Exam Bundle

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 Pinecrest Hotels correction for: A model monitoring job alerts on every small weekly seasonal variation and overwhelms operators despite meeting business quality requirements. The decisive acceptance check is instead: A normal seasonal replay stays below the reviewed alert threshold and an injected abnormal shift still produces an alert.

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 Pinecrest Hotels correction for: A model monitoring job alerts on every small weekly seasonal variation and overwhelms operators despite meeting business quality requirements. The decisive acceptance check is instead: A normal seasonal replay stays below the reviewed alert threshold and an injected abnormal shift still produces an alert.

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 Pinecrest Hotels correction for: A model monitoring job alerts on every small weekly seasonal variation and overwhelms operators despite meeting business quality requirements. The decisive acceptance check is instead: A normal seasonal replay stays below the reviewed alert threshold and an injected abnormal shift still produces an alert.

Use pipeline-dependent training resource lifecycle controls with completion-triggered teardown and failure handling. It does not directly address the Oakridge Public Services case: A retrained model is deployed without comparing its output distributions with the approved production model, causing unexplained score shifts. The relevant acceptance criterion for this case is: A representative request cohort produces traceable per-model score differences and unacceptable changes block promotion.

Require appropriate SSE-KMS settings on the output bucket and ensure the training role is authorized to use the chosen key. It does not directly address the Oakridge Public Services case: A retrained model is deployed without comparing its output distributions with the approved production model, causing unexplained score shifts. The relevant acceptance criterion for this case is: A representative request cohort produces traceable per-model score differences and unacceptable changes block promotion.

Evaluate supported alternate instance families or regional capacity and introduce a tested provisioning fallback compatible with residency rules. It does not directly address the Oakridge Public Services case: A retrained model is deployed without comparing its output distributions with the approved production model, causing unexplained score shifts. The relevant acceptance criterion for this case is: A representative request cohort produces traceable per-model score differences and unacceptable changes block promotion.

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 Oakridge Public Services correction for: A retrained model is deployed without comparing its output distributions with the approved production model, causing unexplained score shifts. The decisive acceptance check is instead: A representative request cohort produces traceable per-model score differences and unacceptable changes block promotion.

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 Oakridge Public Services correction for: A retrained model is deployed without comparing its output distributions with the approved production model, causing unexplained score shifts. The decisive acceptance check is instead: A representative request cohort produces traceable per-model score differences and unacceptable changes block promotion.

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 Oakridge Public Services correction for: A retrained model is deployed without comparing its output distributions with the approved production model, causing unexplained score shifts. The decisive acceptance check is instead: A representative request cohort produces traceable per-model score differences and unacceptable changes block promotion.

Enforce protected build contexts, isolated untrusted code execution and restricted deployment credentials available only after review. It does not directly address the Harborview Insurance case: A retrained model is deployed without comparing its output distributions with the approved production model, causing unexplained score shifts. The relevant acceptance criterion for this case is: A representative request cohort produces traceable per-model score differences and unacceptable changes block promotion.

Use approved private subnets, security groups and VPC endpoints where supported to restrict unnecessary network egress. It does not directly address the Harborview Insurance case: A retrained model is deployed without comparing its output distributions with the approved production model, causing unexplained score shifts. The relevant acceptance criterion for this case is: A representative request cohort produces traceable per-model score differences and unacceptable changes block promotion.

Apply identity-based domain and resource permission boundaries with segregated workspace roles and least privilege. It does not directly address the Harborview Insurance case: A retrained model is deployed without comparing its output distributions with the approved production model, causing unexplained score shifts. The relevant acceptance criterion for this case is: A representative request cohort produces traceable per-model score differences and unacceptable changes block promotion.

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 Harborview Insurance correction for: A retrained model is deployed without comparing its output distributions with the approved production model, causing unexplained score shifts. The decisive acceptance check is instead: A representative request cohort produces traceable per-model score differences and unacceptable changes block promotion.

A tampered artifact is rejected before the endpoint loads it and an approved version passes integrity verification. This would verify a different operation: Pin a governed immutable model artifact version and validate checksums or signatures through the approved release process. That separate action addresses: A production model file is overwritten with a maliciously altered artifact because deployment does not verify integrity or origin. It cannot establish the required Harborview Insurance correction for: A retrained model is deployed without comparing its output distributions with the approved production model, causing unexplained score shifts. The decisive acceptance check is instead: A representative request cohort produces traceable per-model score differences and unacceptable changes block promotion.

A low-traffic replay meets p95 response requirements and documents the cost of maintaining necessary warm capacity. This would verify a different operation: Choose a suitable minimum serving capacity or compatible hosting method and validate the idle-cost versus cold-start tradeoff. That separate action addresses: A model endpoint scales to zero immediately after every request but subsequent cold starts repeatedly violate the low-latency objective. It cannot establish the required Harborview Insurance correction for: A retrained model is deployed without comparing its output distributions with the approved production model, causing unexplained score shifts. The decisive acceptance check is instead: A representative request cohort produces traceable per-model score differences and unacceptable changes block promotion.

Replace embedded access keys with authorized IAM roles and secure short-lived credential delivery for the notebook environment. It does not directly address the Redstone Aviation case: An inference monitoring workflow cannot associate captured predictions with later labels because request identifiers are stripped during processing. The relevant acceptance criterion for this case is: A controlled event's original prediction joins to the matching eventual label without exposing unauthorized personal identifiers.

Create AWS Budgets alerts with defined cost thresholds and route notifications to the accountable ML operations owner. It does not directly address the Redstone Aviation case: An inference monitoring workflow cannot associate captured predictions with later labels because request identifiers are stripped during processing. The relevant acceptance criterion for this case is: A controlled event's original prediction joins to the matching eventual label without exposing unauthorized personal identifiers.

Require appropriate SSE-KMS settings on the output bucket and ensure the training role is authorized to use the chosen key. It does not directly address the Redstone Aviation case: An inference monitoring workflow cannot associate captured predictions with later labels because request identifiers are stripped during processing. The relevant acceptance criterion for this case is: A controlled event's original prediction joins to the matching eventual label without exposing unauthorized personal identifiers.

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 Redstone Aviation correction for: An inference monitoring workflow cannot associate captured predictions with later labels because request identifiers are stripped during processing. The decisive acceptance check is instead: A controlled event's original prediction joins to the matching eventual label without exposing unauthorized personal identifiers.

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 Redstone Aviation correction for: An inference monitoring workflow cannot associate captured predictions with later labels because request identifiers are stripped during processing. The decisive acceptance check is instead: A controlled event's original prediction joins to the matching eventual label without exposing unauthorized personal identifiers.

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 Redstone Aviation correction for: An inference monitoring workflow cannot associate captured predictions with later labels because request identifiers are stripped during processing. The decisive acceptance check is instead: A controlled event's original prediction joins to the matching eventual label without exposing unauthorized personal identifiers.

Replace embedded access keys with authorized IAM roles and secure short-lived credential delivery for the notebook environment. It does not directly address the Meadowbrook Finance case: An inference monitoring workflow cannot associate captured predictions with later labels because request identifiers are stripped during processing. The relevant acceptance criterion for this case is: A controlled event's original prediction joins to the matching eventual label without exposing unauthorized personal identifiers.

Review artifact location, cache or image-layer design and choose a supported reuse strategy consistent with version integrity. It does not directly address the Meadowbrook Finance case: An inference monitoring workflow cannot associate captured predictions with later labels because request identifiers are stripped during processing. The relevant acceptance criterion for this case is: A controlled event's original prediction joins to the matching eventual label without exposing unauthorized personal identifiers.

Apply identity-based domain and resource permission boundaries with segregated workspace roles and least privilege. It does not directly address the Meadowbrook Finance case: An inference monitoring workflow cannot associate captured predictions with later labels because request identifiers are stripped during processing. The relevant acceptance criterion for this case is: A controlled event's original prediction joins to the matching eventual label without exposing unauthorized personal identifiers.

A production task retrieves its secret with the authorized role while build logs reveal no plaintext credential. This would verify a different operation: Use AWS Secrets Manager or an approved secret provider with a scoped runtime role and suppress secret values from pipeline logs. That separate action addresses: An automated deployment retrieves a production database password from a plaintext environment variable stored in a shared build log. It cannot establish the required Meadowbrook Finance correction for: An inference monitoring workflow cannot associate captured predictions with later labels because request identifiers are stripped during processing. The decisive acceptance check is instead: A controlled event's original prediction joins to the matching eventual label without exposing unauthorized personal identifiers.

A tampered artifact is rejected before the endpoint loads it and an approved version passes integrity verification. This would verify a different operation: Pin a governed immutable model artifact version and validate checksums or signatures through the approved release process. That separate action addresses: A production model file is overwritten with a maliciously altered artifact because deployment does not verify integrity or origin. It cannot establish the required Meadowbrook Finance correction for: An inference monitoring workflow cannot associate captured predictions with later labels because request identifiers are stripped during processing. The decisive acceptance check is instead: A controlled event's original prediction joins to the matching eventual label without exposing unauthorized personal identifiers.

A code scan finds no static secret and the notebook's execution role can use only its intended dataset resources. This would verify a different operation: Replace embedded access keys with authorized IAM roles and secure short-lived credential delivery for the notebook environment. That separate action addresses: A SageMaker notebook user stores long-lived AWS credentials in the notebook source so other project members can inspect them. It cannot establish the required Meadowbrook Finance correction for: An inference monitoring workflow cannot associate captured predictions with later labels because request identifiers are stripped during processing. The decisive acceptance check is instead: A controlled event's original prediction joins to the matching eventual label without exposing unauthorized personal identifiers.

Require appropriate SSE-KMS settings on the output bucket and ensure the training role is authorized to use the chosen key. It does not directly address the Maplewood Schools case: A model receives rare null-heavy inputs in production that were absent from training and a batch of such requests produces unstable predictions. The relevant acceptance criterion for this case is: An injected malformed feature vector is handled according to policy and creates an attributable monitoring event.

Use comparable inference benchmarks across supported instance families and evaluate total cost per thousand successful requests. It does not directly address the Maplewood Schools case: A model receives rare null-heavy inputs in production that were absent from training and a batch of such requests produces unstable predictions. The relevant acceptance criterion for this case is: An injected malformed feature vector is handled according to policy and creates an attributable monitoring event.

Enable appropriate organization or account CloudTrail trails with secure retention and access controls for relevant management events. It does not directly address the Maplewood Schools case: A model receives rare null-heavy inputs in production that were absent from training and a batch of such requests produces unstable predictions. The relevant acceptance criterion for this case is: An injected malformed feature vector is handled according to policy and creates an attributable monitoring event.

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 Maplewood Schools correction for: A model receives rare null-heavy inputs in production that were absent from training and a batch of such requests produces unstable predictions. The decisive acceptance check is instead: An injected malformed feature vector is handled according to policy and creates an attributable monitoring event.

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 Maplewood Schools correction for: A model receives rare null-heavy inputs in production that were absent from training and a batch of such requests produces unstable predictions. The decisive acceptance check is instead: An injected malformed feature vector is handled according to policy and creates an attributable monitoring event.

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 Maplewood Schools correction for: A model receives rare null-heavy inputs in production that were absent from training and a batch of such requests produces unstable predictions. The decisive acceptance check is instead: An injected malformed feature vector is handled according to policy and creates an attributable monitoring event.