Configurable controls in Bedrock to filter harmful content, block disallowed topics, redact sensitive information (PII), and reduce hallucinations, applied to both user inputs and model outputs.
In AIF-C01 (Domain 4, Responsible AI) it's the specific tool for implementing content safety guardrails. Question: prevent a customer service chatbot from discussing competitors or generating offensive content → configure Guardrails with content and topic filtering.
Amazon Bedrock Guardrails is a concept that can show up on the exam. Check the full guide to see it in context.