- A
Use RAG to retrieve transaction data from a vector database and include it in the prompt to the LLM
Why wrong: RAG would include raw transaction data (containing PII) in the prompt, exposing PII to the model and potentially in outputs.
- B
Fine-tune an Amazon Titan model on the transaction data after masking PII, then use the fine-tuned model for inference
Why wrong: Even masked PII may be memorized; fine-tuning on sensitive data increases risk of data leakage.
- C
Host the model on Amazon SageMaker and apply differential privacy during training
Why wrong: Differential privacy can help but is complex; training on PII still poses risk. A pre-trained model avoids training on sensitive data altogether.
- D
Use a pre-trained foundation model via Amazon Bedrock with a system prompt that instructs the model not to output PII, and enable Bedrock’s data protection
Pre-trained model avoids PII in training; system prompt and data protection guardrails prevent PII in outputs.
AIF-C01 Practice Question: A financial services firm needs an LLM-powered…
This AIF-C01 practice question tests your understanding of aif-c01 exam topics. Match the stated requirement to the specific cloud service, access model, or configuration option — many options are valid in isolation but not for this scenario. After answering, compare your reasoning against the explanation and wrong-answer breakdown below. Once you have made your selection, read the full explanation to reinforce the concept and understand why each distractor is designed to mislead on exam day.
A financial services firm needs an LLM-powered application that analyzes customer transaction data and generates compliance reports. The data contains personally identifiable information (PII). The firm must ensure that no training data includes PII, and that the LLM never outputs PII. Which combination of AWS services and practices should they use?
Clue words in this question
Noticing these words before you look at the options changes how you read each choice.
Clue:
"never"Why it matters: Absolute qualifier. True only if the statement has zero exceptions — be cautious of options that seem obvious but break down in edge cases.
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 a pre-trained foundation model via Amazon Bedrock with a system prompt that instructs the model not to output PII, and enable Bedrock’s data protection
Using Amazon Bedrock with a pre-trained foundation model (no fine-tuning) ensures PII is not in training data. A system prompt instructing the model to avoid PII, combined with Bedrock’s built-in data protection, prevents PII in outputs. Fine-tuning or RAG with sensitive data would risk exposure.
Key principle: Count usable hosts — not total addresses — and remember that the network and broadcast addresses are not available to hosts in standard IPv4 subnets.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Use RAG to retrieve transaction data from a vector database and include it in the prompt to the LLM
Why it's wrong here
RAG would include raw transaction data (containing PII) in the prompt, exposing PII to the model and potentially in outputs.
- ✗
Fine-tune an Amazon Titan model on the transaction data after masking PII, then use the fine-tuned model for inference
Why it's wrong here
Even masked PII may be memorized; fine-tuning on sensitive data increases risk of data leakage.
- ✗
Host the model on Amazon SageMaker and apply differential privacy during training
Why it's wrong here
Differential privacy can help but is complex; training on PII still poses risk. A pre-trained model avoids training on sensitive data altogether.
- ✓
Use a pre-trained foundation model via Amazon Bedrock with a system prompt that instructs the model not to output PII, and enable Bedrock’s data protection
Why this is correct
Pre-trained model avoids PII in training; system prompt and data protection guardrails prevent PII in outputs.
Clue confirmation
The clue word "never" in the question point toward this answer.
Related concept
CIDR notation defines the prefix length.
Common exam traps
Common exam trap: usable hosts are not the same as total addresses
Subnetting questions often tempt you into counting all addresses. In normal IPv4 subnets, the network and broadcast addresses are not usable host addresses.
Trap categories for this question
Command / output trap
RAG would include raw transaction data (containing PII) in the prompt, exposing PII to the model and potentially in outputs.
Detailed technical explanation
How to think about this question
Subnetting questions test whether you can identify the network, broadcast address, usable range, mask and correct subnet. Slow down enough to calculate the block size correctly.
KKey Concepts to Remember
- CIDR notation defines the prefix length.
- Block size helps identify subnet boundaries.
- Network and broadcast addresses are not usable hosts in normal IPv4 subnets.
- The required host count determines the smallest suitable subnet.
TExam Day Tips
- Write the block size before choosing the subnet.
- Check whether the question asks for hosts, subnets or a specific address range.
- Do not confuse /24, /25, /26 and /27 host counts.
Key takeaway
Count usable hosts — not total addresses — and remember that the network and broadcast addresses are not available to hosts in standard IPv4 subnets.
Real-world example
How this comes up in practice
A cloud solutions architect for a retail company is evaluating services for a new workload. The correct answer here reflects best practice for the specific scenario described — not a general cloud recommendation. Count usable hosts — not total addresses — and remember that the network and broadcast addresses are not available to hosts in standard IPv4 subnets. Cloud exam questions reward reading the constraint carefully: the same technology can be right or wrong depending on the use case.
What to study next
Got this wrong? Here's your next step.
Review block sizes, usable host formulas (2^n − 2), and how to find network and broadcast addresses for /24 through /30. Then practise related AIF-C01 subnetting questions on CIDR, address ranges, and subnet selection.
Related practice questions
Related AIF-C01 practice-question pages
Use these pages to review the topic behind this question. This is how one missed question becomes focused revision.
Applications of Foundation Models practice questions
Practise AIF-C01 questions linked to Applications of Foundation Models.
Fundamentals of AI and ML practice questions
Practise AIF-C01 questions linked to Fundamentals of AI and ML.
Fundamentals of Generative AI practice questions
Practise AIF-C01 questions linked to Fundamentals of Generative AI.
Guidelines for Responsible AI practice questions
Practise AIF-C01 questions linked to Guidelines for Responsible AI.
Security, Compliance and Governance for AI Solutions practice questions
Practise AIF-C01 questions linked to Security, Compliance and Governance for AI Solutions.
AIF-C01 fundamentals practice questions
Practise AIF-C01 questions linked to AIF-C01 fundamentals.
AIF-C01 scenario practice questions
Practise AIF-C01 questions linked to AIF-C01 scenario.
AIF-C01 troubleshooting practice questions
Practise AIF-C01 questions linked to AIF-C01 troubleshooting.
Practice this exam
Start a free AIF-C01 practice session
Short sessions build daily habit. Longer sessions build exam-day stamina. Try a timed session to simulate real conditions.
FAQ
Questions learners often ask
What does this AIF-C01 question test?
CIDR notation defines the prefix length.
What is the correct answer to this question?
The correct answer is: Use a pre-trained foundation model via Amazon Bedrock with a system prompt that instructs the model not to output PII, and enable Bedrock’s data protection — Using Amazon Bedrock with a pre-trained foundation model (no fine-tuning) ensures PII is not in training data. A system prompt instructing the model to avoid PII, combined with Bedrock’s built-in data protection, prevents PII in outputs. Fine-tuning or RAG with sensitive data would risk exposure.
What should I do if I get this AIF-C01 question wrong?
Review block sizes, usable host formulas (2^n − 2), and how to find network and broadcast addresses for /24 through /30. Then practise related AIF-C01 subnetting questions on CIDR, address ranges, and subnet selection.
Are there clue words in this question I should notice?
Yes — watch for: "never". Absolute qualifier. True only if the statement has zero exceptions — be cautious of options that seem obvious but break down in edge cases.
What is the key concept behind this question?
CIDR notation defines the prefix length.
About these practice questions
Courseiva creates original exam-style practice questions with explanations and wrong-answer analysis. It does not publish real exam questions, exam dumps, or protected exam content. Learn why practice questions differ from exam dumps →
Last reviewed: Jul 4, 2026
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.
Question Discussion
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
Sign in to join the discussion.