},
Conditions: []iam.GetPolicyDocumentStatementCondition{
{
Test: "StringEquals",
Values: interface{}{
current.AccountId,
},
Variable: "aws:SourceAccount",
},
{
Test: "ArnLike",
Values: []string{
fmt.Sprintf("arn:%v:bedrock:%v:%v:agent/*", currentGetPartition.Partition, currentGetRegion.Name, current.AccountId),
},
Variable: "AWS:SourceArn",
},
},
},
},
}, nil);
if err != nil {
return err
}
exampleAgentPermissions, err := iam.GetPolicyDocument(ctx, &iam.GetPolicyDocumentArgs{
Statements: []iam.GetPolicyDocumentStatement{
{
Actions: []string{
"bedrock:InvokeModel",
},
Resources: []string{
fmt.Sprintf("arn:%v:bedrock:%v::foundation-model/anthropic.claude-v2", currentGetPartition.Partition, currentGetRegion.Name),
},
},
},
}, nil);
if err != nil {
return err
}
example, err := iam.NewRole(ctx, "example", &iam.RoleArgs{
AssumeRolePolicy: pulumi.String(exampleAgentTrust.Json),
NamePrefix: pulumi.String("AmazonBedrockExecutionRoleForAgents_"),
})
if err != nil {
return err
}
_, err = iam.NewRolePolicy(ctx, "example", &iam.RolePolicyArgs{
Policy: pulumi.String(exampleAgentPermissions.Json),
Role: example.ID(),
})
if err != nil {
return err
}
_, err = bedrock.NewAgentAgent(ctx, "example", &bedrock.AgentAgentArgs{
AgentName: pulumi.String("my-agent-name"),
AgentResourceRoleArn: example.Arn,
IdleSessionTtlInSeconds: pulumi.Int(500),
FoundationModel: pulumi.String("anthropic.claude-v2"),
})
if err != nil {
return err
}
return nil
})
}
Copy
using System.Collections.Generic;
using System.Linq;
using Pulumi;
using Aws = Pulumi.Aws;

return await Deployment.RunAsync(() => 
{
    var current = Aws.GetCallerIdentity.Invoke();

    var currentGetPartition = Aws.GetPartition.Invoke();

    var currentGetRegion = Aws.GetRegion.Invoke();

    var exampleAgentTrust = Aws.Iam.GetPolicyDocument.Invoke(new()
    {
        Statements = new[]
        {
            new Aws.Iam.Inputs.GetPolicyDocumentStatementInputArgs
            {
                Actions = new[]
                {
                    "sts:AssumeRole",
                },
                Principals = new[]
                {
                    new Aws.Iam.Inputs.GetPolicyDocumentStatementPrincipalInputArgs
                    {
                        Identifiers = new[]
                        {
                            "bedrock.amazonaws.com",
                        },
                        Type = "Service",
                    },
                },
                Conditions = new[]
                {
                    new Aws.Iam.Inputs.GetPolicyDocumentStatementConditionInputArgs
                    {
                        Test = "StringEquals",
                        Values = new[]
                        {
                            current.Apply(getCallerIdentityResult => getCallerIdentityResult.AccountId),
                        },
                        Variable = "aws:SourceAccount",
                    },
                    new Aws.Iam.Inputs.GetPolicyDocumentStatementConditionInputArgs
                    {
                        Test = "ArnLike",
                        Values = new[]
                        {
                            $"arn:{currentGetPartition.Apply(getPartitionResult => getPartitionResult.Partition)}:bedrock:{currentGetRegion.Apply(getRegionResult => getRegionResult.Name)}:{current.Apply(getCallerIdentityResult => getCallerIdentityResult.AccountId)}:agent/*",
                        },
                        Variable = "AWS:SourceArn",
                    },
                },
            },
        },
    });

    var exampleAgentPermissions = Aws.Iam.GetPolicyDocument.Invoke(new()
    {
        Statements = new[]
        {
            new Aws.Iam.Inputs.GetPolicyDocumentStatementInputArgs
            {
                Actions = new[]
                {
                    "bedrock:InvokeModel",
                },
                Resources = new[]
                {
                    $"arn:{currentGetPartition.Apply(getPartitionResult => getPartitionResult.Partition)}:bedrock:{currentGetRegion.Apply(getRegionResult => getRegionResult.Name)}::foundation-model/anthropic.claude-v2",
                },
            },
        },
    });

    var example = new Aws.Iam.Role("example", new()
    {
        AssumeRolePolicy = exampleAgentTrust.Apply(getPolicyDocumentResult => getPolicyDocumentResult.Json),
        NamePrefix = "AmazonBedrockExecutionRoleForAgents_",
    });

    var exampleRolePolicy = new Aws.Iam.RolePolicy("example", new()
    {
        Policy = exampleAgentPermissions.Apply(getPolicyDocumentResult => getPolicyDocumentResult.Json),
        Role = example.Id,
    });

    var exampleAgentAgent = new Aws.Bedrock.AgentAgent("example", new()
    {
        AgentName = "my-agent-name",
        AgentResourceRoleArn = example.Arn,
        IdleSessionTtlInSeconds = 500,
        FoundationModel = "anthropic.claude-v2",
    });

});
Copy
package generated_program;

import com.pulumi.Context;
import com.pulumi.Pulumi;
import com.pulumi.core.Output;
import com.pulumi.aws.AwsFunctions;
import com.pulumi.aws.inputs.GetCallerIdentityArgs;
import com.pulumi.aws.inputs.GetPartitionArgs;
import com.pulumi.aws.inputs.GetRegionArgs;
import com.pulumi.aws.iam.IamFunctions;
import com.pulumi.aws.iam.inputs.GetPolicyDocumentArgs;
import com.pulumi.aws.iam.Role;
import com.pulumi.aws.iam.RoleArgs;
import com.pulumi.aws.iam.RolePolicy;
import com.pulumi.aws.iam.RolePolicyArgs;
import com.pulumi.aws.bedrock.AgentAgent;
import com.pulumi.aws.bedrock.AgentAgentArgs;
import java.util.List;
import java.util.ArrayList;
import java.util.Map;
import java.io.File;
import java.nio.file.Files;
import java.nio.file.Paths;

public class App {
    public static void main(String[] args) {
        Pulumi.run(App::stack);
    }

    public static void stack(Context ctx) {
        final var current = AwsFunctions.getCallerIdentity();

        final var currentGetPartition = AwsFunctions.getPartition();

        final var currentGetRegion = AwsFunctions.getRegion();

        final var exampleAgentTrust = IamFunctions.getPolicyDocument(GetPolicyDocumentArgs.builder()
            .statements(GetPolicyDocumentStatementArgs.builder()
                .actions("sts:AssumeRole")
                .principals(GetPolicyDocumentStatementPrincipalArgs.builder()
                    .identifiers("bedrock.amazonaws.com")
                    .type("Service")
                    .build())
                .conditions(                
                    GetPolicyDocumentStatementConditionArgs.builder()
                        .test("StringEquals")
                        .values(current.applyValue(getCallerIdentityResult -> getCallerIdentityResult.accountId()))
                        .variable("aws:SourceAccount")
                        .build(),
                    GetPolicyDocumentStatementConditionArgs.builder()
                        .test("ArnLike")
                        .values(String.format("arn:%s:bedrock:%s:%s:agent/*", currentGetPartition.applyValue(getPartitionResult -> getPartitionResult.partition()),currentGetRegion.applyValue(getRegionResult -> getRegionResult.name()),current.applyValue(getCallerIdentityResult -> getCallerIdentityResult.accountId())))
                        .variable("AWS:SourceArn")
                        .build())
                .build())
            .build());

        final var exampleAgentPermissions = IamFunctions.getPolicyDocument(GetPolicyDocumentArgs.builder()
            .statements(GetPolicyDocumentStatementArgs.builder()
                .actions("bedrock:InvokeModel")
                .resources(String.format("arn:%s:bedrock:%s::foundation-model/anthropic.claude-v2", currentGetPartition.applyValue(getPartitionResult -> getPartitionResult.partition()),currentGetRegion.applyValue(getRegionResult -> getRegionResult.name())))
                .build())
            .build());

        var example = new Role("example", RoleArgs.builder()
            .assumeRolePolicy(exampleAgentTrust.applyValue(getPolicyDocumentResult -> getPolicyDocumentResult.json()))
            .namePrefix("AmazonBedrockExecutionRoleForAgents_")
            .build());

        var exampleRolePolicy = new RolePolicy("exampleRolePolicy", RolePolicyArgs.builder()
            .policy(exampleAgentPermissions.applyValue(getPolicyDocumentResult -> getPolicyDocumentResult.json()))
            .role(example.id())
            .build());

        var exampleAgentAgent = new AgentAgent("exampleAgentAgent", AgentAgentArgs.builder()
            .agentName("my-agent-name")
            .agentResourceRoleArn(example.arn())
            .idleSessionTtlInSeconds(500)
            .foundationModel("anthropic.claude-v2")
            .build());

    }
}
Copy
resources:
  example:
    type: aws:iam:Role
    properties:
      assumeRolePolicy: ${exampleAgentTrust.json}
      namePrefix: AmazonBedrockExecutionRoleForAgents_
  exampleRolePolicy:
    type: aws:iam:RolePolicy
    name: example
    properties:
      policy: ${exampleAgentPermissions.json}
      role: ${example.id}
  exampleAgentAgent:
    type: aws:bedrock:AgentAgent
    name: example
    properties:
      agentName: my-agent-name
      agentResourceRoleArn: ${example.arn}
      idleSessionTtlInSeconds: 500
      foundationModel: anthropic.claude-v2
variables:
  current:
    fn::invoke:
      function: aws:getCallerIdentity
      arguments: {}
  currentGetPartition:
    fn::invoke:
      function: aws:getPartition
      arguments: {}
  currentGetRegion:
    fn::invoke:
      function: aws:getRegion
      arguments: {}
  exampleAgentTrust:
    fn::invoke:
      function: aws:iam:getPolicyDocument
      arguments:
        statements:
          - actions:
              - sts:AssumeRole
            principals:
              - identifiers:
                  - bedrock.amazonaws.com
                type: Service
            conditions:
              - test: StringEquals
                values:
                  - ${current.accountId}
                variable: aws:SourceAccount
              - test: ArnLike
                values:
                  - arn:${currentGetPartition.partition}:bedrock:${currentGetRegion.name}:${current.accountId}:agent/*
                variable: AWS:SourceArn
  exampleAgentPermissions:
    fn::invoke:
      function: aws:iam:getPolicyDocument
      arguments:
        statements:
          - actions:
              - bedrock:InvokeModel
            resources:
              - arn:${currentGetPartition.partition}:bedrock:${currentGetRegion.name}::foundation-model/anthropic.claude-v2
Copy

Create AgentAgent Resource

Resources are created with functions called constructors. To learn more about declaring and configuring resources, see Resources.

Constructor syntax

new AgentAgent(name: string, args: AgentAgentArgs, opts?: CustomResourceOptions);
@overload
def AgentAgent(resource_name: str,
               args: AgentAgentArgs,
               opts: Optional[ResourceOptions] = None)

@overload
def AgentAgent(resource_name: str,
               opts: Optional[ResourceOptions] = None,
               foundation_model: Optional[str] = None,
               agent_name: Optional[str] = None,
               agent_resource_role_arn: Optional[str] = None,
               guardrail_configurations: Optional[Sequence[AgentAgentGuardrailConfigurationArgs]] = None,
               description: Optional[str] = None,
               customer_encryption_key_arn: Optional[str] = None,
               agent_collaboration: Optional[str] = None,
               idle_session_ttl_in_seconds: Optional[int] = None,
               instruction: Optional[str] = None,
               memory_configurations: Optional[Sequence[AgentAgentMemoryConfigurationArgs]] = None,
               prepare_agent: Optional[bool] = None,
               prompt_override_configurations: Optional[Sequence[AgentAgentPromptOverrideConfigurationArgs]] = None,
               skip_resource_in_use_check: Optional[bool] = None,
               tags: Optional[Mapping[str, str]] = None,
               timeouts: Optional[AgentAgentTimeoutsArgs] = None)
func NewAgentAgent(ctx *Context, name string, args AgentAgentArgs, opts ...ResourceOption) (*AgentAgent, error)
public AgentAgent(string name, AgentAgentArgs args, CustomResourceOptions? opts = null)
public AgentAgent(String name, AgentAgentArgs args)
public AgentAgent(String name, AgentAgentArgs args, CustomResourceOptions options)

type: aws:bedrock:AgentAgent
properties: # The arguments to resource properties.
options: # Bag of options to control resource's behavior.

Parameters

name This property is required. string
The unique name of the resource.
args This property is required. AgentAgentArgs
The arguments to resource properties.
opts CustomResourceOptions
Bag of options to control resource's behavior.
resource_name This property is required. str
The unique name of the resource.
args This property is required. AgentAgentArgs
The arguments to resource properties.
opts ResourceOptions
Bag of options to control resource's behavior.
ctx Context
Context object for the current deployment.
name This property is required. string
The unique name of the resource.
args This property is required. AgentAgentArgs
The arguments to resource properties.
opts ResourceOption
Bag of options to control resource's behavior.
name This property is required. string
The unique name of the resource.
args This property is required. AgentAgentArgs
The arguments to resource properties.
opts CustomResourceOptions
Bag of options to control resource's behavior.
name This property is required. String
The unique name of the resource.
args This property is required. AgentAgentArgs
The arguments to resource properties.
options CustomResourceOptions
Bag of options to control resource's behavior.

Constructor example

The following reference example uses placeholder values for all input properties.

var agentAgentResource = new Aws.Bedrock.AgentAgent("agentAgentResource", new()
{
    FoundationModel = "string",
    AgentName = "string",
    AgentResourceRoleArn = "string",
    GuardrailConfigurations = new[]
    {
        new Aws.Bedrock.Inputs.AgentAgentGuardrailConfigurationArgs
        {
            GuardrailIdentifier = "string",
            GuardrailVersion = "string",
        },
    },
    Description = "string",
    CustomerEncryptionKeyArn = "string",
    AgentCollaboration = "string",
    IdleSessionTtlInSeconds = 0,
    Instruction = "string",
    MemoryConfigurations = new[]
    {
        new Aws.Bedrock.Inputs.AgentAgentMemoryConfigurationArgs
        {
            EnabledMemoryTypes = new[]
            {
                "string",
            },
            StorageDays = 0,
        },
    },
    PrepareAgent = false,
    PromptOverrideConfigurations = new[]
    {
        new Aws.Bedrock.Inputs.AgentAgentPromptOverrideConfigurationArgs
        {
            OverrideLambda = "string",
            PromptConfigurations = new[]
            {
                new Aws.Bedrock.Inputs.AgentAgentPromptOverrideConfigurationPromptConfigurationArgs
                {
                    BasePromptTemplate = "string",
                    InferenceConfigurations = new[]
                    {
                        new Aws.Bedrock.Inputs.AgentAgentPromptOverrideConfigurationPromptConfigurationInferenceConfigurationArgs
                        {
                            MaxLength = 0,
                            StopSequences = new[]
                            {
                                "string",
                            },
                            Temperature = 0,
                            TopK = 0,
                            TopP = 0,
                        },
                    },
                    ParserMode = "string",
                    PromptCreationMode = "string",
                    PromptState = "string",
                    PromptType = "string",
                },
            },
        },
    },
    SkipResourceInUseCheck = false,
    Tags = 
    {
        { "string", "string" },
    },
    Timeouts = new Aws.Bedrock.Inputs.AgentAgentTimeoutsArgs
    {
        Create = "string",
        Delete = "string",
        Update = "string",
    },
});
Copy
example, err := bedrock.NewAgentAgent(ctx, "agentAgentResource", &bedrock.AgentAgentArgs{
	FoundationModel:      pulumi.String("string"),
	AgentName:            pulumi.String("string"),
	AgentResourceRoleArn: pulumi.String("string"),
	GuardrailConfigurations: bedrock.AgentAgentGuardrailConfigurationArray{
		&bedrock.AgentAgentGuardrailConfigurationArgs{
			GuardrailIdentifier: pulumi.String("string"),
			GuardrailVersion:    pulumi.String("string"),
		},
	},
	Description:              pulumi.String("string"),
	CustomerEncryptionKeyArn: pulumi.String("string"),
	AgentCollaboration:       pulumi.String("string"),
	IdleSessionTtlInSeconds:  pulumi.Int(0),
	Instruction:              pulumi.String("string"),
	MemoryConfigurations: bedrock.AgentAgentMemoryConfigurationArray{
		&bedrock.AgentAgentMemoryConfigurationArgs{
			EnabledMemoryTypes: pulumi.StringArray{
				pulumi.String("string"),
			},
			StorageDays: pulumi.Int(0),
		},
	},
	PrepareAgent: pulumi.Bool(false),
	PromptOverrideConfigurations: bedrock.AgentAgentPromptOverrideConfigurationArray{
		&bedrock.AgentAgentPromptOverrideConfigurationArgs{
			OverrideLambda: pulumi.String("string"),
			PromptConfigurations: bedrock.AgentAgentPromptOverrideConfigurationPromptConfigurationArray{
				&bedrock.AgentAgentPromptOverrideConfigurationPromptConfigurationArgs{
					BasePromptTemplate: pulumi.String("string"),
					InferenceConfigurations: bedrock.AgentAgentPromptOverrideConfigurationPromptConfigurationInferenceConfigurationArray{
						&bedrock.AgentAgentPromptOverrideConfigurationPromptConfigurationInferenceConfigurationArgs{
							MaxLength: pulumi.Int(0),
							StopSequences: pulumi.StringArray{
								pulumi.String("string"),
							},
							Temperature: pulumi.Float64(0),
							TopK:        pulumi.Int(0),
							TopP:        pulumi.Float64(0),
						},
					},
					ParserMode:         pulumi.String("string"),
					PromptCreationMode: pulumi.String("string"),
					PromptState:        pulumi.String("string"),
					PromptType:         pulumi.String("string"),
				},
			},
		},
	},
	SkipResourceInUseCheck: pulumi.Bool(false),
	Tags: pulumi.StringMap{
		"string": pulumi.String("string"),
	},
	Timeouts: &bedrock.AgentAgentTimeoutsArgs{
		Create: pulumi.String("string"),
		Delete: pulumi.String("string"),
		Update: pulumi.String("string"),
	},
})
Copy
var agentAgentResource = new AgentAgent("agentAgentResource", AgentAgentArgs.builder()
    .foundationModel("string")
    .agentName("string")
    .agentResourceRoleArn("string")
    .guardrailConfigurations(AgentAgentGuardrailConfigurationArgs.builder()
        .guardrailIdentifier("string")
        .guardrailVersion("string")
        .build())
    .description("string")
    .customerEncryptionKeyArn("string")
    .agentCollaboration("string")
    .idleSessionTtlInSeconds(0)
    .instruction("string")
    .memoryConfigurations(AgentAgentMemoryConfigurationArgs.builder()
        .enabledMemoryTypes("string")
        .storageDays(0)
        .build())
    .prepareAgent(false)
    .promptOverrideConfigurations(AgentAgentPromptOverrideConfigurationArgs.builder()
        .overrideLambda("string")
        .promptConfigurations(AgentAgentPromptOverrideConfigurationPromptConfigurationArgs.builder()
            .basePromptTemplate("string")
            .inferenceConfigurations(AgentAgentPromptOverrideConfigurationPromptConfigurationInferenceConfigurationArgs.builder()
                .maxLength(0)
                .stopSequences("string")
                .temperature(0)
                .topK(0)
                .topP(0)
                .build())
            .parserMode("string")
            .promptCreationMode("string")
            .promptState("string")
            .promptType("string")
            .build())
        .build())
    .skipResourceInUseCheck(false)
    .tags(Map.of("string", "string"))
    .timeouts(AgentAgentTimeoutsArgs.builder()
        .create("string")
        .delete("string")
        .update("string")
        .build())
    .build());
Copy
agent_agent_resource = aws.bedrock.AgentAgent("agentAgentResource",
    foundation_model="string",
    agent_name="string",
    agent_resource_role_arn="string",
    guardrail_configurations=[{
        "guardrail_identifier": "string",
        "guardrail_version": "string",
    }],
    description="string",
    customer_encryption_key_arn="string",
    agent_collaboration="string",
    idle_session_ttl_in_seconds=0,
    instruction="string",
    memory_configurations=[{
        "enabled_memory_types": ["string"],
        "storage_days": 0,
    }],
    prepare_agent=False,
    prompt_override_configurations=[{
        "override_lambda": "string",
        "prompt_configurations": [{
            "base_prompt_template": "string",
            "inference_configurations": [{
                "max_length": 0,
                "stop_sequences": ["string"],
                "temperature": 0,
                "top_k": 0,
                "top_p": 0,
            }],
            "parser_mode": "string",
            "prompt_creation_mode": "string",
            "prompt_state": "string",
            "prompt_type": "string",
        }],
    }],
    skip_resource_in_use_check=False,
    tags={
        "string": "string",
    },
    timeouts={
        "create": "string",
        "delete": "string",
        "update": "string",
    })
Copy
const agentAgentResource = new aws.bedrock.AgentAgent("agentAgentResource", {
    foundationModel: "string",
    agentName: "string",
    agentResourceRoleArn: "string",
    guardrailConfigurations: [{
        guardrailIdentifier: "string",
        guardrailVersion: "string",
    }],
    description: "string",
    customerEncryptionKeyArn: "string",
    agentCollaboration: "string",
    idleSessionTtlInSeconds: 0,
    instruction: "string",
    memoryConfigurations: [{
        enabledMemoryTypes: ["string"],
        storageDays: 0,
    }],
    prepareAgent: false,
    promptOverrideConfigurations: [{
        overrideLambda: "string",
        promptConfigurations: [{
            basePromptTemplate: "string",
            inferenceConfigurations: [{
                maxLength: 0,
                stopSequences: ["string"],
                temperature: 0,
                topK: 0,
                topP: 0,
            }],
            parserMode: "string",
            promptCreationMode: "string",
            promptState: "string",
            promptType: "string",
        }],
    }],
    skipResourceInUseCheck: false,
    tags: {
        string: "string",
    },
    timeouts: {
        create: "string",
        "delete": "string",
        update: "string",
    },
});
Copy
type: aws:bedrock:AgentAgent
properties:
    agentCollaboration: string
    agentName: string
    agentResourceRoleArn: string
    customerEncryptionKeyArn: string
    description: string
    foundationModel: string
    guardrailConfigurations:
        - guardrailIdentifier: string
          guardrailVersion: string
    idleSessionTtlInSeconds: 0
    instruction: string
    memoryConfigurations:
        - enabledMemoryTypes:
            - string
          storageDays: 0
    prepareAgent: false
    promptOverrideConfigurations:
        - overrideLambda: string
          promptConfigurations:
            - basePromptTemplate: string
              inferenceConfigurations:
                - maxLength: 0
                  stopSequences:
                    - string
                  temperature: 0
                  topK: 0
                  topP: 0
              parserMode: string
              promptCreationMode: string
              promptState: string
              promptType: string
    skipResourceInUseCheck: false
    tags:
        string: string
    timeouts:
        create: string
        delete: string
        update: string
Copy

AgentAgent Resource Properties

To learn more about resource properties and how to use them, see Inputs and Outputs in the Architecture and Concepts docs.

Inputs

In Python, inputs that are objects can be passed either as argument classes or as dictionary literals.

The AgentAgent resource accepts the following input properties:

AgentName This property is required. string
Name of the agent.
AgentResourceRoleArn This property is required. string
ARN of the IAM role with permissions to invoke API operations on the agent.
FoundationModel This property is required. string

Foundation model used for orchestration by the agent.

The following arguments are optional:

AgentCollaboration string
Agents collaboration role. Valid values: SUPERVISOR, SUPERVISOR_ROUTER, DISABLED.
CustomerEncryptionKeyArn string
ARN of the AWS KMS key that encrypts the agent.
Description string
Description of the agent.
GuardrailConfigurations List<AgentAgentGuardrailConfiguration>
Details about the guardrail associated with the agent. See guardrail_configuration Block for details.
IdleSessionTtlInSeconds int
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 string
Instructions that tell the agent what it should do and how it should interact with users. The valid range is 40 - 8000 characters.
MemoryConfigurations List<AgentAgentMemoryConfiguration>
Configurations for the agent's ability to retain the conversational context.
PrepareAgent bool
Whether to prepare the agent after creation or modification. Defaults to true.
PromptOverrideConfigurations List<AgentAgentPromptOverrideConfiguration>
Configurations to override prompt templates in different parts of an agent sequence. For more information, see Advanced prompts. See prompt_override_configuration Block for details.
SkipResourceInUseCheck bool
Whether the in-use check is skipped when deleting the agent.
Tags Dictionary<string, string>
Map of tags assigned to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
Timeouts AgentAgentTimeouts
AgentName This property is required. string
Name of the agent.
AgentResourceRoleArn This property is required. string
ARN of the IAM role with permissions to invoke API operations on the agent.
FoundationModel This property is required. string

Foundation model used for orchestration by the agent.

The following arguments are optional:

AgentCollaboration string
Agents collaboration role. Valid values: SUPERVISOR, SUPERVISOR_ROUTER, DISABLED.
CustomerEncryptionKeyArn string
ARN of the AWS KMS key that encrypts the agent.
Description string
Description of the agent.
GuardrailConfigurations []AgentAgentGuardrailConfigurationArgs
Details about the guardrail associated with the agent. See guardrail_configuration Block for details.
IdleSessionTtlInSeconds int
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 string
Instructions that tell the agent what it should do and how it should interact with users. The valid range is 40 - 8000 characters.
MemoryConfigurations []AgentAgentMemoryConfigurationArgs
Configurations for the agent's ability to retain the conversational context.
PrepareAgent bool
Whether to prepare the agent after creation or modification. Defaults to true.
PromptOverrideConfigurations []AgentAgentPromptOverrideConfigurationArgs
Configurations to override prompt templates in different parts of an agent sequence. For more information, see Advanced prompts. See prompt_override_configuration Block for details.
SkipResourceInUseCheck bool
Whether the in-use check is skipped when deleting the agent.
Tags map[string]string
Map of tags assigned to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
Timeouts AgentAgentTimeoutsArgs
agentName This property is required. String
Name of the agent.
agentResourceRoleArn This property is required. String
ARN of the IAM role with permissions to invoke API operations on the agent.
foundationModel This property is required. String

Foundation model used for orchestration by the agent.

The following arguments are optional:

agentCollaboration String
Agents collaboration role. Valid values: SUPERVISOR, SUPERVISOR_ROUTER, DISABLED.
customerEncryptionKeyArn String
ARN of the AWS KMS key that encrypts the agent.
description String
Description of the agent.
guardrailConfigurations List<AgentAgentGuardrailConfiguration>
Details about the guardrail associated with the agent. See guardrail_configuration Block for details.
idleSessionTtlInSeconds Integer
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 String
Instructions that tell the agent what it should do and how it should interact with users. The valid range is 40 - 8000 characters.
memoryConfigurations List<AgentAgentMemoryConfiguration>
Configurations for the agent's ability to retain the conversational context.
prepareAgent Boolean
Whether to prepare the agent after creation or modification. Defaults to true.
promptOverrideConfigurations List<AgentAgentPromptOverrideConfiguration>
Configurations to override prompt templates in different parts of an agent sequence. For more information, see Advanced prompts. See prompt_override_configuration Block for details.
skipResourceInUseCheck Boolean
Whether the in-use check is skipped when deleting the agent.
tags Map<String,String>
Map of tags assigned to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
timeouts AgentAgentTimeouts
agentName This property is required. string
Name of the agent.
agentResourceRoleArn This property is required. string
ARN of the IAM role with permissions to invoke API operations on the agent.
foundationModel This property is required. string

Foundation model used for orchestration by the agent.

The following arguments are optional:

agentCollaboration string
Agents collaboration role. Valid values: SUPERVISOR, SUPERVISOR_ROUTER, DISABLED.
customerEncryptionKeyArn string
ARN of the AWS KMS key that encrypts the agent.
description string
Description of the agent.
guardrailConfigurations AgentAgentGuardrailConfiguration[]
Details about the guardrail associated with the agent. See guardrail_configuration Block for details.
idleSessionTtlInSeconds number
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 string
Instructions that tell the agent what it should do and how it should interact with users. The valid range is 40 - 8000 characters.
memoryConfigurations AgentAgentMemoryConfiguration[]
Configurations for the agent's ability to retain the conversational context.
prepareAgent boolean
Whether to prepare the agent after creation or modification. Defaults to true.
promptOverrideConfigurations AgentAgentPromptOverrideConfiguration[]
Configurations to override prompt templates in different parts of an agent sequence. For more information, see Advanced prompts. See prompt_override_configuration Block for details.
skipResourceInUseCheck boolean
Whether the in-use check is skipped when deleting the agent.
tags {[key: string]: string}
Map of tags assigned to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
timeouts AgentAgentTimeouts
agent_name This property is required. str
Name of the agent.
agent_resource_role_arn This property is required. str
ARN of the IAM role with permissions to invoke API operations on the agent.
foundation_model This property is required. str

Foundation model used for orchestration by the agent.

The following arguments are optional:

agent_collaboration str
Agents collaboration role. Valid values: SUPERVISOR, SUPERVISOR_ROUTER, DISABLED.
customer_encryption_key_arn str
ARN of the AWS KMS key that encrypts the agent.
description str
Description of the agent.
guardrail_configurations Sequence[AgentAgentGuardrailConfigurationArgs]
Details about the guardrail associated with the agent. See guardrail_configuration Block for details.
idle_session_ttl_in_seconds int
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 str
Instructions that tell the agent what it should do and how it should interact with users. The valid range is 40 - 8000 characters.
memory_configurations Sequence[AgentAgentMemoryConfigurationArgs]
Configurations for the agent's ability to retain the conversational context.
prepare_agent bool
Whether to prepare the agent after creation or modification. Defaults to true.
prompt_override_configurations Sequence[AgentAgentPromptOverrideConfigurationArgs]
Configurations to override prompt templates in different parts of an agent sequence. For more information, see Advanced prompts. See prompt_override_configuration Block for details.
skip_resource_in_use_check bool
Whether the in-use check is skipped when deleting the agent.
tags Mapping[str, str]
Map of tags assigned to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
timeouts AgentAgentTimeoutsArgs
agentName This property is required. String
Name of the agent.
agentResourceRoleArn This property is required. String
ARN of the IAM role with permissions to invoke API operations on the agent.
foundationModel This property is required. String

Foundation model used for orchestration by the agent.

The following arguments are optional:

agentCollaboration String
Agents collaboration role. Valid values: SUPERVISOR, SUPERVISOR_ROUTER, DISABLED.
customerEncryptionKeyArn String
ARN of the AWS KMS key that encrypts the agent.
description String
Description of the agent.
guardrailConfigurations List<Property Map>
Details about the guardrail associated with the agent. See guardrail_configuration Block for details.
idleSessionTtlInSeconds Number
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 String
Instructions that tell the agent what it should do and how it should interact with users. The valid range is 40 - 8000 characters.
memoryConfigurations List<Property Map>
Configurations for the agent's ability to retain the conversational context.
prepareAgent Boolean
Whether to prepare the agent after creation or modification. Defaults to true.
promptOverrideConfigurations List<Property Map>
Configurations to override prompt templates in different parts of an agent sequence. For more information, see Advanced prompts. See prompt_override_configuration Block for details.
skipResourceInUseCheck Boolean
Whether the in-use check is skipped when deleting the agent.
tags Map<String>
Map of tags assigned to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
timeouts Property Map

Outputs

All input properties are implicitly available as output properties. Additionally, the AgentAgent resource produces the following output properties:

AgentArn string
ARN of the agent.
AgentId string
Unique identifier of the agent.
AgentVersion string
Version of the agent.
Id string
The provider-assigned unique ID for this managed resource.
TagsAll Dictionary<string, string>
Map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

Deprecated: Please use tags instead.

AgentArn string
ARN of the agent.
AgentId string
Unique identifier of the agent.
AgentVersion string
Version of the agent.
Id string
The provider-assigned unique ID for this managed resource.
TagsAll map[string]string
Map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

Deprecated: Please use tags instead.

agentArn String
ARN of the agent.
agentId String
Unique identifier of the agent.
agentVersion String
Version of the agent.
id String
The provider-assigned unique ID for this managed resource.
tagsAll Map<String,String>
Map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

Deprecated: Please use tags instead.

agentArn string
ARN of the agent.
agentId string
Unique identifier of the agent.
agentVersion string
Version of the agent.
id string
The provider-assigned unique ID for this managed resource.
tagsAll {[key: string]: string}
Map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

Deprecated: Please use tags instead.

agent_arn str
ARN of the agent.
agent_id str
Unique identifier of the agent.
agent_version str
Version of the agent.
id str
The provider-assigned unique ID for this managed resource.
tags_all Mapping[str, str]
Map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

Deprecated: Please use tags instead.

agentArn String
ARN of the agent.
agentId String
Unique identifier of the agent.
agentVersion String
Version of the agent.
id String
The provider-assigned unique ID for this managed resource.
tagsAll Map<String>
Map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

Deprecated: Please use tags instead.

Look up Existing AgentAgent Resource

Get an existing AgentAgent resource’s state with the given name, ID, and optional extra properties used to qualify the lookup.

public static get(name: string, id: Input<ID>, state?: AgentAgentState, opts?: CustomResourceOptions): AgentAgent
@staticmethod
def get(resource_name: str,
        id: str,
        opts: Optional[ResourceOptions] = None,
        agent_arn: Optional[str] = None,
        agent_collaboration: Optional[str] = None,
        agent_id: Optional[str] = None,
        agent_name: Optional[str] = None,
        agent_resource_role_arn: Optional[str] = None,
        agent_version: Optional[str] = None,
        customer_encryption_key_arn: Optional[str] = None,
        description: Optional[str] = None,
        foundation_model: Optional[str] = None,
        guardrail_configurations: Optional[Sequence[AgentAgentGuardrailConfigurationArgs]] = None,
        idle_session_ttl_in_seconds: Optional[int] = None,
        instruction: Optional[str] = None,
        memory_configurations: Optional[Sequence[AgentAgentMemoryConfigurationArgs]] = None,
        prepare_agent: Optional[bool] = None,
        prompt_override_configurations: Optional[Sequence[AgentAgentPromptOverrideConfigurationArgs]] = None,
        skip_resource_in_use_check: Optional[bool] = None,
        tags: Optional[Mapping[str, str]] = None,
        tags_all: Optional[Mapping[str, str]] = None,
        timeouts: Optional[AgentAgentTimeoutsArgs] = None) -> AgentAgent
func GetAgentAgent(ctx *Context, name string, id IDInput, state *AgentAgentState, opts ...ResourceOption) (*AgentAgent, error)
public static AgentAgent Get(string name, Input<string> id, AgentAgentState? state, CustomResourceOptions? opts = null)
public static AgentAgent get(String name, Output<String> id, AgentAgentState state, CustomResourceOptions options)
resources:  _:    type: aws:bedrock:AgentAgent    get:      id: ${id}
name This property is required.
The unique name of the resulting resource.
id This property is required.
The unique provider ID of the resource to lookup.
state
Any extra arguments used during the lookup.
opts
A bag of options that control this resource's behavior.
resource_name This property is required.
The unique name of the resulting resource.
id This property is required.
The unique provider ID of the resource to lookup.
name This property is required.
The unique name of the resulting resource.
id This property is required.
The unique provider ID of the resource to lookup.
state
Any extra arguments used during the lookup.
opts
A bag of options that control this resource's behavior.
name This property is required.
The unique name of the resulting resource.
id This property is required.
The unique provider ID of the resource to lookup.
state
Any extra arguments used during the lookup.
opts
A bag of options that control this resource's behavior.
name This property is required.
The unique name of the resulting resource.
id This property is required.
The unique provider ID of the resource to lookup.
state
Any extra arguments used during the lookup.
opts
A bag of options that control this resource's behavior.
The following state arguments are supported:
AgentArn string
ARN of the agent.
AgentCollaboration string
Agents collaboration role. Valid values: SUPERVISOR, SUPERVISOR_ROUTER, DISABLED.
AgentId string
Unique identifier of the agent.
AgentName string
Name of the agent.
AgentResourceRoleArn string
ARN of the IAM role with permissions to invoke API operations on the agent.
AgentVersion string
Version of the agent.
CustomerEncryptionKeyArn string
ARN of the AWS KMS key that encrypts the agent.
Description string
Description of the agent.
FoundationModel string

Foundation model used for orchestration by the agent.

The following arguments are optional:

GuardrailConfigurations List<AgentAgentGuardrailConfiguration>
Details about the guardrail associated with the agent. See guardrail_configuration Block for details.
IdleSessionTtlInSeconds int
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 string
Instructions that tell the agent what it should do and how it should interact with users. The valid range is 40 - 8000 characters.
MemoryConfigurations List<AgentAgentMemoryConfiguration>
Configurations for the agent's ability to retain the conversational context.
PrepareAgent bool
Whether to prepare the agent after creation or modification. Defaults to true.
PromptOverrideConfigurations List<AgentAgentPromptOverrideConfiguration>
Configurations to override prompt templates in different parts of an agent sequence. For more information, see Advanced prompts. See prompt_override_configuration Block for details.
SkipResourceInUseCheck bool
Whether the in-use check is skipped when deleting the agent.
Tags Dictionary<string, string>
Map of tags assigned to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
TagsAll Dictionary<string, string>
Map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

Deprecated: Please use tags instead.

Timeouts AgentAgentTimeouts
AgentArn string
ARN of the agent.
AgentCollaboration string
Agents collaboration role. Valid values: SUPERVISOR, SUPERVISOR_ROUTER, DISABLED.
AgentId string
Unique identifier of the agent.
AgentName string
Name of the agent.
AgentResourceRoleArn string
ARN of the IAM role with permissions to invoke API operations on the agent.
AgentVersion string
Version of the agent.
CustomerEncryptionKeyArn string
ARN of the AWS KMS key that encrypts the agent.
Description string
Description of the agent.
FoundationModel string

Foundation model used for orchestration by the agent.

The following arguments are optional:

GuardrailConfigurations []AgentAgentGuardrailConfigurationArgs
Details about the guardrail associated with the agent. See guardrail_configuration Block for details.
IdleSessionTtlInSeconds int
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 string
Instructions that tell the agent what it should do and how it should interact with users. The valid range is 40 - 8000 characters.
MemoryConfigurations []AgentAgentMemoryConfigurationArgs
Configurations for the agent's ability to retain the conversational context.
PrepareAgent bool
Whether to prepare the agent after creation or modification. Defaults to true.
PromptOverrideConfigurations []AgentAgentPromptOverrideConfigurationArgs
Configurations to override prompt templates in different parts of an agent sequence. For more information, see Advanced prompts. See prompt_override_configuration Block for details.
SkipResourceInUseCheck bool
Whether the in-use check is skipped when deleting the agent.
Tags map[string]string
Map of tags assigned to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
TagsAll map[string]string
Map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

Deprecated: Please use tags instead.

Timeouts AgentAgentTimeoutsArgs
agentArn String
ARN of the agent.
agentCollaboration String
Agents collaboration role. Valid values: SUPERVISOR, SUPERVISOR_ROUTER, DISABLED.
agentId String
Unique identifier of the agent.
agentName String
Name of the agent.
agentResourceRoleArn String
ARN of the IAM role with permissions to invoke API operations on the agent.
agentVersion String
Version of the agent.
customerEncryptionKeyArn String
ARN of the AWS KMS key that encrypts the agent.
description String
Description of the agent.
foundationModel String

Foundation model used for orchestration by the agent.

The following arguments are optional:

guardrailConfigurations List<AgentAgentGuardrailConfiguration>
Details about the guardrail associated with the agent. See guardrail_configuration Block for details.
idleSessionTtlInSeconds Integer
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 String
Instructions that tell the agent what it should do and how it should interact with users. The valid range is 40 - 8000 characters.
memoryConfigurations List<AgentAgentMemoryConfiguration>
Configurations for the agent's ability to retain the conversational context.
prepareAgent Boolean
Whether to prepare the agent after creation or modification. Defaults to true.
promptOverrideConfigurations List<AgentAgentPromptOverrideConfiguration>
Configurations to override prompt templates in different parts of an agent sequence. For more information, see Advanced prompts. See prompt_override_configuration Block for details.
skipResourceInUseCheck Boolean
Whether the in-use check is skipped when deleting the agent.
tags Map<String,String>
Map of tags assigned to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
tagsAll Map<String,String>
Map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

Deprecated: Please use tags instead.

timeouts AgentAgentTimeouts
agentArn string
ARN of the agent.
agentCollaboration string
Agents collaboration role. Valid values: SUPERVISOR, SUPERVISOR_ROUTER, DISABLED.
agentId string
Unique identifier of the agent.
agentName string
Name of the agent.
agentResourceRoleArn string
ARN of the IAM role with permissions to invoke API operations on the agent.
agentVersion string
Version of the agent.
customerEncryptionKeyArn string
ARN of the AWS KMS key that encrypts the agent.
description string
Description of the agent.
foundationModel string

Foundation model used for orchestration by the agent.

The following arguments are optional:

guardrailConfigurations AgentAgentGuardrailConfiguration[]
Details about the guardrail associated with the agent. See guardrail_configuration Block for details.
idleSessionTtlInSeconds number
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 string
Instructions that tell the agent what it should do and how it should interact with users. The valid range is 40 - 8000 characters.
memoryConfigurations AgentAgentMemoryConfiguration[]
Configurations for the agent's ability to retain the conversational context.
prepareAgent boolean
Whether to prepare the agent after creation or modification. Defaults to true.
promptOverrideConfigurations AgentAgentPromptOverrideConfiguration[]
Configurations to override prompt templates in different parts of an agent sequence. For more information, see Advanced prompts. See prompt_override_configuration Block for details.
skipResourceInUseCheck boolean
Whether the in-use check is skipped when deleting the agent.
tags {[key: string]: string}
Map of tags assigned to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
tagsAll {[key: string]: string}
Map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

Deprecated: Please use tags instead.

timeouts AgentAgentTimeouts
agent_arn str
ARN of the agent.
agent_collaboration str
Agents collaboration role. Valid values: SUPERVISOR, SUPERVISOR_ROUTER, DISABLED.
agent_id str
Unique identifier of the agent.
agent_name str
Name of the agent.
agent_resource_role_arn str
ARN of the IAM role with permissions to invoke API operations on the agent.
agent_version str
Version of the agent.
customer_encryption_key_arn str
ARN of the AWS KMS key that encrypts the agent.
description str
Description of the agent.
foundation_model str

Foundation model used for orchestration by the agent.

The following arguments are optional:

guardrail_configurations Sequence[AgentAgentGuardrailConfigurationArgs]
Details about the guardrail associated with the agent. See guardrail_configuration Block for details.
idle_session_ttl_in_seconds int
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 str
Instructions that tell the agent what it should do and how it should interact with users. The valid range is 40 - 8000 characters.
memory_configurations Sequence[AgentAgentMemoryConfigurationArgs]
Configurations for the agent's ability to retain the conversational context.
prepare_agent bool
Whether to prepare the agent after creation or modification. Defaults to true.
prompt_override_configurations Sequence[AgentAgentPromptOverrideConfigurationArgs]
Configurations to override prompt templates in different parts of an agent sequence. For more information, see Advanced prompts. See prompt_override_configuration Block for details.
skip_resource_in_use_check bool
Whether the in-use check is skipped when deleting the agent.
tags Mapping[str, str]
Map of tags assigned to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
tags_all Mapping[str, str]
Map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

Deprecated: Please use tags instead.

timeouts AgentAgentTimeoutsArgs
agentArn String
ARN of the agent.
agentCollaboration String
Agents collaboration role. Valid values: SUPERVISOR, SUPERVISOR_ROUTER, DISABLED.
agentId String
Unique identifier of the agent.
agentName String
Name of the agent.
agentResourceRoleArn String
ARN of the IAM role with permissions to invoke API operations on the agent.
agentVersion String
Version of the agent.
customerEncryptionKeyArn String
ARN of the AWS KMS key that encrypts the agent.
description String
Description of the agent.
foundationModel String

Foundation model used for orchestration by the agent.

The following arguments are optional:

guardrailConfigurations List<Property Map>
Details about the guardrail associated with the agent. See guardrail_configuration Block for details.
idleSessionTtlInSeconds Number
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 String
Instructions that tell the agent what it should do and how it should interact with users. The valid range is 40 - 8000 characters.
memoryConfigurations List<Property Map>
Configurations for the agent's ability to retain the conversational context.
prepareAgent Boolean
Whether to prepare the agent after creation or modification. Defaults to true.
promptOverrideConfigurations List<Property Map>
Configurations to override prompt templates in different parts of an agent sequence. For more information, see Advanced prompts. See prompt_override_configuration Block for details.
skipResourceInUseCheck Boolean
Whether the in-use check is skipped when deleting the agent.
tags Map<String>
Map of tags assigned to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
tagsAll Map<String>
Map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

Deprecated: Please use tags instead.

timeouts Property Map

Supporting Types

AgentAgentGuardrailConfiguration
, AgentAgentGuardrailConfigurationArgs

GuardrailIdentifier This property is required. string
Unique identifier of the guardrail.
GuardrailVersion This property is required. string
Version of the guardrail.
GuardrailIdentifier This property is required. string
Unique identifier of the guardrail.
GuardrailVersion This property is required. string
Version of the guardrail.
guardrailIdentifier This property is required. String
Unique identifier of the guardrail.
guardrailVersion This property is required. String
Version of the guardrail.
guardrailIdentifier This property is required. string
Unique identifier of the guardrail.
guardrailVersion This property is required. string
Version of the guardrail.
guardrail_identifier This property is required. str
Unique identifier of the guardrail.
guardrail_version This property is required. str
Version of the guardrail.
guardrailIdentifier This property is required. String
Unique identifier of the guardrail.
guardrailVersion This property is required. String
Version of the guardrail.

AgentAgentMemoryConfiguration
, AgentAgentMemoryConfigurationArgs

EnabledMemoryTypes This property is required. List<string>
The type of memory being stored by the agent. See AWS API documentation for possible values.
StorageDays This property is required. int
The number of days the agent is configured to retain the conversational context. Minimum value of 0, maximum value of 30.
EnabledMemoryTypes This property is required. []string
The type of memory being stored by the agent. See AWS API documentation for possible values.
StorageDays This property is required. int
The number of days the agent is configured to retain the conversational context. Minimum value of 0, maximum value of 30.
enabledMemoryTypes This property is required. List<String>
The type of memory being stored by the agent. See AWS API documentation for possible values.
storageDays This property is required. Integer
The number of days the agent is configured to retain the conversational context. Minimum value of 0, maximum value of 30.
enabledMemoryTypes This property is required. string[]
The type of memory being stored by the agent. See AWS API documentation for possible values.
storageDays This property is required. number
The number of days the agent is configured to retain the conversational context. Minimum value of 0, maximum value of 30.
enabled_memory_types This property is required. Sequence[str]
The type of memory being stored by the agent. See AWS API documentation for possible values.
storage_days This property is required. int
The number of days the agent is configured to retain the conversational context. Minimum value of 0, maximum value of 30.
enabledMemoryTypes This property is required. List<String>
The type of memory being stored by the agent. See AWS API documentation for possible values.
storageDays This property is required. Number
The number of days the agent is configured to retain the conversational context. Minimum value of 0, maximum value of 30.

AgentAgentPromptOverrideConfiguration
, AgentAgentPromptOverrideConfigurationArgs

OverrideLambda This property is required. string
ARN of the Lambda function to use when parsing the raw foundation model output in parts of the agent sequence. If you specify this field, at least one of the prompt_configurations block must contain a parser_mode value that is set to OVERRIDDEN.
PromptConfigurations This property is required. List<AgentAgentPromptOverrideConfigurationPromptConfiguration>
Configurations to override a prompt template in one part of an agent sequence. See prompt_configurations Block for details.
OverrideLambda This property is required. string
ARN of the Lambda function to use when parsing the raw foundation model output in parts of the agent sequence. If you specify this field, at least one of the prompt_configurations block must contain a parser_mode value that is set to OVERRIDDEN.
PromptConfigurations This property is required. []AgentAgentPromptOverrideConfigurationPromptConfiguration
Configurations to override a prompt template in one part of an agent sequence. See prompt_configurations Block for details.
overrideLambda This property is required. String
ARN of the Lambda function to use when parsing the raw foundation model output in parts of the agent sequence. If you specify this field, at least one of the prompt_configurations block must contain a parser_mode value that is set to OVERRIDDEN.
promptConfigurations This property is required. List<AgentAgentPromptOverrideConfigurationPromptConfiguration>
Configurations to override a prompt template in one part of an agent sequence. See prompt_configurations Block for details.
overrideLambda This property is required. string
ARN of the Lambda function to use when parsing the raw foundation model output in parts of the agent sequence. If you specify this field, at least one of the prompt_configurations block must contain a parser_mode value that is set to OVERRIDDEN.
promptConfigurations This property is required. AgentAgentPromptOverrideConfigurationPromptConfiguration[]
Configurations to override a prompt template in one part of an agent sequence. See prompt_configurations Block for details.
override_lambda This property is required. str
ARN of the Lambda function to use when parsing the raw foundation model output in parts of the agent sequence. If you specify this field, at least one of the prompt_configurations block must contain a parser_mode value that is set to OVERRIDDEN.
prompt_configurations This property is required. Sequence[AgentAgentPromptOverrideConfigurationPromptConfiguration]
Configurations to override a prompt template in one part of an agent sequence. See prompt_configurations Block for details.
overrideLambda This property is required. String
ARN of the Lambda function to use when parsing the raw foundation model output in parts of the agent sequence. If you specify this field, at least one of the prompt_configurations block must contain a parser_mode value that is set to OVERRIDDEN.
promptConfigurations This property is required. List<Property Map>
Configurations to override a prompt template in one part of an agent sequence. See prompt_configurations Block for details.

AgentAgentPromptOverrideConfigurationPromptConfiguration
, AgentAgentPromptOverrideConfigurationPromptConfigurationArgs

BasePromptTemplate This property is required. string
prompt template with which to replace the default prompt template. You can use placeholder variables in the base prompt template to customize the prompt. For more information, see Prompt template placeholder variables.
InferenceConfigurations This property is required. List<AgentAgentPromptOverrideConfigurationPromptConfigurationInferenceConfiguration>
Inference parameters to use when the agent invokes a foundation model in the part of the agent sequence defined by the prompt_type. For more information, see Inference parameters for foundation models. See inference_configuration Block for details.
ParserMode This property is required. string
Whether to override the default parser Lambda function when parsing the raw foundation model output in the part of the agent sequence defined by the prompt_type. If you set the argument as OVERRIDDEN, the override_lambda argument in the prompt_override_configuration block must be specified with the ARN of a Lambda function. Valid values: DEFAULT, OVERRIDDEN.
PromptCreationMode This property is required. string
Whether to override the default prompt template for this prompt_type. Set this argument to OVERRIDDEN to use the prompt that you provide in the base_prompt_template. If you leave it as DEFAULT, the agent uses a default prompt template. Valid values: DEFAULT, OVERRIDDEN.
PromptState This property is required. string
Whether to allow the agent to carry out the step specified in the prompt_type. If you set this argument to DISABLED, the agent skips that step. Valid Values: ENABLED, DISABLED.
PromptType This property is required. string
Step in the agent sequence that this prompt configuration applies to. Valid values: PRE_PROCESSING, ORCHESTRATION, POST_PROCESSING, KNOWLEDGE_BASE_RESPONSE_GENERATION.
BasePromptTemplate This property is required. string
prompt template with which to replace the default prompt template. You can use placeholder variables in the base prompt template to customize the prompt. For more information, see Prompt template placeholder variables.
InferenceConfigurations This property is required. []AgentAgentPromptOverrideConfigurationPromptConfigurationInferenceConfiguration
Inference parameters to use when the agent invokes a foundation model in the part of the agent sequence defined by the prompt_type. For more information, see Inference parameters for foundation models. See inference_configuration Block for details.
ParserMode This property is required. string
Whether to override the default parser Lambda function when parsing the raw foundation model output in the part of the agent sequence defined by the prompt_type. If you set the argument as OVERRIDDEN, the override_lambda argument in the prompt_override_configuration block must be specified with the ARN of a Lambda function. Valid values: DEFAULT, OVERRIDDEN.
PromptCreationMode This property is required. string
Whether to override the default prompt template for this prompt_type. Set this argument to OVERRIDDEN to use the prompt that you provide in the base_prompt_template. If you leave it as DEFAULT, the agent uses a default prompt template. Valid values: DEFAULT, OVERRIDDEN.
PromptState This property is required. string
Whether to allow the agent to carry out the step specified in the prompt_type. If you set this argument to DISABLED, the agent skips that step. Valid Values: ENABLED, DISABLED.
PromptType This property is required. string
Step in the agent sequence that this prompt configuration applies to. Valid values: PRE_PROCESSING, ORCHESTRATION, POST_PROCESSING, KNOWLEDGE_BASE_RESPONSE_GENERATION.
basePromptTemplate This property is required. String
prompt template with which to replace the default prompt template. You can use placeholder variables in the base prompt template to customize the prompt. For more information, see Prompt template placeholder variables.
inferenceConfigurations This property is required. List<AgentAgentPromptOverrideConfigurationPromptConfigurationInferenceConfiguration>
Inference parameters to use when the agent invokes a foundation model in the part of the agent sequence defined by the prompt_type. For more information, see Inference parameters for foundation models. See inference_configuration Block for details.
parserMode This property is required. String
Whether to override the default parser Lambda function when parsing the raw foundation model output in the part of the agent sequence defined by the prompt_type. If you set the argument as OVERRIDDEN, the override_lambda argument in the prompt_override_configuration block must be specified with the ARN of a Lambda function. Valid values: DEFAULT, OVERRIDDEN.
promptCreationMode This property is required. String
Whether to override the default prompt template for this prompt_type. Set this argument to OVERRIDDEN to use the prompt that you provide in the base_prompt_template. If you leave it as DEFAULT, the agent uses a default prompt template. Valid values: DEFAULT, OVERRIDDEN.
promptState This property is required. String
Whether to allow the agent to carry out the step specified in the prompt_type. If you set this argument to DISABLED, the agent skips that step. Valid Values: ENABLED, DISABLED.
promptType This property is required. String
Step in the agent sequence that this prompt configuration applies to. Valid values: PRE_PROCESSING, ORCHESTRATION, POST_PROCESSING, KNOWLEDGE_BASE_RESPONSE_GENERATION.
basePromptTemplate This property is required. string
prompt template with which to replace the default prompt template. You can use placeholder variables in the base prompt template to customize the prompt. For more information, see Prompt template placeholder variables.
inferenceConfigurations This property is required. AgentAgentPromptOverrideConfigurationPromptConfigurationInferenceConfiguration[]
Inference parameters to use when the agent invokes a foundation model in the part of the agent sequence defined by the prompt_type. For more information, see Inference parameters for foundation models. See inference_configuration Block for details.
parserMode This property is required. string
Whether to override the default parser Lambda function when parsing the raw foundation model output in the part of the agent sequence defined by the prompt_type. If you set the argument as OVERRIDDEN, the override_lambda argument in the prompt_override_configuration block must be specified with the ARN of a Lambda function. Valid values: DEFAULT, OVERRIDDEN.
promptCreationMode This property is required. string
Whether to override the default prompt template for this prompt_type. Set this argument to OVERRIDDEN to use the prompt that you provide in the base_prompt_template. If you leave it as DEFAULT, the agent uses a default prompt template. Valid values: DEFAULT, OVERRIDDEN.
promptState This property is required. string
Whether to allow the agent to carry out the step specified in the prompt_type. If you set this argument to DISABLED, the agent skips that step. Valid Values: ENABLED, DISABLED.
promptType This property is required. string
Step in the agent sequence that this prompt configuration applies to. Valid values: PRE_PROCESSING, ORCHESTRATION, POST_PROCESSING, KNOWLEDGE_BASE_RESPONSE_GENERATION.
base_prompt_template This property is required. str
prompt template with which to replace the default prompt template. You can use placeholder variables in the base prompt template to customize the prompt. For more information, see Prompt template placeholder variables.
inference_configurations This property is required. Sequence[AgentAgentPromptOverrideConfigurationPromptConfigurationInferenceConfiguration]
Inference parameters to use when the agent invokes a foundation model in the part of the agent sequence defined by the prompt_type. For more information, see Inference parameters for foundation models. See inference_configuration Block for details.
parser_mode This property is required. str
Whether to override the default parser Lambda function when parsing the raw foundation model output in the part of the agent sequence defined by the prompt_type. If you set the argument as OVERRIDDEN, the override_lambda argument in the prompt_override_configuration block must be specified with the ARN of a Lambda function. Valid values: DEFAULT, OVERRIDDEN.
prompt_creation_mode This property is required. str
Whether to override the default prompt template for this prompt_type. Set this argument to OVERRIDDEN to use the prompt that you provide in the base_prompt_template. If you leave it as DEFAULT, the agent uses a default prompt template. Valid values: DEFAULT, OVERRIDDEN.
prompt_state This property is required. str
Whether to allow the agent to carry out the step specified in the prompt_type. If you set this argument to DISABLED, the agent skips that step. Valid Values: ENABLED, DISABLED.
prompt_type This property is required. str
Step in the agent sequence that this prompt configuration applies to. Valid values: PRE_PROCESSING, ORCHESTRATION, POST_PROCESSING, KNOWLEDGE_BASE_RESPONSE_GENERATION.
basePromptTemplate This property is required. String
prompt template with which to replace the default prompt template. You can use placeholder variables in the base prompt template to customize the prompt. For more information, see Prompt template placeholder variables.
inferenceConfigurations This property is required. List<Property Map>
Inference parameters to use when the agent invokes a foundation model in the part of the agent sequence defined by the prompt_type. For more information, see Inference parameters for foundation models. See inference_configuration Block for details.
parserMode This property is required. String
Whether to override the default parser Lambda function when parsing the raw foundation model output in the part of the agent sequence defined by the prompt_type. If you set the argument as OVERRIDDEN, the override_lambda argument in the prompt_override_configuration block must be specified with the ARN of a Lambda function. Valid values: DEFAULT, OVERRIDDEN.
promptCreationMode This property is required. String
Whether to override the default prompt template for this prompt_type. Set this argument to OVERRIDDEN to use the prompt that you provide in the base_prompt_template. If you leave it as DEFAULT, the agent uses a default prompt template. Valid values: DEFAULT, OVERRIDDEN.
promptState This property is required. String
Whether to allow the agent to carry out the step specified in the prompt_type. If you set this argument to DISABLED, the agent skips that step. Valid Values: ENABLED, DISABLED.
promptType This property is required. String
Step in the agent sequence that this prompt configuration applies to. Valid values: PRE_PROCESSING, ORCHESTRATION, POST_PROCESSING, KNOWLEDGE_BASE_RESPONSE_GENERATION.

AgentAgentPromptOverrideConfigurationPromptConfigurationInferenceConfiguration
, AgentAgentPromptOverrideConfigurationPromptConfigurationInferenceConfigurationArgs

MaxLength This property is required. int
Maximum number of tokens to allow in the generated response.
StopSequences This property is required. List<string>
List of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating the response.
Temperature This property is required. double
Likelihood of the model selecting higher-probability options while generating a response. A lower value makes the model more likely to choose higher-probability options, while a higher value makes the model more likely to choose lower-probability options.
TopK This property is required. int
Number of top most-likely candidates, between 0 and 500, from which the model chooses the next token in the sequence.
TopP This property is required. double
Top percentage of the probability distribution of next tokens, between 0 and 1 (denoting 0% and 100%), from which the model chooses the next token in the sequence.
MaxLength This property is required. int
Maximum number of tokens to allow in the generated response.
StopSequences This property is required. []string
List of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating the response.
Temperature This property is required. float64
Likelihood of the model selecting higher-probability options while generating a response. A lower value makes the model more likely to choose higher-probability options, while a higher value makes the model more likely to choose lower-probability options.
TopK This property is required. int
Number of top most-likely candidates, between 0 and 500, from which the model chooses the next token in the sequence.
TopP This property is required. float64
Top percentage of the probability distribution of next tokens, between 0 and 1 (denoting 0% and 100%), from which the model chooses the next token in the sequence.
maxLength This property is required. Integer
Maximum number of tokens to allow in the generated response.
stopSequences This property is required. List<String>
List of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating the response.
temperature This property is required. Double
Likelihood of the model selecting higher-probability options while generating a response. A lower value makes the model more likely to choose higher-probability options, while a higher value makes the model more likely to choose lower-probability options.
topK This property is required. Integer
Number of top most-likely candidates, between 0 and 500, from which the model chooses the next token in the sequence.
topP This property is required. Double
Top percentage of the probability distribution of next tokens, between 0 and 1 (denoting 0% and 100%), from which the model chooses the next token in the sequence.
maxLength This property is required. number
Maximum number of tokens to allow in the generated response.
stopSequences This property is required. string[]
List of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating the response.
temperature This property is required. number
Likelihood of the model selecting higher-probability options while generating a response. A lower value makes the model more likely to choose higher-probability options, while a higher value makes the model more likely to choose lower-probability options.
topK This property is required. number
Number of top most-likely candidates, between 0 and 500, from which the model chooses the next token in the sequence.
topP This property is required. number
Top percentage of the probability distribution of next tokens, between 0 and 1 (denoting 0% and 100%), from which the model chooses the next token in the sequence.
max_length This property is required. int
Maximum number of tokens to allow in the generated response.
stop_sequences This property is required. Sequence[str]
List of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating the response.
temperature This property is required. float
Likelihood of the model selecting higher-probability options while generating a response. A lower value makes the model more likely to choose higher-probability options, while a higher value makes the model more likely to choose lower-probability options.
top_k This property is required. int
Number of top most-likely candidates, between 0 and 500, from which the model chooses the next token in the sequence.
top_p This property is required. float
Top percentage of the probability distribution of next tokens, between 0 and 1 (denoting 0% and 100%), from which the model chooses the next token in the sequence.
maxLength This property is required. Number
Maximum number of tokens to allow in the generated response.
stopSequences This property is required. List<String>
List of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating the response.
temperature This property is required. Number
Likelihood of the model selecting higher-probability options while generating a response. A lower value makes the model more likely to choose higher-probability options, while a higher value makes the model more likely to choose lower-probability options.
topK This property is required. Number
Number of top most-likely candidates, between 0 and 500, from which the model chooses the next token in the sequence.
topP This property is required. Number
Top percentage of the probability distribution of next tokens, between 0 and 1 (denoting 0% and 100%), from which the model chooses the next token in the sequence.

AgentAgentTimeouts
, AgentAgentTimeoutsArgs

Create string
A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours).
Delete string
A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours). Setting a timeout for a Delete operation is only applicable if changes are saved into state before the destroy operation occurs.
Update string
A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours).
Create string
A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours).
Delete string
A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours). Setting a timeout for a Delete operation is only applicable if changes are saved into state before the destroy operation occurs.
Update string
A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours).
create String
A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours).
delete String
A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours). Setting a timeout for a Delete operation is only applicable if changes are saved into state before the destroy operation occurs.
update String
A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours).
create string
A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours).
delete string
A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours). Setting a timeout for a Delete operation is only applicable if changes are saved into state before the destroy operation occurs.
update string
A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours).
create str
A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours).
delete str
A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours). Setting a timeout for a Delete operation is only applicable if changes are saved into state before the destroy operation occurs.
update str
A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours).
create String
A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours).
delete String
A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours). Setting a timeout for a Delete operation is only applicable if changes are saved into state before the destroy operation occurs.
update String
A string that can be parsed as a duration consisting of numbers and unit suffixes, such as "30s" or "2h45m". Valid time units are "s" (seconds), "m" (minutes), "h" (hours).

Import

Using pulumi import, import Agents for Amazon Bedrock Agent using the agent ID. For example:

$ pulumi import aws:bedrock/agentAgent:AgentAgent example GGRRAED6JP
Copy

To learn more about importing existing cloud resources, see Importing resources.

Package Details

Repository
AWS Classic pulumi/pulumi-aws
License
Apache-2.0
Notes
This Pulumi package is based on the aws Terraform Provider.
AWS v6.76.0 published on Tuesday, Apr 8, 2025 by Pulumi
pulumi/pulumi-aws