Exam Bundle

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 Keystone BioLabs correction for: A SageMaker Studio user can create experiments in a production domain even though their intended access is restricted to development. The decisive acceptance check is instead: The development user can create approved experiments in the correct domain but receives AccessDenied for protected production operations.

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 Keystone BioLabs correction for: A SageMaker Studio user can create experiments in a production domain even though their intended access is restricted to development. The decisive acceptance check is instead: The development user can create approved experiments in the correct domain but receives AccessDenied for protected production operations.

A capacity-failure drill scales inference on an approved alternate target while meeting availability and data-residency constraints. This would verify a different operation: Evaluate supported alternate instance families or regional capacity and introduce a tested provisioning fallback compatible with residency rules. That separate action addresses: An ML platform switches all traffic to an accelerated instance type even though the chosen AWS Region has insufficient capacity for peak scaling. It cannot establish the required Keystone BioLabs correction for: A SageMaker Studio user can create experiments in a production domain even though their intended access is restricted to development. The decisive acceptance check is instead: The development user can create approved experiments in the correct domain but receives AccessDenied for protected production operations.

Define seasonal reference windows and calibrated drift thresholds rather than using an inappropriate static training baseline for all periods. It does not directly address the Granite SaaS case: An ML data labeling job grants external workers access to original unmasked patient records even though only de-identified images are required. The relevant acceptance criterion for this case is: A test labeling worker can view only approved anonymized images and cannot retrieve the original patient metadata.

Evaluate supported alternate instance families or regional capacity and introduce a tested provisioning fallback compatible with residency rules. It does not directly address the Granite SaaS case: An ML data labeling job grants external workers access to original unmasked patient records even though only de-identified images are required. The relevant acceptance criterion for this case is: A test labeling worker can view only approved anonymized images and cannot retrieve the original patient metadata.

Monitor the appropriate GPU utilization, memory and throughput metrics for the selected hosting architecture. It does not directly address the Granite SaaS case: An ML data labeling job grants external workers access to original unmasked patient records even though only de-identified images are required. The relevant acceptance criterion for this case is: A test labeling worker can view only approved anonymized images and cannot retrieve the original patient metadata.

An injected malformed feature vector is handled according to policy and creates an attributable monitoring event. This would verify a different operation: Apply input validation with monitored missingness and a documented safe fallback or rejection policy for out-of-contract requests. That separate action addresses: A model receives rare null-heavy inputs in production that were absent from training and a batch of such requests produces unstable predictions. It cannot establish the required Granite SaaS correction for: An ML data labeling job grants external workers access to original unmasked patient records even though only de-identified images are required. The decisive acceptance check is instead: A test labeling worker can view only approved anonymized images and cannot retrieve the original patient metadata.

A cost model using observed utilization demonstrates the break-even point and documents the selected financial tradeoff. This would verify a different operation: Compare actual steady-state resource usage and purchasing alternatives before choosing a suitable commitment or On-Demand strategy. That separate action addresses: A team purchases reserved inference capacity without measuring whether its utilization is predictable enough to offset commitment cost. It cannot establish the required Granite SaaS correction for: An ML data labeling job grants external workers access to original unmasked patient records even though only de-identified images are required. The decisive acceptance check is instead: A test labeling worker can view only approved anonymized images and cannot retrieve the original patient metadata.

A controlled payload replay reproduces the bottleneck and the targeted correction restores throughput without indiscriminate scaling. This would verify a different operation: Correlate payload sizes, invocation mix, ModelLatency and resource metrics to identify the actual throughput constraint. That separate action addresses: A model's endpoint throughput suddenly falls but the operator adds instances before investigating payload size changes in incoming traffic. It cannot establish the required Granite SaaS correction for: An ML data labeling job grants external workers access to original unmasked patient records even though only de-identified images are required. The decisive acceptance check is instead: A test labeling worker can view only approved anonymized images and cannot retrieve the original patient metadata.

Monitor inference request schema and null-value rates against a versioned accepted contract before treating the endpoint as healthy. It does not directly address the Westhaven Retail case: An ML data labeling job grants external workers access to original unmasked patient records even though only de-identified images are required. The relevant acceptance criterion for this case is: A test labeling worker can view only approved anonymized images and cannot retrieve the original patient metadata.

Add model-specific output-validity checks and application error metrics alongside endpoint health measurements. It does not directly address the Westhaven Retail case: An ML data labeling job grants external workers access to original unmasked patient records even though only de-identified images are required. The relevant acceptance criterion for this case is: A test labeling worker can view only approved anonymized images and cannot retrieve the original patient metadata.

Monitor predicted probability buckets against observed outcome frequencies using suitable delayed labels and calibration baselines. It does not directly address the Westhaven Retail case: An ML data labeling job grants external workers access to original unmasked patient records even though only de-identified images are required. The relevant acceptance criterion for this case is: A test labeling worker can view only approved anonymized images and cannot retrieve the original patient metadata.

A tagged cost breakdown identifies the new resource responsible for the measured increase and supports an accountable remediation. This would verify a different operation: Use AWS Cost Explorer and properly applied resource tags to compare endpoint, training and storage cost changes over time. That separate action addresses: An operations team tracks aggregate monthly AWS charges but cannot isolate a sudden cost increase to new model endpoints. It cannot establish the required Westhaven Retail correction for: An ML data labeling job grants external workers access to original unmasked patient records even though only de-identified images are required. The decisive acceptance check is instead: A test labeling worker can view only approved anonymized images and cannot retrieve the original patient metadata.

The nightly workload still meets its completion target while cost reports show reduced idle serving hours. This would verify a different operation: Measure invocation patterns and replace unnecessary continuous capacity with supported scheduled batch or appropriately scaled alternatives. That separate action addresses: An inference workload maintains two always-on high-memory SageMaker endpoints for models invoked only during a brief nightly window. It cannot establish the required Westhaven Retail correction for: An ML data labeling job grants external workers access to original unmasked patient records even though only de-identified images are required. The decisive acceptance check is instead: A test labeling worker can view only approved anonymized images and cannot retrieve the original patient metadata.

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: An ML data labeling job grants external workers access to original unmasked patient records even though only de-identified images are required. The decisive acceptance check is instead: A test labeling worker can view only approved anonymized images and cannot retrieve the original patient metadata.

Track total received records, rejected records and successful predictions with clear denominators across batch processing. It does not directly address the Brookside Manufacturing case: An automated deployment retrieves a production database password from a plaintext environment variable stored in a shared build log. The relevant acceptance criterion for this case is: A production task retrieves its secret with the authorized role while build logs reveal no plaintext credential.

Retain privacy-preserving stable correlation keys through prediction capture and delayed outcome ingestion. It does not directly address the Brookside Manufacturing case: An automated deployment retrieves a production database password from a plaintext environment variable stored in a shared build log. The relevant acceptance criterion for this case is: A production task retrieves its secret with the authorized role while build logs reveal no plaintext credential.

Inspect SageMaker service quotas and scaling target limits and request justified quota changes before increasing traffic. It does not directly address the Brookside Manufacturing case: An automated deployment retrieves a production database password from a plaintext environment variable stored in a shared build log. The relevant acceptance criterion for this case is: A production task retrieves its secret with the authorized role while build logs reveal no plaintext credential.

A controlled payload replay reproduces the bottleneck and the targeted correction restores throughput without indiscriminate scaling. This would verify a different operation: Correlate payload sizes, invocation mix, ModelLatency and resource metrics to identify the actual throughput constraint. That separate action addresses: A model's endpoint throughput suddenly falls but the operator adds instances before investigating payload size changes in incoming traffic. It cannot establish the required Brookside Manufacturing correction for: An automated deployment retrieves a production database password from a plaintext environment variable stored in a shared build log. The decisive acceptance check is instead: A production task retrieves its secret with the authorized role while build logs reveal no plaintext credential.

A missing-feature test request raises the expected data-quality signal and compatible requests retain their normal score output. This would verify a different operation: Monitor inference request schema and null-value rates against a versioned accepted contract before treating the endpoint as healthy. That separate action addresses: A deployed model's training-serving schema changes silently when one upstream feature is renamed, leaving most online predictions based on missing values. It cannot establish the required Brookside Manufacturing correction for: An automated deployment retrieves a production database password from a plaintext environment variable stored in a shared build log. The decisive acceptance check is instead: A production task retrieves its secret with the authorized role while build logs reveal no plaintext credential.

A simulated stale feature feed triggers a dependency alarm even though the SageMaker endpoint remains available. This would verify a different operation: Monitor end-to-end feature freshness, dependency errors and successful business prediction rates in addition to endpoint health. That separate action addresses: Production predictions fail silently during a partial downstream feature outage while endpoint uptime remains normal. It cannot establish the required Brookside Manufacturing correction for: An automated deployment retrieves a production database password from a plaintext environment variable stored in a shared build log. The decisive acceptance check is instead: A production task retrieves its secret with the authorized role while build logs reveal no plaintext credential.

Measure invocation patterns and replace unnecessary continuous capacity with supported scheduled batch or appropriately scaled alternatives. It does not directly address the Bluehaven Transit case: An automated deployment retrieves a production database password from a plaintext environment variable stored in a shared build log. The relevant acceptance criterion for this case is: A production task retrieves its secret with the authorized role while build logs reveal no plaintext credential.

Use pipeline-dependent training resource lifecycle controls with completion-triggered teardown and failure handling. It does not directly address the Bluehaven Transit case: An automated deployment retrieves a production database password from a plaintext environment variable stored in a shared build log. The relevant acceptance criterion for this case is: A production task retrieves its secret with the authorized role while build logs reveal no plaintext credential.

Evaluate supported alternate instance families or regional capacity and introduce a tested provisioning fallback compatible with residency rules. It does not directly address the Bluehaven Transit case: An automated deployment retrieves a production database password from a plaintext environment variable stored in a shared build log. The relevant acceptance criterion for this case is: A production task retrieves its secret with the authorized role while build logs reveal no plaintext credential.

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 Bluehaven Transit correction for: An automated deployment retrieves a production database password from a plaintext environment variable stored in a shared build log. The decisive acceptance check is instead: A production task retrieves its secret with the authorized role while build logs reveal no plaintext credential.

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 Bluehaven Transit correction for: An automated deployment retrieves a production database password from a plaintext environment variable stored in a shared build log. The decisive acceptance check is instead: A production task retrieves its secret with the authorized role while build logs reveal no plaintext credential.

An authorized monitoring sample supports drift analysis and a security scan finds no forbidden raw identifiers in captured payloads. This would verify a different operation: Configure bounded and redacted inference data capture with access controls, sampling and retention matched to monitoring requirements. That separate action addresses: A SageMaker endpoint stores all prediction payloads in logs despite a governance rule prohibiting raw customer identifiers in captured inference data. It cannot establish the required Bluehaven Transit correction for: An automated deployment retrieves a production database password from a plaintext environment variable stored in a shared build log. The decisive acceptance check is instead: A production task retrieves its secret with the authorized role while build logs reveal no plaintext credential.

Define seasonal reference windows and calibrated drift thresholds rather than using an inappropriate static training baseline for all periods. It does not directly address the Northgate Telecom case: A model training job writes regulated outputs to an unencrypted S3 location despite a documented data-at-rest encryption standard. The relevant acceptance criterion for this case is: New output artifacts have the documented KMS key metadata and an attempted unencrypted write is rejected by bucket policy.

Create a SageMaker Model Monitor data-quality baseline and schedule inference feature-distribution checks against it. It does not directly address the Northgate Telecom case: A model training job writes regulated outputs to an unencrypted S3 location despite a documented data-at-rest encryption standard. The relevant acceptance criterion for this case is: New output artifacts have the documented KMS key metadata and an attempted unencrypted write is rejected by bucket policy.

Version monitoring baselines with each released model and capture a reviewed transition policy between old and new expectations. It does not directly address the Northgate Telecom case: A model training job writes regulated outputs to an unencrypted S3 location despite a documented data-at-rest encryption standard. The relevant acceptance criterion for this case is: New output artifacts have the documented KMS key metadata and an attempted unencrypted write is rejected by bucket policy.

A capacity-failure drill scales inference on an approved alternate target while meeting availability and data-residency constraints. This would verify a different operation: Evaluate supported alternate instance families or regional capacity and introduce a tested provisioning fallback compatible with residency rules. That separate action addresses: An ML platform switches all traffic to an accelerated instance type even though the chosen AWS Region has insufficient capacity for peak scaling. It cannot establish the required Northgate Telecom correction for: A model training job writes regulated outputs to an unencrypted S3 location despite a documented data-at-rest encryption standard. The decisive acceptance check is instead: New output artifacts have the documented KMS key metadata and an attempted unencrypted write is rejected by bucket policy.

An injected malformed feature vector is handled according to policy and creates an attributable monitoring event. This would verify a different operation: Apply input validation with monitored missingness and a documented safe fallback or rejection policy for out-of-contract requests. That separate action addresses: A model receives rare null-heavy inputs in production that were absent from training and a batch of such requests produces unstable predictions. It cannot establish the required Northgate Telecom correction for: A model training job writes regulated outputs to an unencrypted S3 location despite a documented data-at-rest encryption standard. The decisive acceptance check is instead: New output artifacts have the documented KMS key metadata and an attempted unencrypted write is rejected by bucket policy.

Objects past the retention window transition or expire as intended while protected evidence remains retrievable. This would verify a different operation: Apply reviewed S3 lifecycle transition and expiration policies aligned to audit retention and replay requirements. That separate action addresses: S3 inference request captures accumulate indefinitely in a costly storage class even after their approved monitoring retention period expires. It cannot establish the required Northgate Telecom correction for: A model training job writes regulated outputs to an unencrypted S3 location despite a documented data-at-rest encryption standard. The decisive acceptance check is instead: New output artifacts have the documented KMS key metadata and an attempted unencrypted write is rejected by bucket policy.