AIF-C01 Guidelines for Responsible AI Practice Question
A financial services company has deployed a machine learning model that approves or denies loan applications in real time. The compliance team requires that any applicant who is denied must receive a meaningful explanation of the decision, and the company must be able to prove which model version and input features produced each decision for audit purposes. Which AWS service should the company use to capture the model's feature attributions and store them for each inference request?
⚠ Common exam trap
The trap here is assuming that a monitoring service such as SageMaker Model Monitor produces per-request explanations, when it only aggregates drift and quality statistics across traffic.
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 SageMaker Clarify with online explainability enabled on the endpoint
Per-decision explainability requires a capability that computes feature attributions at inference time and persists them for audit. SageMaker Clarify online explainability does exactly this inside the endpoint, returning a SHAP-based attribution for each request, and endpoint data capture stores the request and response in Amazon S3. Together they satisfy both the applicant-facing explanation requirement and the internal audit trail obligation.
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 SageMaker Experiments to track the training runs
Why it's wrong here
SageMaker Experiments organizes and tracks training trials, hyperparameters, and metrics so teams can compare model iterations. It is a training-time lineage tool, not a runtime explanation mechanism. It could help prove which model version exists, but it captures nothing about individual inference requests or the feature contributions behind a specific loan decision.
- ✗
Amazon SageMaker Model Monitor with a data quality baseline
Why it's wrong here
Model Monitor compares incoming traffic against statistical baselines to detect data drift, model quality degradation, bias drift, and feature attribution drift over time. It is a monitoring and alerting capability, not a per-request explanation engine. It would tell the company that something changed in aggregate, but it cannot produce a meaningful reason for any single loan denial decision.
- ✓
Amazon SageMaker Clarify with online explainability enabled on the endpoint
Why this is correct
SageMaker Clarify online explainability runs within the endpoint and returns a feature attribution for each individual request, so the company can attach a per-applicant explanation to each denial decision. Combined with endpoint data capture writing to Amazon S3, this produces the per-inference audit record the compliance team requires, tying each decision to the model version and the input features that drove it.
- ✗
AWS CloudTrail data events on the SageMaker endpoint
Why it's wrong here
CloudTrail logs API activity such as InvokeEndpoint calls, including the caller identity, timestamp, and source IP. It records that an inference happened and who requested it, but it does not capture or compute feature attributions. It therefore cannot explain why a particular applicant was denied, which is the core compliance obligation described in the scenario.
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
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 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.