This course was developed by members of AWS Technical Field Communities (TFC), an AWS community of technical experts. The content is intended to complement our standard training curriculum and augment your AWS learning journey. We are aware some courses have accessibility limitations and are working to address. If you require accommodation, please contact AWS Training and Certification Customer Support.
This course introduces Amazon Bedrock Guardrails features for implementing safety, privacy, and responsible AI controls in generative AI applications. Participants will learn how Amazon Bedrock Guardrails used as a tool to help organizations address the unique risks and challenges associated with deploying foundation models while ensuring compliance with responsible AI policies.
The course covers Amazon Bedrock Guardrails' core features, including content filtering, denied topics management, prompt protection, and sensitive information redaction. Through demonstrations, learners will explore how to implement Guardrails to detect and filter various types of problematic content such as harmful responses, prompt attack, and sensitive data like personally identifiable (PII) and credit card information.
