hands-on lab

Building a Generative AI Workflow With Amazon Bedrock Flows

Difficulty: Beginner
Duration: Up to 45 minutes
Students: 4
Get guided in a real environmentPractice with a step-by-step scenario in a real, provisioned environment.
Learn and validateUse validations to check your solutions every step of the way.
See resultsTrack your knowledge and monitor your progress.

Description

Amazon Bedrock Flows is a visual workflow builder that enables developers to create generative AI applications without the need to write code. The Amazon Bedrock Flow Builder is a console tool that offers seamless integration of foundation models, prompts, knowledge bases, and AWS services. The service offers key benefits like simplified workflow development, enhanced safety controls using Bedrock Guardrails, and the ability to quickly test and deploy these workflows.

In this lab, you will work with the Amazon Bedrock Flow builder to configure generative AI workflows using nodes to control the data and logic of the flow. You will create a basic prompt flow that utilizes the input, output, and prompt nodes to generate responses using an Amazon Titan foundation model. You will also configure a flow using the condition node to interact with Amazon S3 or AWS Lambda based on the input query type.

Learning objectives

Upon completion of this beginner-level lab, you will be able to:

  • Define an Amazon Bedrock Flow
  • Implement conditional logic into an Amazon Bedrock Flow
  • Configure Amazon S3 and AWS Lambda nodes in an Amazon Bedrock Flow

Intended audience

  • Cloud Architects
  • Software Engineers

Prerequisites

Familiarity with the following will be beneficial but is not required:

  • Amazon Bedrock

The following content can be used to fulfill the prerequisites:

Environment before

Environment after

Covered topics

Lab steps

Logging In to the Amazon Web Services Console
Configuring an Amazon Bedrock Flow
Controlling Flow Logic with Condition Nodes
Handling Amazon Bedrock Flow Data With Amazon S3 and AWS Lambda