Moderating Content with Amazon Bedrock

Generative AI models, such as those available through the fully managed Amazon Bedrock service, can be used to moderate content in sophisticated and flexible ways. These models are capable of moderating at a human level of understanding and can be used to moderate text, images, and audio.

Learning how to integrate Amazon Bedrock into an existing content moderation system will benefit anyone looking to make use of generative AI in their systems.

In this hands-on lab, you will configure Amazon SNS and Amazon SQS to work together, implement an AWS Lambda function that invokes a generative AI model, and test the resulting content moderation system.

Learning objectives

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

• Subscribe an Amazon SQS queue to an Amazon SNS topic
• Invoke an Amazon Bedrock model from an AWS Lambda function using Python
• Use the AWS CLI to upload content to Amazon S3
• Monitor the moderation system using Amazon CloudWatch

Intended audience

• Candidates for the AWS Certified AI Practitioner certification
• Cloud Architects
• Data Engineers
• DevOps Engineers
• Machine Learning Engineers
• Software Engineers

Prerequisites

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

• Amazon SNS and Amazon SQS
• AWS Lambda and Python
• Amazon Bedrock

The following content can be used to fulfill the prerequisites:

• Amazon SQS versus Amazon SNS - What is the Difference?
• Monitoring and Debugging AWS Lambda Functions
• Interacting with Amazon Bedrock Foundation Models using APIs

Updates

July 25th, 2025 - Upgraded lab to use the latest Nova Micro model

April 18th, 2025 - Updated instructions to reflect the latest Lambda console interface

March 5th, 2025 - Added a file with complete Python code for convenience