{
  "schema_version": 2,
  "id": "integrate/amazon-bedrock/create-agent",
  "title": "Create a Bedrock agent",
  "url": "https://redis.io/docs/latest/integrate/amazon-bedrock/create-agent/",
  "summary": "Shows how to set up your Agent in Amazon Bedrock.",
  "aliases": [
    "/integrate/aws-bedrock/create-agent/"
  ],
  "tags": [
    "docs",
    "integrate",
    "oss",
    "rs",
    "rc"
  ],
  "last_updated": "2026-10-02T14:54:03+01:00",
  "page_type": "content",
  "content_hash": "92cb856369067b40ee62a9525a26ee1b877a90f881cc0cbdf56bfac0eced0ff8",
  "sections": [
    {
      "id": "overview",
      "title": "Overview",
      "role": "overview",
      "text": "After you have [created a knowledge base](https://redis.io/docs/latest/integrate/amazon-bedrock/create-knowledge-base), you can use it to create an agent on Amazon Bedrock.\n\nBefore you begin this guide, you will need:\n\n- An [AWS IAM Role](https://docs.aws.amazon.com/IAM/latest/UserGuide/id_roles_create_for-service.html) with [permissions for the Bedrock agent](https://docs.aws.amazon.com/bedrock/latest/userguide/security_iam_id-based-policy-examples.html).\n\n- A [Bedrock knowledge base](https://redis.io/docs/latest/integrate/amazon-bedrock/create-knowledge-base) connected to a [Redis Cloud vector database](https://redis.io/docs/latest/integrate/amazon-bedrock/set-up-redis)."
    },
    {
      "id": "create-an-agent",
      "title": "Create an agent",
      "role": "content",
      "text": "1. Sign in to the [AWS console](https://console.aws.amazon.com/). \n\n1. Use the **Services** menu to locate and select **Machine Learning** > **Amazon Bedrock**.  This takes you to the Amazon Bedrock admin panel.\n\n1. Select **Agents** > **Create Agent** to create your knowledge base.\n\n    ![The Create Agent button.](https://redis.io/docs/latest/images/rc/bedrock-aws-button-create-agent.png)\n\n1. In the **Agent name** section, enter a name and description for your agent.\n\n1. Select whether or not you want the agent to be able to ask for additional information in the **User input** section.\n\n1. Select the IAM role for the Bedrock agent in the **IAM Permissions** section. \n\n1. Choose how long you want your idle session timeout to be in the **Idle session timeout** section. Select **Next** to continue.\n\n1. In the **Model details** section, choose which model you want to use and enter the instructions for your agent. Select **Next** to continue.\n\n1. In the **Action groups** section, you may specify any tasks you would like the agent to perform. Select **Next** to continue.\n\n1. Select the [knowledge base](#create-a-knowledge-base) you created and summarize the information in the knowledge base in the **Knowledge base instructions for Agent** form. Select **Add another knowledge base** if you would like to add multiple knowledge bases. \n\n     ![The Add another knowledge base button.](https://redis.io/docs/latest/images/rc/bedrock-aws-button-add-knowledge-base.png)\n\n    Select **Next** to continue.\n\n1. Review your agent before you create it. Select **Create Agent** to finish creation.\n\n    ![The Create Agent button.](https://redis.io/docs/latest/images/rc/bedrock-aws-button-create-agent.png)\n\nAmazon Bedrock will create your agent and link it to your knowledge base. This will take some time. \n\nYour agent will have a status of **Ready** when it is ready to be tested. \n\n![A Bedrock agent with a Ready status.](https://redis.io/docs/latest/images/rc/bedrock-aws-status-agent-ready.png)\n\nSelect the name of your agent to view the versions and draft aliases of your agent. You can also test your agent by entering prompts in the **Enter your message here** field."
    }
  ],
  "examples": []
}