AIF-C01 Applications of Foundation Models Practice Question
A healthcare company uses Amazon Bedrock to generate patient summaries. They need to ensure no protected health information (PHI) is leaked in the output. Which AWS service can they use to detect and mask PHI in text?
⚠ Common exam trap
AWS often tests the distinction between general-purpose data protection services (like Macie) and domain-specific medical NLP services (like Comprehend Medical), leading candidates to choose Macie because it is associated with sensitive data discovery, even though it cannot perform inline text masking.
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
✓
Amazon Comprehend Medical
Amazon Comprehend Medical is specifically designed to extract and identify protected health information (PHI) from unstructured medical text using natural language processing (NLP). It can detect entities such as patient names, dates, medical conditions, and medications, and provides APIs to mask or redact that PHI before output. This makes it the correct choice for the healthcare company's requirement to prevent PHI leakage in patient summaries generated by Amazon Bedrock.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Amazon Comprehend Medical
Why this is correct
Amazon Comprehend Medical applies natural language processing purpose-built for clinical text, detecting protected health information such as names, dates and medical record numbers, then masking it. This directly satisfies the requirement to prevent PHI leakage in generated patient summaries.
- ✗
Amazon Macie
Why it's wrong here
Amazon Macie discovers and classifies sensitive data in Amazon S3, not in Bedrock's generated text responses. It is tempting because Macie detects PII and PHI in stored objects, which suits S3 data-discovery audits, but it cannot inspect or mask the model's runtime output.
- ✗
AWS Glue
Why it's wrong here
AWS Glue is an ETL service that catalogues and transforms data; it performs no PHI detection or masking on generated text. It is tempting because Glue can run Spark jobs over data stores, but that suits building pipelines, not inspecting Bedrock output for protected health information.
- ✗
Amazon Rekognition
Why it's wrong here
Amazon Rekognition analyses images and video, so it cannot detect or mask PHI within text output. It is tempting because Rekognition does content moderation and face detection, which suits media pipelines, but the scenario requires text analysis, which Rekognition does not perform.
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.