Perform AI prompt-chaining with Amazon Bedrock - AWS Step Functions

Perform AI prompt-chaining with Amazon Bedrock

This sample project demonstrates how you can integrate with Amazon Bedrock to perform AI prompt-chaining. This sample project shows how you can build high-quality chatbots using Amazon Bedrock. The project chains together some prompts and resolves them in the sequence in which they're provided. Chaining of these prompts augments the ability of the language model being used to deliver a highly-curated response.

This sample project creates the state machine, the supporting AWS resources, and configures the related IAM permissions. Explore this sample project to learn about using Amazon Bedrock optimized service integration with Step Functions state machines, or use it as a starting point for your own projects.

AWS CloudFormation template and additional resources

You use a CloudFormation template to deploy this sample project. This template creates the following resources in your AWS account:

  • A Step Functions state machine.

  • Execution role for the state machine. This role grants the permissions that your state machine needs to access other AWS services and resources such as the Amazon Bedrock InvokeModel action.


This sample project uses the Cohere Command large language model (LLM). To successfully run this sample project, you must add access to this LLM from the Amazon Bedrock console. To add the model access, do the following:

  1. Open the Amazon Bedrock console.

  2. On the navigation pane, choose Model access.

  3. Choose Manage model access.

  4. Select the check box next to Cohere.

  5. Choose Request access. The Access status for Cohere model shows as Access granted.

Step 1: Create the state machine and provision resources

  1. Open the Step Functions console and choose Create state machine.

  2. Type bedrock in the search box, and then choose Perform AI prompt-chaining with Bedrock from the search results that are returned.

  3. Choose Next to continue.

  4. Step Functions lists the AWS services used in the sample project you selected. It also shows a workflow graph for the sample project. Deploy this project to your AWS account or use it as a starting point for building your own projects. Based on how you want to proceed, choose Run a demo or Build on it.

    This sample project deploys the following resources:

    • An AWS Step Functions state machine

    • Related AWS Identity and Access Management (IAM) roles

    The following image shows the workflow graph for the Perform AI prompt-chaining with Bedrock sample project:

    Workflow graph of the Perform prompt-chaining with Bedrock sample project.
  5. Choose Use template to continue with your selection.

  6. Do one of the following:

    • If you selected Build on it, Step Functions creates the workflow prototype for the sample project you selected. Step Functions doesn't deploy the resources listed in the workflow definition.

      In Workflow Studio's Design mode, drag and drop states from the States browser to continue building your workflow protoype. Or switch to the Code mode that provides an integrated code editor similar to VS Code for updating the Amazon States Language (ASL) definition of your state machine within the Step Functions console. For more information about using Workflow Studio to build your state machines, see Using Workflow Studio.


      Remember to update the placeholder Amazon Resource Name (ARN) for the resources used in the sample project before you run your workflow.

    • If you selected Run a demo, Step Functions creates a read-only sample project which uses an AWS CloudFormation template to deploy the AWS resources listed in that template to your AWS account.


      To view the state machine definition of the sample project, choose Code.

      When you're ready, choose Deploy and run to deploy the sample project and create the resources.

      It can take up to 10 minutes for these resources and related IAM permissions to be created. While your resources are being deployed, you can open the CloudFormation Stack ID link to see which resources are being provisioned.

      After all the resources in the sample project are created, you can see the new sample project listed on the State machines page.


      Standard charges may apply for each service used in the CloudFormation template.

Step 2: Run the state machine

  1. On the State machines page, choose your sample project.

  2. On the sample project page, choose Start execution.

  3. In the Start execution dialog box, do the following:

    1. (Optional) To identify your execution, you can specify a name for it in the Name box. By default, Step Functions automatically generates a unique execution name.


      Step Functions allows you to create names for state machines, executions, activities, and labels that contain non-ASCII characters. These non-ASCII names don't work with Amazon CloudWatch. To ensure that you can track CloudWatch metrics, choose a name that uses only ASCII characters.

    2. (Optional) In the Input box, enter input values in JSON format to run your workflow.

      If you chose to Run a demo, you need not provide any execution input.

    3. Choose Start execution.

    4. The Step Functions console directs you to a page that's titled with your execution ID. This page is known as the Execution Details page. On this page, you can review the execution results as the execution progresses or after it's complete.

      To review the execution results, choose individual states on the Graph view, and then choose the individual tabs on the Step details pane to view each state's details including input, output, and definition respectively. For details about the execution information you can view on the Execution Details page, see Execution Details page – Interface overview.