Exam Bundle

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 Juniper Media correction for: An operations dashboard treats a rising model input drift score as proof that prediction correctness already decreased without label evidence. The decisive acceptance check is instead: The monitoring report labels distribution shift and actual error metrics distinctly and does not infer accuracy loss from drift alone.

An authorized tenant role decrypts only its dataset and a cross-tenant key operation is denied. This would verify a different operation: Apply dataset-specific KMS grants or key policies and distinct IAM roles aligned with tenant segregation requirements. That separate action addresses: An ML feature store contains regulated fields encrypted with an AWS KMS key, but a shared role can decrypt every organization's dataset. It cannot establish the required Juniper Media correction for: An operations dashboard treats a rising model input drift score as proof that prediction correctness already decreased without label evidence. The decisive acceptance check is instead: The monitoring report labels distribution shift and actual error metrics distinctly and does not infer accuracy loss from drift alone.

A representative slow request shows the delay attributed to one documented processing stage rather than undifferentiated total time. This would verify a different operation: Instrument authorized distributed traces or structured per-stage timings, using AWS X-Ray where supported, to isolate bottlenecks. That separate action addresses: An ML API has intermittent latency spikes but CloudWatch cannot reveal whether the delay occurs in preprocessing or downstream inference. It cannot establish the required Juniper Media correction for: An operations dashboard treats a rising model input drift score as proof that prediction correctness already decreased without label evidence. The decisive acceptance check is instead: The monitoring report labels distribution shift and actual error metrics distinctly and does not infer accuracy loss from drift alone.

Use comparable inference benchmarks across supported instance families and evaluate total cost per thousand successful requests. It does not directly address the Timberline Foods case: A risk model is deployed with a new model version but its SageMaker Model Monitor schedule continues capturing only the old endpoint variant. The relevant acceptance criterion for this case is: A controlled prediction from the new variant appears in the correct monitoring dataset and the old variant is not mistaken for current.

Integrate ECR image scanning and an enforced reviewed vulnerability acceptance gate before deploying the immutable image digest. It does not directly address the Timberline Foods case: A risk model is deployed with a new model version but its SageMaker Model Monitor schedule continues capturing only the old endpoint variant. The relevant acceptance criterion for this case is: A controlled prediction from the new variant appears in the correct monitoring dataset and the old variant is not mistaken for current.

Use approved private subnets, security groups and VPC endpoints where supported to restrict unnecessary network egress. It does not directly address the Timberline Foods case: A risk model is deployed with a new model version but its SageMaker Model Monitor schedule continues capturing only the old endpoint variant. The relevant acceptance criterion for this case is: A controlled prediction from the new variant appears in the correct monitoring dataset and the old variant is not mistaken for current.

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 Timberline Foods correction for: A risk model is deployed with a new model version but its SageMaker Model Monitor schedule continues capturing only the old endpoint variant. The decisive acceptance check is instead: A controlled prediction from the new variant appears in the correct monitoring dataset and the old variant is not mistaken for current.

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 Timberline Foods correction for: A risk model is deployed with a new model version but its SageMaker Model Monitor schedule continues capturing only the old endpoint variant. The decisive acceptance check is instead: A controlled prediction from the new variant appears in the correct monitoring dataset and the old variant is not mistaken for current.

The revised sweep consumes fewer training hours and still identifies a candidate meeting the accepted validation target. This would verify a different operation: Enable appropriate tuning-job completion limits and early termination policies where supported for the selected metric. That separate action addresses: An expensive SageMaker hyperparameter search continues after clearly underperforming trials without any early stopping or experiment budget. It cannot establish the required Timberline Foods correction for: A risk model is deployed with a new model version but its SageMaker Model Monitor schedule continues capturing only the old endpoint variant. The decisive acceptance check is instead: A controlled prediction from the new variant appears in the correct monitoring dataset and the old variant is not mistaken for current.

Apply dataset-specific KMS grants or key policies and distinct IAM roles aligned with tenant segregation requirements. It does not directly address the Keystone BioLabs case: A risk model is deployed with a new model version but its SageMaker Model Monitor schedule continues capturing only the old endpoint variant. The relevant acceptance criterion for this case is: A controlled prediction from the new variant appears in the correct monitoring dataset and the old variant is not mistaken for current.

Apply consistent project, environment and model cost-allocation tags and activate the corresponding billing reports. It does not directly address the Keystone BioLabs case: A risk model is deployed with a new model version but its SageMaker Model Monitor schedule continues capturing only the old endpoint variant. The relevant acceptance criterion for this case is: A controlled prediction from the new variant appears in the correct monitoring dataset and the old variant is not mistaken for current.

Use pipeline-dependent training resource lifecycle controls with completion-triggered teardown and failure handling. It does not directly address the Keystone BioLabs case: A risk model is deployed with a new model version but its SageMaker Model Monitor schedule continues capturing only the old endpoint variant. The relevant acceptance criterion for this case is: A controlled prediction from the new variant appears in the correct monitoring dataset and the old variant is not mistaken for current.

The revised sweep consumes fewer training hours and still identifies a candidate meeting the accepted validation target. This would verify a different operation: Enable appropriate tuning-job completion limits and early termination policies where supported for the selected metric. That separate action addresses: An expensive SageMaker hyperparameter search continues after clearly underperforming trials without any early stopping or experiment budget. It cannot establish the required Keystone BioLabs correction for: A risk model is deployed with a new model version but its SageMaker Model Monitor schedule continues capturing only the old endpoint variant. The decisive acceptance check is instead: A controlled prediction from the new variant appears in the correct monitoring dataset and the old variant is not mistaken for current.

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 Keystone BioLabs correction for: A risk model is deployed with a new model version but its SageMaker Model Monitor schedule continues capturing only the old endpoint variant. The decisive acceptance check is instead: A controlled prediction from the new variant appears in the correct monitoring dataset and the old variant is not mistaken for current.

A finished training execution releases its compute automatically and leaves only approved persistent artifacts for later evaluation. This would verify a different operation: Use pipeline-dependent training resource lifecycle controls with completion-triggered teardown and failure handling. That separate action addresses: A training environment repeatedly provisions expensive instances after data preparation finishes and leaves them idle until an operator manually stops them. It cannot establish the required Keystone BioLabs correction for: A risk model is deployed with a new model version but its SageMaker Model Monitor schedule continues capturing only the old endpoint variant. The decisive acceptance check is instead: A controlled prediction from the new variant appears in the correct monitoring dataset and the old variant is not mistaken for current.

Apply consistent project, environment and model cost-allocation tags and activate the corresponding billing reports. It does not directly address the Granite SaaS case: A service tracks only average model prediction values while a narrow segment receives systematically poor results that aggregate statistics hide. The relevant acceptance criterion for this case is: A synthetic slice regression is detected even though the overall average metric remains inside its broad threshold.

Enable appropriate tuning-job completion limits and early termination policies where supported for the selected metric. It does not directly address the Granite SaaS case: A service tracks only average model prediction values while a narrow segment receives systematically poor results that aggregate statistics hide. The relevant acceptance criterion for this case is: A synthetic slice regression is detected even though the overall average metric remains inside its broad threshold.

Pin a governed immutable model artifact version and validate checksums or signatures through the approved release process. It does not directly address the Granite SaaS case: A service tracks only average model prediction values while a narrow segment receives systematically poor results that aggregate statistics hide. The relevant acceptance criterion for this case is: A synthetic slice regression is detected even though the overall average metric remains inside its broad threshold.

An authorized tenant role decrypts only its dataset and a cross-tenant key operation is denied. This would verify a different operation: Apply dataset-specific KMS grants or key policies and distinct IAM roles aligned with tenant segregation requirements. That separate action addresses: An ML feature store contains regulated fields encrypted with an AWS KMS key, but a shared role can decrypt every organization's dataset. It cannot establish the required Granite SaaS correction for: A service tracks only average model prediction values while a narrow segment receives systematically poor results that aggregate statistics hide. The decisive acceptance check is instead: A synthetic slice regression is detected even though the overall average metric remains inside its broad threshold.

The runtime writes to the intended log stream but cannot modify an unrelated service's logging resources. This would verify a different operation: Scope CloudWatch log actions to required resource ARNs and separate log configuration permissions from ordinary invocation needs. That separate action addresses: A model deployment can write arbitrary CloudWatch Logs groups because its inference IAM role includes broad administrative logging permissions. It cannot establish the required Granite SaaS correction for: A service tracks only average model prediction values while a narrow segment receives systematically poor results that aggregate statistics hide. The decisive acceptance check is instead: A synthetic slice regression is detected even though the overall average metric remains inside its broad threshold.

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 Granite SaaS correction for: A service tracks only average model prediction values while a narrow segment receives systematically poor results that aggregate statistics hide. The decisive acceptance check is instead: A synthetic slice regression is detected even though the overall average metric remains inside its broad threshold.

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 Westhaven Retail case: A service tracks only average model prediction values while a narrow segment receives systematically poor results that aggregate statistics hide. The relevant acceptance criterion for this case is: A synthetic slice regression is detected even though the overall average metric remains inside its broad threshold.

Correlate payload sizes, invocation mix, ModelLatency and resource metrics to identify the actual throughput constraint. It does not directly address the Westhaven Retail case: A service tracks only average model prediction values while a narrow segment receives systematically poor results that aggregate statistics hide. The relevant acceptance criterion for this case is: A synthetic slice regression is detected even though the overall average metric remains inside its broad threshold.

Evaluate supported alternate instance families or regional capacity and introduce a tested provisioning fallback compatible with residency rules. It does not directly address the Westhaven Retail case: A service tracks only average model prediction values while a narrow segment receives systematically poor results that aggregate statistics hide. The relevant acceptance criterion for this case is: A synthetic slice regression is detected even though the overall average metric remains inside its broad threshold.

The development user can create approved experiments in the correct domain but receives AccessDenied for protected production operations. This would verify a different operation: Apply identity-based domain and resource permission boundaries with segregated workspace roles and least privilege. That separate action addresses: A SageMaker Studio user can create experiments in a production domain even though their intended access is restricted to development. It cannot establish the required Westhaven Retail correction for: A service tracks only average model prediction values while a narrow segment receives systematically poor results that aggregate statistics hide. The decisive acceptance check is instead: A synthetic slice regression is detected even though the overall average metric remains inside its broad threshold.

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: A service tracks only average model prediction values while a narrow segment receives systematically poor results that aggregate statistics hide. The decisive acceptance check is instead: A synthetic slice regression is detected even though the overall average metric remains inside its broad threshold.

An authorized tenant role decrypts only its dataset and a cross-tenant key operation is denied. This would verify a different operation: Apply dataset-specific KMS grants or key policies and distinct IAM roles aligned with tenant segregation requirements. That separate action addresses: An ML feature store contains regulated fields encrypted with an AWS KMS key, but a shared role can decrypt every organization's dataset. It cannot establish the required Westhaven Retail correction for: A service tracks only average model prediction values while a narrow segment receives systematically poor results that aggregate statistics hide. The decisive acceptance check is instead: A synthetic slice regression is detected even though the overall average metric remains inside its broad threshold.

Enable the appropriate S3 Block Public Access configuration and scope bucket access to authorized ML roles. It does not directly address the Brookside Manufacturing case: A SageMaker endpoint stores all prediction payloads in logs despite a governance rule prohibiting raw customer identifiers in captured inference data. The relevant acceptance criterion for this case is: An authorized monitoring sample supports drift analysis and a security scan finds no forbidden raw identifiers in captured payloads.

Apply dataset-specific KMS grants or key policies and distinct IAM roles aligned with tenant segregation requirements. It does not directly address the Brookside Manufacturing case: A SageMaker endpoint stores all prediction payloads in logs despite a governance rule prohibiting raw customer identifiers in captured inference data. The relevant acceptance criterion for this case is: An authorized monitoring sample supports drift analysis and a security scan finds no forbidden raw identifiers in captured payloads.

Evaluate SageMaker Managed Spot Training with checkpointing and compare interruption risk and effective completion cost. It does not directly address the Brookside Manufacturing case: A SageMaker endpoint stores all prediction payloads in logs despite a governance rule prohibiting raw customer identifiers in captured inference data. The relevant acceptance criterion for this case is: An authorized monitoring sample supports drift analysis and a security scan finds no forbidden raw identifiers in captured payloads.

A test model role reads its permitted subset and is denied access to unrelated original customer attributes. This would verify a different operation: Publish an approved data subset or governed view and grant read access only to the required machine learning project roles. That separate action addresses: A team shares a full customer dataset across projects by broadening S3 bucket access instead of providing a minimally scoped training extract. It cannot establish the required Brookside Manufacturing correction for: A SageMaker endpoint stores all prediction payloads in logs despite a governance rule prohibiting raw customer identifiers in captured inference data. The decisive acceptance check is instead: An authorized monitoring sample supports drift analysis and a security scan finds no forbidden raw identifiers in captured payloads.

The inference container accesses authorized model artifacts privately and an external egress test remains blocked. This would verify a different operation: Use approved private subnets, security groups and VPC endpoints where supported to restrict unnecessary network egress. That separate action addresses: A production inference container is placed in subnets with internet egress although its required datasets and dependencies are private AWS services. It cannot establish the required Brookside Manufacturing correction for: A SageMaker endpoint stores all prediction payloads in logs despite a governance rule prohibiting raw customer identifiers in captured inference data. The decisive acceptance check is instead: An authorized monitoring sample supports drift analysis and a security scan finds no forbidden raw identifiers in captured payloads.

The production role loads the shared artifact and a separate untrusted account still receives an access denial. This would verify a different operation: Configure precise cross-account package, S3 and KMS key permissions for the trusted production consumer role. That separate action addresses: A cross-account model registry package is shared with a production account but the referenced encrypted S3 model artifact cannot be decrypted there. It cannot establish the required Brookside Manufacturing correction for: A SageMaker endpoint stores all prediction payloads in logs despite a governance rule prohibiting raw customer identifiers in captured inference data. The decisive acceptance check is instead: An authorized monitoring sample supports drift analysis and a security scan finds no forbidden raw identifiers in captured payloads.