AIF-C01 Guidelines for Responsible AI Practice Question
A retail bank is deploying an Amazon SageMaker model that recommends credit limit increases to existing cardholders. The bank's responsible AI review board requires that the model's decisions be explainable to customers who request an adverse action notice, and that the team be able to detect whether any single input feature is disproportionately driving predictions. Which TWO capabilities should the team implement to meet these requirements? (Choose two.)
⚠ Common exam trap
The trap here is treating SageMaker Model Monitor as a fairness tool, when it only detects input or output drift and does not compute feature attributions or bias metrics.
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 SageMaker Clarify explainability to generate SHAP-based feature attributions for individual predictions
SageMaker Clarify provides both SHAP-based per-prediction explanations and bias metrics such as disparate impact and feature importance. Together they let the bank produce customer-facing adverse action reasons and detect whether a particular feature disproportionately drives decisions. Model Monitor, Debugger, and load balancer controls address drift, training internals, and traffic security rather than explainability or fairness.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Enable SageMaker Debugger to capture tensor values during training
Why it's wrong here
SageMaker Debugger captures tensors, gradients, and resource utilization during training to diagnose convergence and performance issues. It operates on the training job internals, not on the fairness or explainability of final predictions. Debugger output would not produce customer-facing reasons or group-level bias metrics, so it does not meet the review board's requirements.
- ✓
Use SageMaker Clarify explainability to generate SHAP-based feature attributions for individual predictions
Why this is correct
SageMaker Clarify explainability computes SHAP values that quantify how much each input feature contributed to a specific prediction. For adverse action notices, this gives the bank concrete per-customer reasons, such as utilization rate or recent delinquencies, that drove the credit limit decision. It directly supports the explainability requirement at the individual prediction level.
- ✓
Run SageMaker Clarify bias detection to measure feature importance and disparate impact across groups
Why this is correct
SageMaker Clarify bias detection reports metrics such as disparate impact, difference in positive proportions, and feature importance across defined groups. This allows the bank to see whether a protected attribute or a proxy feature disproportionately influences outcomes, meeting the requirement to detect any single feature driving predictions. It complements per-prediction explanations with dataset-level fairness analysis.
- ✗
Deploy the model behind an Application Load Balancer with AWS WAF for request filtering
Why it's wrong here
An Application Load Balancer with AWS WAF provides traffic distribution and protection against malicious requests. These are security and availability controls and have no bearing on model explainability or bias detection. Adding them would not help the bank explain credit decisions to customers or identify features that disproportionately affect outcomes.
- ✗
Configure SageMaker Model Monitor to track feature drift against a baseline distribution
Why it's wrong here
Model Monitor detects when input feature distributions drift from the training baseline, which is valuable for operational health. It does not explain individual predictions or identify which feature drives a given decision. While drift monitoring is part of a mature MLOps practice, it does not satisfy the adverse action explainability or feature attribution requirements described.
Go deeper
Related to this question
About these practice questions
One of 862 original AIF-C01 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. 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.