AIF-C01 Practice Question: Security, Compliance, and Governance for AI Solutions
A company wants to use Amazon Bedrock to generate responses grounded in their proprietary knowledge base. They need to minimize hallucinations and ensure responses are based on the provided documents. Which feature should they enable?
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
✓
Grounding check
Grounding check in Bedrock Guardrails verifies that the model's response is supported by the source documents, reducing hallucinations.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Topic restrictions
Why it's wrong here
Topic restrictions block defined subjects in prompts and completions, so they cannot ground answers in your documents or cite retrieved passages. They are tempting because they do constrain output scope, and would be correct for refusing off-limits subjects such as competitors or medical advice, not for retrieval-augmented grounding.
- ✗
Word filters
Why it's wrong here
Word filters block specific terms or phrases in prompts and completions, which cannot attach source documents to a model invocation. They are tempting because they restrict generated text, and would be correct for suppressing profanity, competitor names or banned vocabulary — not for grounding answers in proprietary documents to reduce hallucination.
- ✓
Grounding check
Why this is correct
Grounding check measures whether each response is supported by the retrieved source passages, flagging or filtering ungrounded statements. This directly reduces hallucination by tying outputs to the proprietary knowledge base documents rather than model memory.
- ✗
Content filters
Why it's wrong here
Content filters screen prompts and responses against harmful categories such as hate, violence and sexual content; they add no retrieval step, so responses remain ungrounded in the knowledge base. They are tempting because they reduce undesirable output, and would be correct for enforcing safety and moderation policies rather than factual grounding.
Go deeper
Related to this question
About these practice questions
Courseiva writes every AIF-C01 question from scratch — 862 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
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.