Cert Master

AIP-C01 Domain 4: Security, Testing, and Governance for GenAI Applications

A team must block harmful prompts and responses. Which option meets the requirement?

Multiple choice — select one answer

Answer choices

  1. a. Amazon Bedrock Guardrails
  2. b. IAM policies scoped to model ARNs
  3. c. Data masking and policy on PII
  4. d. Structured adversarial testing

Architectural breakdown & explanation

Guardrails enforce content policies.

Correct answer(s): a. Amazon Bedrock Guardrails

Exam domain: Domain 4: Security, Testing, and Governance for GenAI Applications (24% weight on the official guide).

Official documentation & study links

Practice this certification

This page is one question from the AWS Certified Generative AI Developer – Professional bank. Run a full timed practice exam with domain-weighted random questions in your browser.

Start practice exam View exam overview All certifications