Exam Bundle

A controlled scale-out reaches the revised allowed capacity and queue depth returns to its operating threshold. This would verify a different operation: Inspect SageMaker service quotas and scaling target limits and request justified quota changes before increasing traffic. That separate action addresses: A scaling endpoint's queue grows despite spare traffic capacity because the service hits its allowed instance scaling quota. It cannot establish the required Juniper Media correction for: An ML training execution role has wildcard permission to read every company S3 bucket although it needs one versioned feature prefix. The decisive acceptance check is instead: The training role reads its authorized feature objects but a test access to an unrelated bucket is denied.

A controlled budget threshold scenario generates the intended notice before a hard cost-cap assumption is made. This would verify a different operation: Create AWS Budgets alerts with defined cost thresholds and route notifications to the accountable ML operations owner. That separate action addresses: A budget owner discovers large GPU training overspend only after the invoice arrives because no cost threshold notification exists. It cannot establish the required Juniper Media correction for: An ML training execution role has wildcard permission to read every company S3 bucket although it needs one versioned feature prefix. The decisive acceptance check is instead: The training role reads its authorized feature objects but a test access to an unrelated bucket is denied.

The benchmark identifies the accelerator bottleneck and the selected corrective capacity change reduces inference failures. This would verify a different operation: Monitor the appropriate GPU utilization, memory and throughput metrics for the selected hosting architecture. That separate action addresses: A CloudWatch dashboard claims the inference host is idle because CPU is low, yet GPU memory saturation causes inference throttling. It cannot establish the required Juniper Media correction for: An ML training execution role has wildcard permission to read every company S3 bucket although it needs one versioned feature prefix. The decisive acceptance check is instead: The training role reads its authorized feature objects but a test access to an unrelated bucket is denied.

Evaluate supported alternate instance families or regional capacity and introduce a tested provisioning fallback compatible with residency rules. It does not directly address the Alpine Healthcare case: An ML training execution role has wildcard permission to read every company S3 bucket although it needs one versioned feature prefix. The relevant acceptance criterion for this case is: The training role reads its authorized feature objects but a test access to an unrelated bucket is denied.

Track high-percentile ModelLatency and relevant invocation or backlog metrics with thresholds based on the service-level objective. It does not directly address the Alpine Healthcare case: An ML training execution role has wildcard permission to read every company S3 bucket although it needs one versioned feature prefix. The relevant acceptance criterion for this case is: The training role reads its authorized feature objects but a test access to an unrelated bucket is denied.

Use AWS Cost Explorer and properly applied resource tags to compare endpoint, training and storage cost changes over time. It does not directly address the Alpine Healthcare case: An ML training execution role has wildcard permission to read every company S3 bucket although it needs one versioned feature prefix. The relevant acceptance criterion for this case is: The training role reads its authorized feature objects but a test access to an unrelated bucket is denied.

Cost Explorer separates test and production project charges by approved tags without assigning shared costs to the wrong team. This would verify a different operation: Apply consistent project, environment and model cost-allocation tags and activate the corresponding billing reports. That separate action addresses: A team attributes all SageMaker training expenses to a shared account and cannot explain spending differences across model projects. It cannot establish the required Alpine Healthcare correction for: An ML training execution role has wildcard permission to read every company S3 bucket although it needs one versioned feature prefix. The decisive acceptance check is instead: The training role reads its authorized feature objects but a test access to an unrelated bucket is denied.

The benchmark identifies the accelerator bottleneck and the selected corrective capacity change reduces inference failures. This would verify a different operation: Monitor the appropriate GPU utilization, memory and throughput metrics for the selected hosting architecture. That separate action addresses: A CloudWatch dashboard claims the inference host is idle because CPU is low, yet GPU memory saturation causes inference throttling. It cannot establish the required Alpine Healthcare correction for: An ML training execution role has wildcard permission to read every company S3 bucket although it needs one versioned feature prefix. The decisive acceptance check is instead: The training role reads its authorized feature objects but a test access to an unrelated bucket is denied.

The monitoring report labels distribution shift and actual error metrics distinctly and does not infer accuracy loss from drift alone. This would verify a different operation: Distinguish covariate drift from verified performance degradation and evaluate outcome labels and model-quality metrics separately. That separate action addresses: An operations dashboard treats a rising model input drift score as proof that prediction correctness already decreased without label evidence. It cannot establish the required Alpine Healthcare correction for: An ML training execution role has wildcard permission to read every company S3 bucket although it needs one versioned feature prefix. The decisive acceptance check is instead: The training role reads its authorized feature objects but a test access to an unrelated bucket is denied.

Enable appropriate tuning-job completion limits and early termination policies where supported for the selected metric. It does not directly address the Keystone BioLabs case: A cross-account model registry package is shared with a production account but the referenced encrypted S3 model artifact cannot be decrypted there. The relevant acceptance criterion for this case is: The production role loads the shared artifact and a separate untrusted account still receives an access denial.

Run shadow or controlled A/B inference comparisons with logged model version and matched request IDs before full rollout. It does not directly address the Keystone BioLabs case: A cross-account model registry package is shared with a production account but the referenced encrypted S3 model artifact cannot be decrypted there. The relevant acceptance criterion for this case is: The production role loads the shared artifact and a separate untrusted account still receives an access denial.

Track high-percentile ModelLatency and relevant invocation or backlog metrics with thresholds based on the service-level objective. It does not directly address the Keystone BioLabs case: A cross-account model registry package is shared with a production account but the referenced encrypted S3 model artifact cannot be decrypted there. The relevant acceptance criterion for this case is: The production role loads the shared artifact and a separate untrusted account still receives an access denial.

The monitoring metadata links the live model package to its correct reviewed baseline and tests produce expected alerts. This would verify a different operation: Version monitoring baselines with each released model and capture a reviewed transition policy between old and new expectations. That separate action addresses: A model owner uses one unversioned monitoring baseline for every retraining run, so legitimate model improvements trigger constant false alarms. It cannot establish the required Keystone BioLabs correction for: A cross-account model registry package is shared with a production account but the referenced encrypted S3 model artifact cannot be decrypted there. The decisive acceptance check is instead: The production role loads the shared artifact and a separate untrusted account still receives an access denial.

A load test that violates the p99 target triggers an alarm even though mean latency remains acceptable. This would verify a different operation: Track high-percentile ModelLatency and relevant invocation or backlog metrics with thresholds based on the service-level objective. That separate action addresses: An endpoint's p99 latency increases during bursts but CloudWatch averages look stable and no tail-latency alarm is configured. It cannot establish the required Keystone BioLabs correction for: A cross-account model registry package is shared with a production account but the referenced encrypted S3 model artifact cannot be decrypted there. The decisive acceptance check is instead: The production role loads the shared artifact and a separate untrusted account still receives an access denial.

The selected instance meets the latency requirement with measured lower normalized cost than the oversized GPU option. This would verify a different operation: Use comparable inference benchmarks across supported instance families and evaluate total cost per thousand successful requests. That separate action addresses: An enterprise ML team assumes a larger GPU instance always reduces cost although the model is small and memory bandwidth is not a bottleneck. It cannot establish the required Keystone BioLabs correction for: A cross-account model registry package is shared with a production account but the referenced encrypted S3 model artifact cannot be decrypted there. The decisive acceptance check is instead: The production role loads the shared artifact and a separate untrusted account still receives an access denial.

Apply input validation with monitored missingness and a documented safe fallback or rejection policy for out-of-contract requests. It does not directly address the Timberline Foods case: A cross-account model registry package is shared with a production account but the referenced encrypted S3 model artifact cannot be decrypted there. The relevant acceptance criterion for this case is: The production role loads the shared artifact and a separate untrusted account still receives an access denial.

Review artifact location, cache or image-layer design and choose a supported reuse strategy consistent with version integrity. It does not directly address the Timberline Foods case: A cross-account model registry package is shared with a production account but the referenced encrypted S3 model artifact cannot be decrypted there. The relevant acceptance criterion for this case is: The production role loads the shared artifact and a separate untrusted account still receives an access denial.

Use pipeline-dependent training resource lifecycle controls with completion-triggered teardown and failure handling. It does not directly address the Timberline Foods case: A cross-account model registry package is shared with a production account but the referenced encrypted S3 model artifact cannot be decrypted there. The relevant acceptance criterion for this case is: The production role loads the shared artifact and a separate untrusted account still receives an access denial.

A synthetic slice regression is detected even though the overall average metric remains inside its broad threshold. This would verify a different operation: Create monitored business slices and evaluate approved per-segment metrics and bias indicators using retained ground-truth labels. That separate action addresses: A service tracks only average model prediction values while a narrow segment receives systematically poor results that aggregate statistics hide. It cannot establish the required Timberline Foods correction for: A cross-account model registry package is shared with a production account but the referenced encrypted S3 model artifact cannot be decrypted there. The decisive acceptance check is instead: The production role loads the shared artifact and a separate untrusted account still receives an access denial.

A controlled disparity case is surfaced by the intended bias metric and the report records sample sizes and review limitations. This would verify a different operation: Use appropriate SageMaker Clarify post-training bias measures and valid governed outcome data with documented fairness interpretation. That separate action addresses: A post-deployment bias analysis aggregates only predictions while never comparing their distribution with relevant protected-group outcomes. It cannot establish the required Timberline Foods correction for: A cross-account model registry package is shared with a production account but the referenced encrypted S3 model artifact cannot be decrypted there. The decisive acceptance check is instead: The production role loads the shared artifact and a separate untrusted account still receives an access denial.

A controlled shifted feature batch triggers the intended drift alert while a reference batch remains within its baseline threshold. This would verify a different operation: Create a SageMaker Model Monitor data-quality baseline and schedule inference feature-distribution checks against it. That separate action addresses: A customer churn model starts receiving features with a distribution that differs sharply from training, but the endpoint tracks only CPU and availability. It cannot establish the required Timberline Foods correction for: A cross-account model registry package is shared with a production account but the referenced encrypted S3 model artifact cannot be decrypted there. The decisive acceptance check is instead: The production role loads the shared artifact and a separate untrusted account still receives an access denial.

Create a SageMaker Model Monitor data-quality baseline and schedule inference feature-distribution checks against it. It does not directly address the Westhaven Retail case: A SageMaker notebook user stores long-lived AWS credentials in the notebook source so other project members can inspect them. The relevant acceptance criterion for this case is: A code scan finds no static secret and the notebook's execution role can use only its intended dataset resources.

Apply consistent project, environment and model cost-allocation tags and activate the corresponding billing reports. It does not directly address the Westhaven Retail case: A SageMaker notebook user stores long-lived AWS credentials in the notebook source so other project members can inspect them. The relevant acceptance criterion for this case is: A code scan finds no static secret and the notebook's execution role can use only its intended dataset resources.

Enable appropriate tuning-job completion limits and early termination policies where supported for the selected metric. It does not directly address the Westhaven Retail case: A SageMaker notebook user stores long-lived AWS credentials in the notebook source so other project members can inspect them. The relevant acceptance criterion for this case is: A code scan finds no static secret and the notebook's execution role can use only its intended dataset resources.

A normal seasonal replay stays below the reviewed alert threshold and an injected abnormal shift still produces an alert. This would verify a different operation: Define seasonal reference windows and calibrated drift thresholds rather than using an inappropriate static training baseline for all periods. That separate action addresses: A model monitoring job alerts on every small weekly seasonal variation and overwhelms operators despite meeting business quality requirements. It cannot establish the required Westhaven Retail correction for: A SageMaker notebook user stores long-lived AWS credentials in the notebook source so other project members can inspect them. The decisive acceptance check is instead: A code scan finds no static secret and the notebook's execution role can use only its intended dataset resources.

A representative request cohort produces traceable per-model score differences and unacceptable changes block promotion. This would verify a different operation: Run shadow or controlled A/B inference comparisons with logged model version and matched request IDs before full rollout. That separate action addresses: A retrained model is deployed without comparing its output distributions with the approved production model, causing unexplained score shifts. It cannot establish the required Westhaven Retail correction for: A SageMaker notebook user stores long-lived AWS credentials in the notebook source so other project members can inspect them. The decisive acceptance check is instead: A code scan finds no static secret and the notebook's execution role can use only its intended dataset resources.

A reference set with known labels produces a measurable recall trend and an agreed quality alert fires when the threshold is breached. This would verify a different operation: Create a governed delayed-label collection path and compare production predictions with matched observed labels for model quality monitoring. That separate action addresses: A production classifier's false-negative rate rises over several months, but predictions are logged without collecting any eventual ground-truth outcomes. It cannot establish the required Westhaven Retail correction for: A SageMaker notebook user stores long-lived AWS credentials in the notebook source so other project members can inspect them. The decisive acceptance check is instead: A code scan finds no static secret and the notebook's execution role can use only its intended dataset resources.

Create a SageMaker Model Monitor data-quality baseline and schedule inference feature-distribution checks against it. It does not directly address the Granite SaaS case: A SageMaker notebook user stores long-lived AWS credentials in the notebook source so other project members can inspect them. The relevant acceptance criterion for this case is: A code scan finds no static secret and the notebook's execution role can use only its intended dataset resources.

Choose a suitable minimum serving capacity or compatible hosting method and validate the idle-cost versus cold-start tradeoff. It does not directly address the Granite SaaS case: A SageMaker notebook user stores long-lived AWS credentials in the notebook source so other project members can inspect them. The relevant acceptance criterion for this case is: A code scan finds no static secret and the notebook's execution role can use only its intended dataset resources.

Monitor predicted probability buckets against observed outcome frequencies using suitable delayed labels and calibration baselines. It does not directly address the Granite SaaS case: A SageMaker notebook user stores long-lived AWS credentials in the notebook source so other project members can inspect them. The relevant acceptance criterion for this case is: A code scan finds no static secret and the notebook's execution role can use only its intended dataset resources.

A controlled malformed-input batch is counted in the rejection metric and overall error reporting includes all attempted records. This would verify a different operation: Track total received records, rejected records and successful predictions with clear denominators across batch processing. That separate action addresses: A batch prediction system drops malformed records but the monitoring report tracks only successfully scored inputs and understates total error rate. It cannot establish the required Granite SaaS correction for: A SageMaker notebook user stores long-lived AWS credentials in the notebook source so other project members can inspect them. The decisive acceptance check is instead: A code scan finds no static secret and the notebook's execution role can use only its intended dataset resources.

A controlled disparity case is surfaced by the intended bias metric and the report records sample sizes and review limitations. This would verify a different operation: Use appropriate SageMaker Clarify post-training bias measures and valid governed outcome data with documented fairness interpretation. That separate action addresses: A post-deployment bias analysis aggregates only predictions while never comparing their distribution with relevant protected-group outcomes. It cannot establish the required Granite SaaS correction for: A SageMaker notebook user stores long-lived AWS credentials in the notebook source so other project members can inspect them. The decisive acceptance check is instead: A code scan finds no static secret and the notebook's execution role can use only its intended dataset resources.

A controlled missing-lookup request produces a measurable model-error event rather than being counted as a valid prediction. This would verify a different operation: Add model-specific output-validity checks and application error metrics alongside endpoint health measurements. That separate action addresses: A model serving container returns HTTP 200 for all requests even when its predictor emits empty outputs due to a failed feature lookup. It cannot establish the required Granite SaaS correction for: A SageMaker notebook user stores long-lived AWS credentials in the notebook source so other project members can inspect them. The decisive acceptance check is instead: A code scan finds no static secret and the notebook's execution role can use only its intended dataset resources.