Implement input and output safety controls.
9 practice questions under this official exam objective (AIP-C01) — each with the community-verified answer, a full option-by-option explanation and instant feedback.
How to Block Prompt Injection with Bedrock Guardrails and Cross-Region Failover?
Amazon Bedrock Guardrails content filters at high strength, a guardrail profile for cross-Region guardrail inference, and CloudWatch Logs intervention
Amazon Bedrock Guardrails for Financial Compliance
This question explores how to implement Amazon Bedrock Guardrails to ensure an AI assistant complies with financial regulations by blocking high-risk
Which Amazon Comprehend filtering design meets privacy and latency requirements?
Amazon Comprehend layered content filtering for a Bedrock-powered assistant requires toxicity detection, prompt safety classification, and PII redacti
Bedrock Prompt Management & Guardrails Detection
This scenario tests configuring Amazon Bedrock Prompt Management for structured inputs and output formats, alongside Bedrock Guardrails set to detect
Preventing PII Leakage in Bedrock Model Outputs
This clinical AI scenario tests how to stop personally identifiable information from appearing in Amazon Bedrock model responses when input-side scrub
How to Block Violent Bedrock Responses for Children
The scenario tests how to stop Amazon Bedrock from producing violent, child-inappropriate and historically inaccurate answers in an Amazon Nova Pro kn
Which Solution Detects Hallucinations in a Bedrock Clinical Knowledge Base Before Release?
A Bedrock clinical knowledge base that fabricates treatment advice must be validated before release against a reference dataset of approved question-a
Masking PII in Amazon Bedrock FM Responses
For financial services workloads on Amazon Bedrock, masking PII in foundation model responses is most cleanly achieved with native Bedrock Guardrails:
Blocking Harmful Prompts and Streaming Bedrock Guardrail Filters
Amazon Bedrock Guardrails can be applied before, during, and after inference so a social messaging assistant blocks harmful prompts, filters streamed