For the complete documentation index, see llms.txt.
Skip to main content
Version: 8.11 (unreleased)

Amazon Bedrock AgentCore Runtime connector

Use the Amazon Bedrock AgentCore Runtime connector to invoke external agents deployed on Amazon Bedrock AgentCore Runtime from your BPMN process.

About this connector​

The Amazon Bedrock AgentCore Runtime connector is an outbound connector that sends a payload to an agent hosted on AWS and returns the agent's response to your process.

Use this connector to delegate complex reasoning tasks to specialized AI agents hosted on AWS, such as fraud detection, risk analysis, or document processing agents built with frameworks like Strands, LangGraph, or CrewAI.

Prerequisites​

To use the Amazon Bedrock AgentCore Runtime connector, you need the following:

  • An AWS account with an access key and secret key, a configured default credentials chain (hybrid/Self-Managed only), or a saved AWS credential.
  • An agent deployed to AgentCore Runtime in an ACTIVE state.
  • IAM permissions to execute the InvokeAgentRuntime action on the agent's ARN.

Learn more about AgentCore Runtime in the official documentation.

note

Use secrets to store credentials and avoid exposing sensitive information from the process. See managing secrets.

Use this connector​

New to using an outbound connector? Learn how to add and use this type of connector, apply element templates, use connector secrets, handle results and errors, and more.

Configuration​

Authentication​

PropertyTypeRequiredDescriptionExample
AWS credentialConfigurationNoSelect a saved AWS credential with an optional default region, or enter the authentication details and a region in the fields below. Learn more about credentials.
AuthenticationDropdownYes, if no AWS credential is set

The AWS authentication strategy:

  • Credentials (SaaS/Self-Managed): Use this option if you have a valid pair of access and secret keys provided by your AWS account administrator.

  • Default Credentials Chain (hybrid/Self-Managed only): Use this option if your system is configured for implicit authentication, such as role-based authentication, credentials supplied through environment variables, or files on the target host. This approach uses the Default Credential Provider Chain to resolve the required credentials.

Access keyStringYes, if Authentication is CredentialsThe access key of an IAM user with permissions to invoke the agent runtime.
Secret keyStringYes, if Authentication is CredentialsThe secret key of the IAM user with the access key above.

For more information on authentication and security in Amazon Bedrock, see Amazon Bedrock security and privacy.

Region​

PropertyTypeRequiredDescriptionExample
RegionStringYes, if no AWS credential is setThe AWS region where your AgentCore Runtime agent is deployed.us-east-1
RegionStringYes, if the credential has no default regionOverrides the default region of the selected AWS credential. Shown when an AWS credential is selected.

Operations​

The Amazon Bedrock AgentCore Runtime connector supports one operation.

Invoke agent runtime​

Send a payload to a deployed AgentCore Runtime agent and return its response.

Input parameters​

PropertyTypeRequiredDescriptionExample
Agent Runtime ARNStringYesThe ARN of the AgentCore Runtime agent to invoke. You can find it in the AgentCore console or in the output of agentcore deploy.arn:aws:bedrock-agentcore:us-east-1:123456789012:runtime/fraud_agent-1GRoTlCtHi
PayloadStringYesThe payload to send to the agent. Use a FEEL expression to define the structure. The connector sends the payload as JSON, so the structure depends on the agent.={inputText: "your prompt"}
Session IDStringNoAn optional session ID for multi-turn conversations. When provided, the agent retains context from previous interactions within the same session.

Output​

The connector returns the following fields:

FieldDescription
responseThe agent's response. If the agent returns valid JSON, the connector parses it. If the agent streams its response as server-sent events, the connector joins the streamed values into one string. Otherwise, it returns the plain text.
sessionIdThe runtime session ID. Use this value in subsequent calls to continue the conversation.
statusCodeThe HTTP status code of the response.

Use the Result variable to store the response in a process variable, or the Result expression to map specific fields into process variables. For example, to extract the agent's response and the session ID:

= {
answer: response,
session: sessionId
}

Example: Invoke a fraud detection agent​

Configuration:

  • Agent Runtime ARN: arn:aws:bedrock-agentcore:us-east-1:123456789012:runtime/fraud_agent-1GRoTlCtHi
  • Payload: ={inputText: "Claim: Customer reports stolen vehicle worth $45,000. Filed 2 days after policy activation. No police report."}

Response:

In this example, the agent returns a JSON-encoded string, so response is a string. If the agent returns a JSON object, response is the parsed object.

{
"response": "{\"result\": {\"role\": \"assistant\", \"content\": [{\"text\": \"{\\\"riskScore\\\": 85, \\\"riskLevel\\\": \\\"HIGH\\\", \\\"flags\\\": [\\\"Policy activated only 2 days before claim\\\", \\\"No police report filed\\\", \\\"High-value claim\\\"], \\\"recommendation\\\": \\\"REJECT\\\"}\"}]}}",
"sessionId": "76f079e6-f30b-4416-9fbc-5d09d2ad31de",
"statusCode": 200
}

Multi-turn conversations​

To maintain context across multiple interactions with the same agent, pass the sessionId from the previous response into the Session ID field of the next call. This allows the agent to remember prior messages and maintain state.

Troubleshooting​

To learn about general error handling in Camunda, see BPMN errors and failing jobs.

AGENTCORE_RUNTIME_FAILED​

The connector throws an error with the code AGENTCORE_RUNTIME_FAILED when it cannot serialize the payload to JSON, or when AgentCore Runtime returns an error. The error message contains the details from AWS.