Exam Bundle

A controlled endpoint configuration change yields an attributable CloudTrail event retained at the authorized destination. This would verify a different operation: Enable appropriate organization or account CloudTrail trails with secure retention and access controls for relevant management events. That separate action addresses: A security auditor cannot trace who modified a SageMaker endpoint because AWS CloudTrail event retention and organization trails were never configured. It cannot establish the required Timberline Foods correction for: A training environment repeatedly provisions expensive instances after data preparation finishes and leaves them idle until an operator manually stops them. The decisive acceptance check is instead: A finished training execution releases its compute automatically and leaves only approved persistent artifacts for later evaluation.

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 Timberline Foods correction for: A training environment repeatedly provisions expensive instances after data preparation finishes and leaves them idle until an operator manually stops them. The decisive acceptance check is instead: A finished training execution releases its compute automatically and leaves only approved persistent artifacts for later evaluation.

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 Timberline Foods correction for: A training environment repeatedly provisions expensive instances after data preparation finishes and leaves them idle until an operator manually stops them. The decisive acceptance check is instead: A finished training execution releases its compute automatically and leaves only approved persistent artifacts for later evaluation.

Configure bounded and redacted inference data capture with access controls, sampling and retention matched to monitoring requirements. It does not directly address the Keystone BioLabs case: A training environment repeatedly provisions expensive instances after data preparation finishes and leaves them idle until an operator manually stops them. The relevant acceptance criterion for this case is: A finished training execution releases its compute automatically and leaves only approved persistent artifacts for later evaluation.

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 training environment repeatedly provisions expensive instances after data preparation finishes and leaves them idle until an operator manually stops them. The relevant acceptance criterion for this case is: A finished training execution releases its compute automatically and leaves only approved persistent artifacts for later evaluation.

Enforce protected build contexts, isolated untrusted code execution and restricted deployment credentials available only after review. It does not directly address the Keystone BioLabs case: A training environment repeatedly provisions expensive instances after data preparation finishes and leaves them idle until an operator manually stops them. The relevant acceptance criterion for this case is: A finished training execution releases its compute automatically and leaves only approved persistent artifacts for later evaluation.

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 Keystone BioLabs correction for: A training environment repeatedly provisions expensive instances after data preparation finishes and leaves them idle until an operator manually stops them. The decisive acceptance check is instead: A finished training execution releases its compute automatically and leaves only approved persistent artifacts for later evaluation.

A training role cannot approve its own model package and a designated release role can promote a reviewed version. This would verify a different operation: Separate training, model approval and production deployment identities with explicit role and approval boundaries. That separate action addresses: A machine learning pipeline uses a single IAM role to train models, approve registry packages and update production endpoints. It cannot establish the required Keystone BioLabs correction for: A training environment repeatedly provisions expensive instances after data preparation finishes and leaves them idle until an operator manually stops them. The decisive acceptance check is instead: A finished training execution releases its compute automatically and leaves only approved persistent artifacts for later evaluation.

The assignment audit shows representative variant groups and the evaluation respects the intended statistical comparison design. This would verify a different operation: Use consistent random traffic allocation and analyze outcomes per experimental assignment and predefined business slices. That separate action addresses: A production A/B test compares models on different customer cohorts without controlling allocation, making observed performance differences misleading. It cannot establish the required Keystone BioLabs correction for: A training environment repeatedly provisions expensive instances after data preparation finishes and leaves them idle until an operator manually stops them. The decisive acceptance check is instead: A finished training execution releases its compute automatically and leaves only approved persistent artifacts for later evaluation.

Use approved private subnets, security groups and VPC endpoints where supported to restrict unnecessary network egress. It does not directly address the Granite SaaS case: A team purchases reserved inference capacity without measuring whether its utilization is predictable enough to offset commitment cost. The relevant acceptance criterion for this case is: A cost model using observed utilization demonstrates the break-even point and documents the selected financial tradeoff.

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 Granite SaaS case: A team purchases reserved inference capacity without measuring whether its utilization is predictable enough to offset commitment cost. The relevant acceptance criterion for this case is: A cost model using observed utilization demonstrates the break-even point and documents the selected financial tradeoff.

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 Granite SaaS case: A team purchases reserved inference capacity without measuring whether its utilization is predictable enough to offset commitment cost. The relevant acceptance criterion for this case is: A cost model using observed utilization demonstrates the break-even point and documents the selected financial tradeoff.

A test labeling worker can view only approved anonymized images and cannot retrieve the original patient metadata. This would verify a different operation: Use governed de-identification and scoped labeling-access controls before creating the labeling workforce task. That separate action addresses: An ML data labeling job grants external workers access to original unmasked patient records even though only de-identified images are required. It cannot establish the required Granite SaaS correction for: A team purchases reserved inference capacity without measuring whether its utilization is predictable enough to offset commitment cost. The decisive acceptance check is instead: A cost model using observed utilization demonstrates the break-even point and documents the selected financial tradeoff.

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 Granite SaaS correction for: A team purchases reserved inference capacity without measuring whether its utilization is predictable enough to offset commitment cost. The decisive acceptance check is instead: A cost model using observed utilization demonstrates the break-even point and documents the selected financial tradeoff.

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 team purchases reserved inference capacity without measuring whether its utilization is predictable enough to offset commitment cost. The decisive acceptance check is instead: A cost model using observed utilization demonstrates the break-even point and documents the selected financial tradeoff.

Use governed de-identification and scoped labeling-access controls before creating the labeling workforce task. It does not directly address the Westhaven Retail case: A team purchases reserved inference capacity without measuring whether its utilization is predictable enough to offset commitment cost. The relevant acceptance criterion for this case is: A cost model using observed utilization demonstrates the break-even point and documents the selected financial tradeoff.

Monitor end-to-end feature freshness, dependency errors and successful business prediction rates in addition to endpoint health. It does not directly address the Westhaven Retail case: A team purchases reserved inference capacity without measuring whether its utilization is predictable enough to offset commitment cost. The relevant acceptance criterion for this case is: A cost model using observed utilization demonstrates the break-even point and documents the selected financial tradeoff.

Use approved private subnets, security groups and VPC endpoints where supported to restrict unnecessary network egress. It does not directly address the Westhaven Retail case: A team purchases reserved inference capacity without measuring whether its utilization is predictable enough to offset commitment cost. The relevant acceptance criterion for this case is: A cost model using observed utilization demonstrates the break-even point and documents the selected financial tradeoff.

A training role cannot approve its own model package and a designated release role can promote a reviewed version. This would verify a different operation: Separate training, model approval and production deployment identities with explicit role and approval boundaries. That separate action addresses: A machine learning pipeline uses a single IAM role to train models, approve registry packages and update production endpoints. It cannot establish the required Westhaven Retail correction for: A team purchases reserved inference capacity without measuring whether its utilization is predictable enough to offset commitment cost. The decisive acceptance check is instead: A cost model using observed utilization demonstrates the break-even point and documents the selected financial tradeoff.

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 team purchases reserved inference capacity without measuring whether its utilization is predictable enough to offset commitment cost. The decisive acceptance check is instead: A cost model using observed utilization demonstrates the break-even point and documents the selected financial tradeoff.

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 Westhaven Retail correction for: A team purchases reserved inference capacity without measuring whether its utilization is predictable enough to offset commitment cost. The decisive acceptance check is instead: A cost model using observed utilization demonstrates the break-even point and documents the selected financial tradeoff.

Track total received records, rejected records and successful predictions with clear denominators across batch processing. It does not directly address the Brookside Manufacturing case: S3 inference request captures accumulate indefinitely in a costly storage class even after their approved monitoring retention period expires. The relevant acceptance criterion for this case is: Objects past the retention window transition or expire as intended while protected evidence remains retrievable.

Use consistent random traffic allocation and analyze outcomes per experimental assignment and predefined business slices. It does not directly address the Brookside Manufacturing case: S3 inference request captures accumulate indefinitely in a costly storage class even after their approved monitoring retention period expires. The relevant acceptance criterion for this case is: Objects past the retention window transition or expire as intended while protected evidence remains retrievable.

Publish an approved data subset or governed view and grant read access only to the required machine learning project roles. It does not directly address the Brookside Manufacturing case: S3 inference request captures accumulate indefinitely in a costly storage class even after their approved monitoring retention period expires. The relevant acceptance criterion for this case is: Objects past the retention window transition or expire as intended while protected evidence remains retrievable.

A controlled event's original prediction joins to the matching eventual label without exposing unauthorized personal identifiers. This would verify a different operation: Retain privacy-preserving stable correlation keys through prediction capture and delayed outcome ingestion. That separate action addresses: An inference monitoring workflow cannot associate captured predictions with later labels because request identifiers are stripped during processing. It cannot establish the required Brookside Manufacturing correction for: S3 inference request captures accumulate indefinitely in a costly storage class even after their approved monitoring retention period expires. The decisive acceptance check is instead: Objects past the retention window transition or expire as intended while protected evidence remains retrievable.

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 Brookside Manufacturing correction for: S3 inference request captures accumulate indefinitely in a costly storage class even after their approved monitoring retention period expires. The decisive acceptance check is instead: Objects past the retention window transition or expire as intended while protected evidence remains retrievable.

New output artifacts have the documented KMS key metadata and an attempted unencrypted write is rejected by bucket policy. This would verify a different operation: Require appropriate SSE-KMS settings on the output bucket and ensure the training role is authorized to use the chosen key. That separate action addresses: A model training job writes regulated outputs to an unencrypted S3 location despite a documented data-at-rest encryption standard. It cannot establish the required Brookside Manufacturing correction for: S3 inference request captures accumulate indefinitely in a costly storage class even after their approved monitoring retention period expires. The decisive acceptance check is instead: Objects past the retention window transition or expire as intended while protected evidence remains retrievable.

Create a governed delayed-label collection path and compare production predictions with matched observed labels for model quality monitoring. It does not directly address the Bluehaven Transit case: S3 inference request captures accumulate indefinitely in a costly storage class even after their approved monitoring retention period expires. The relevant acceptance criterion for this case is: Objects past the retention window transition or expire as intended while protected evidence remains retrievable.

Enable the appropriate S3 Block Public Access configuration and scope bucket access to authorized ML roles. It does not directly address the Bluehaven Transit case: S3 inference request captures accumulate indefinitely in a costly storage class even after their approved monitoring retention period expires. The relevant acceptance criterion for this case is: Objects past the retention window transition or expire as intended while protected evidence remains retrievable.

Use consistent random traffic allocation and analyze outcomes per experimental assignment and predefined business slices. It does not directly address the Bluehaven Transit case: S3 inference request captures accumulate indefinitely in a costly storage class even after their approved monitoring retention period expires. The relevant acceptance criterion for this case is: Objects past the retention window transition or expire as intended while protected evidence remains retrievable.

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 Bluehaven Transit correction for: S3 inference request captures accumulate indefinitely in a costly storage class even after their approved monitoring retention period expires. The decisive acceptance check is instead: Objects past the retention window transition or expire as intended while protected evidence remains retrievable.

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 Bluehaven Transit correction for: S3 inference request captures accumulate indefinitely in a costly storage class even after their approved monitoring retention period expires. The decisive acceptance check is instead: Objects past the retention window transition or expire as intended while protected evidence remains retrievable.

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 Bluehaven Transit correction for: S3 inference request captures accumulate indefinitely in a costly storage class even after their approved monitoring retention period expires. The decisive acceptance check is instead: Objects past the retention window transition or expire as intended while protected evidence remains retrievable.