AIF-C01 Applications of Foundation Models Practice Question

A financial services company has built an internal assistant on Amazon Bedrock using Anthropic Claude 3 Sonnet. Employees ask questions that require retrieving the latest internal policy documents, which are updated frequently and stored in Amazon S3. The company wants the assistant to answer with accurate, up-to-date citations without retraining the model. Which approach should they implement?

⚠ Common exam trap

The trap here is assuming that fine-tuning is the way to add new knowledge, when RAG is the appropriate pattern for frequently updated, citable source material.

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 Retrieval Augmented Generation (RAG) by creating a knowledge base in Amazon Bedrock that indexes the S3 documents.

Grounding a foundation model in frequently changing internal documents is best achieved with Retrieval Augmented Generation. An Amazon Bedrock knowledge base ingests the S3 content, chunks and embeds it, and retrieves relevant passages at inference time so the model can answer with current, citable information. This avoids retraining and keeps responses accurate as policies evolve.

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 parameter to encourage the model to generate more detailed and specific policy answers.
Why it's wrong here
Temperature controls randomness in token sampling; higher values make output more varied and creative, not more factually grounded. Raising temperature increases the risk of hallucinated policy details. It does nothing to connect the model to the current S3 documents or to produce citations.
✗
Enable model invocation logging in Amazon Bedrock to capture requests and responses for later review.
Why it's wrong here
Invocation logging records prompts and completions for auditing and monitoring. It does not supply the model with current policy content, so answers would still rely on the model's training data. Logging is an observability feature, not a retrieval or grounding mechanism.
✗
Fine-tune the Claude 3 Sonnet model on the policy documents using Amazon Bedrock custom models.
Why it's wrong here
Fine-tuning adjusts model weights for a task, but it is costly, requires training data preparation, and does not automatically reflect frequently updated documents. Re-running fine-tuning on every policy change is impractical, and citations are not reliably produced. It also modifies model behavior rather than providing verifiable source grounding.
✓
Use Retrieval Augmented Generation (RAG) by creating a knowledge base in Amazon Bedrock that indexes the S3 documents.
Why this is correct
RAG with an Amazon Bedrock knowledge base retrieves relevant document chunks from the S3 data source at query time and passes them to the model as context. This grounds responses in current content and can return citations, all without retraining or fine-tuning the underlying foundation model.

Quick reference

AWS S3 Storage Class Comparison

Storage Class	Min Duration	Retrieval	Use Case
S3 Standard	None	Immediate	Frequently accessed data
S3 Standard-IA	30 days	Immediate	Infrequent access, rapid retrieval
S3 One Zone-IA	30 days	Immediate	Non-critical infrequent data
S3 Intelligent-Tiering	None	Immediate–hours	Unknown or changing access patterns
S3 Glacier Instant	90 days	Milliseconds	Archive with instant retrieval
S3 Glacier Flexible	90 days	Minutes–hours	Archive, flexible retrieval
S3 Glacier Deep Archive	180 days	Hours	Long-term compliance archive

Go deeper

AIF-C01 Applications of Foundation Models Practice Question

Why each option matters

Option-by-option breakdown

AWS S3 Storage Class Comparison

Related to this question