Operations reports a need to moderate harmful content in model inputs and outputs. What is the MOST operationally efficient solution? moderate harmful content in model inputs and outputs.
Multiple choice — select one answer
Answer choices
Architectural breakdown & explanation
Guardrails filter topics, PII, and harmful content.
Correct answer(s): c. Amazon Bedrock Guardrails
Exam domain: Domain 3: Applications of Foundation Models (28% weight on the official guide).
Official documentation & study links
Practice this certification
This page is one question from the AWS Certified AI Practitioner bank. Run a full timed practice exam with domain-weighted random questions in your browser.