Amazon Bedrock Agent

End-to-end walkthrough for onboarding an Amazon Bedrock Agent via the Trusted Agent Huddle to the gallery using the AI Refinery runtime.

This walkthrough shows how to add the Amazon Bedrock Agent via the Trusted Agent Huddle, upload its runtime definition, configure credentials, and run validation queries inside the Agent Gallery.

1. Create the Amazon Bedrock Agent

From the Agent Gallery toolbar select Add Agent, pick the owning organisation, and fill out the metadata (identifier, display name, description, licence, and type) for the Amazon Bedrock Agent.

Create Amazon Bedrock agent form completed

Click Create Agent to provision the new entry and advance to its overview page.

Amazon Bedrock agent overview after creation

2. Upload the runtime YAML

Use Edit → Runtime, confirm the runtime type matches your Amazon Bedrock integration, and upload example.yaml with the agent definition below.

orchestrator:
  agent_list:
    - agent_name: "Amazon Assistant"

utility_agents:
  - agent_class: AmazonBedrockAgent
    agent_name: "Amazon Assistant"
    agent_description: "The Amazon Assistant handles any questions related to the Amazon platform."
    config:
      client_key: "AWS_CLIENT_KEY" # Required Client Key
      client_secret: "AWS_CLIENT_SECRET" # Required Client Secret
      deployment_region: "DEPL-REG-1" # Required deployment region (from Bedrock platform overview)
      agent_id: "YourAgentID" # Required Agent identifier (from Bedrock platform overview)
      alias_id: "YourAgentAliasID" # Required alias identifier (from Bedrock platform overview)
      session_id: "123456789" # Optional session identifier
      contexts: # Optional additional agent contexts
        - "date"
        - "chat_history"

Runtime tab with bedrock-example.yaml uploaded for the Amazon Bedrock agent

You should see in the build status that the runtime is successfully uploaded.

3. Register configuration values

Open the Config tab, choose Add Configuration, and register each Amazon Bedrock environment variable referenced in the YAML. Mark the variables as required and masked accordingly.

Configuration dialog listing Amazon Bedrock variables

Environment Variable	Type	Required	Description
`API_KEY`	String	Yes	Your AI Refinery API key.
`AWS_CLIENT_KEY`	String	Yes	AWS access key used to authenticate to Amazon Bedrock.
`AWS_CLIENT_SECRET`	String	Yes	AWS secret key that pairs with the access key.

These will ask for the variables before a run.

4. Launch a validation run

Return to the agent overview and select Run. Choose the hardware preset, populate the configuration fields with valid Amazon Bedrock credentials, and run the agent.

Run dialog for the Amazon Bedrock agent

5. Issue starter queries

Use the chat input to ask introductory questions that verify the Bedrock model responds correctly—for example, ask questions about Amazon. Confirm the responses look correct.

Chat transcript showing successful Amazon Bedrock responses

Amazon Bedrock agent handling more complex prompts

8. Wrap up the session

When validation is complete, shut down the run to release compute resources.