AIF-C01 Applications of Foundation Models Practice Question
A financial services company uses Amazon Bedrock with the Anthropic Claude 3 Haiku model to answer employee questions about internal policies. The knowledge base is updated weekly, and the company wants the model to cite the exact source document and page number in its responses. Which approach should the company use to meet these requirements?
⚠ Common exam trap
The trap here is assuming that fine-tuning or prompt engineering can make a model cite sources, when citation requires a retrieval mechanism such as Amazon Bedrock Knowledge Bases.
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
✓
Use Amazon Bedrock Knowledge Bases with a vector store and enable citations in the RetrieveAndGenerate API call.
The company needs answers grounded in specific internal documents with citations. Amazon Bedrock Knowledge Bases performs retrieval-augmented generation by fetching relevant passages from a connected data source and can return citations that point to the source document and page. This directly satisfies the requirement, whereas fine-tuning, temperature adjustments, or Guardrails do not provide source attribution.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Increase the temperature setting in the InvokeModel API call to encourage the model to include source references.
Why it's wrong here
Temperature controls the randomness of the model's output, not its ability to cite sources. Raising temperature would make responses more creative and less deterministic, but it would not cause the model to reference specific documents or page numbers, so it does not meet the requirement.
- ✗
Fine-tune the Anthropic Claude 3 Haiku model on the internal policy documents and deploy the custom model.
Why it's wrong here
Fine-tuning adapts a model's weights to a specific dataset, but it does not provide a mechanism to cite source documents or page numbers at inference time. The model would generate answers based on learned patterns without attributing them to specific documents, so this approach fails the citation requirement.
- ✗
Use Amazon Bedrock Guardrails to filter responses and automatically append document citations.
Why it's wrong here
Guardrails are designed to enforce content policies, such as blocking harmful or sensitive topics, and to apply filters on inputs and outputs. They do not retrieve documents or generate citations. Therefore, using Guardrails would not provide the source attribution required by the company.
- ✓
Use Amazon Bedrock Knowledge Bases with a vector store and enable citations in the RetrieveAndGenerate API call.
Why this is correct
Amazon Bedrock Knowledge Bases supports retrieval-augmented generation and can return citations that identify the source documents and passages used to generate a response. By enabling citations in the RetrieveAndGenerate API call, the model's answers include references to the exact source, satisfying the requirement for document and page-level attribution.
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.