AIF-C01 Fundamentals of Generative AI Practice Question
A financial services company is subject to strict regulatory requirements. They plan to use generative AI to summarize customer interaction logs. Which combination of AWS services and configurations best ensures compliance while maintaining accuracy?
⚠ Common exam trap
A common misconception is that encryption alone ensures compliance. However, the trap here is that public internet access (even with HTTPS) violates strict regulatory requirements that mandate private network connectivity (via VPC endpoints) and data residency controls.
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 with a private VPC endpoint, AWS KMS encryption, and content filtering.
It combines a private VPC endpoint to keep all traffic within the AWS network (avoiding public internet exposure), AWS KMS encryption for data at rest and in transit, and content filtering to block sensitive or non-compliant outputs. This architecture meets strict regulatory requirements for data privacy and security while using Amazon Bedrock's managed foundation models for accurate summarization.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Deploy an open-source model on Amazon Bedrock in a local on-premises server.
Why it's wrong here
Amazon Bedrock is a fully managed AWS service; it cannot be deployed on a local on-premises server, so this configuration is impossible. It is tempting because on-premises hosting can satisfy strict data-residency rules, and that would be the right approach if the requirement were to keep all data within the company's own data centre.
- ✗
Use Amazon Bedrock with a foundation model and public internet access without encryption.
Why it's wrong here
Public internet access without encryption transmits customer interaction logs in plaintext, violating the confidentiality and data-protection controls the regulator requires. Bedrock with a foundation model is tempting because it delivers accurate summaries with minimal operational effort, and it would be correct when paired with private networking and encryption.
- ✗
Use Amazon SageMaker to host a fine-tuned model with a public API key.
Why it's wrong here
A public API key exposes the summarisation endpoint to anyone, breaching the access-control and confidentiality obligations that strict financial regulation imposes. Fine-tuning on SageMaker is tempting because it improves summarisation accuracy on domain-specific logs, and it would be correct where accuracy matters but the endpoint is secured with authenticated, private access.
- ✓
Use Amazon Bedrock with a private VPC endpoint, AWS KMS encryption, and content filtering.
Why this is correct
A private VPC endpoint keeps traffic off the public internet, KMS encryption protects data at rest and in transit, and content filtering blocks sensitive output, together meeting the strict regulatory constraints while Bedrock summarises the logs.
Visual reference
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.