mediumMultiple Select
AIF-C01 Practice Question: A developer is building a chatbot that must…
A developer is building a chatbot that must refuse to answer questions about internal financial data. They also need to filter out any offensive language from user inputs. Which TWO Bedrock features should they use? (Choose TWO.)
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
✓
Bedrock Guardrails – topic denial
Option B, Bedrock Guardrails – topic denial, is correct because it lets you define denied topics (such as internal financial data) that the model must refuse to discuss, directly satisfying the requirement to block questions about internal financial data. Option C, Bedrock Guardrails – content filtering, is correct because it detects and filters harmful or offensive content like hate speech, insults, and profanity in both inputs and outputs, which addresses the need to filter offensive language from user inputs. Option A, Bedrock Agent, is not correct because it orchestrates tasks and API calls for action-taking workflows, not content refusal or profanity filtering. Option D, prompt engineering with negative instructions, is not correct because prompt-level instructions are not a reliable enforcement mechanism and lack the managed policy controls of Guardrails. Option E, Bedrock Knowledge Base, is not correct because it is a RAG feature for retrieving and grounding answers in data sources, not for denying topics or filtering offensive language.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Bedrock Agent
Why it's wrong here
A Bedrock Agent orchestrates API calls and task workflows; it provides no content guardrail for refusing financial topics or screening offensive input. It is tempting because agents are the right choice when a chatbot must invoke external systems and complete multi-step actions rather than filter content.
- ✓
Bedrock Guardrails – topic denial
Why this is correct
Bedrock Guardrails topic denial lets you define denied topics, so the chatbot refuses questions about internal financial data. Guardrails also apply content filters that block offensive language in user inputs, satisfying both requirements in one configuration. This directly addresses the stem's dual constraints: refusing financial topics and filtering profanity.
- ✓
Bedrock Guardrails – content filtering
Why this is correct
Bedrock Guardrails content filtering applies configurable policies that block offensive language in user inputs, satisfying the profanity-filtering requirement. It also supports denied topics, which lets the developer define internal financial data as a restricted subject so the chatbot refuses those questions, meeting the second constraint within one feature.
- ✗
Prompt engineering with negative instructions
Why it's wrong here
Negative instructions in a prompt are probabilistic guidance, not an enforced control, so they cannot reliably block financial disclosures or filter profanity. It is tempting because prompt engineering is the correct approach for shaping tone, persona and refusal style where deterministic filtering is not mandated.
- ✗
Bedrock Knowledge Base
Why it's wrong here
Knowledge Bases implement retrieval-augmented generation over your own data sources; they do not classify or block content. Guardrails supply both denied-topic filters and content moderation for offensive language, which the scenario requires. Knowledge Bases would be correct when grounding responses in indexed documents rather than refusing topics.
Go deeper
Related to this question
About these practice questions
This AIF-C01 question is part of Courseiva's 862-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam 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.