AIF-C01 Guidelines for Responsible AI Practice Question
A fintech company wants its Amazon Bedrock assistant to answer customer questions only from its approved policy documents and to avoid fabricating answers when the documents do not cover a topic. The team plans to use a knowledge base with retrieval augmented generation. Which Bedrock Guardrails feature should they configure to detect and block responses that are not supported by the retrieved source passages?
⚠ Common exam trap
The trap here is assuming any Guardrails filter prevents hallucination, when only the contextual grounding check compares responses against retrieved source passages.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
A contextual grounding check with a grounding threshold and relevance threshold
Preventing fabricated answers requires checking whether a response is entailed by the retrieved context. Bedrock Guardrails contextual grounding performs exactly that comparison, and its grounding and relevance thresholds determine how strictly unsupported or off-topic responses are blocked. Harmful-content, PII, and word filters address toxicity or confidentiality but never verify factual support from source passages.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
A contextual grounding check with a grounding threshold and relevance threshold
Why this is correct
Contextual grounding evaluates whether a response is supported by the retrieved source and whether it is relevant to the user query, using configurable grounding and relevance thresholds. Setting these thresholds makes the assistant block or flag answers not entailed by the approved policy passages, directly preventing fabrication when the documents do not cover a topic.
- ✗
A sensitive-information filter that blocks personally identifiable information
Why it's wrong here
The sensitive-information filter detects and masks or blocks PII and custom regex patterns. It protects confidentiality but does not verify that a response is entailed by retrieved passages. An unsupported answer containing no PII would still reach the customer, so this filter does not meet the grounding requirement.
- ✗
A word filter that blocks a custom list of profane terms
Why it's wrong here
Word filters match literal terms or phrases on a deny list. They cannot judge whether a response is entailed by retrieved documents, so an invented but polite answer would pass. This control targets specific vocabulary, not factual grounding, and does not address the fabrication risk.
- ✗
Content filters for hate, violence, and insult
Why it's wrong here
Content filters classify text against harmful categories such as hate, violence, sexual content, and insults. They do not compare a response against retrieved source passages, so a plausible but unsupported answer would pass. They address toxicity, not factual grounding, and therefore cannot prevent fabrication relative to the approved policy documents.
Go deeper
Related to this question
About these practice questions
One of 862 original AIF-C01 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Amazon Web Services exam blueprint
This AIF-C01 practice question is part of Courseiva's free Amazon Web Services certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AIF-C01 exam.