Exam Bundle

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.

Track total received records, rejected records and successful predictions with clear denominators across batch processing. It does not directly address the Bluehaven Transit case: A production inference container is placed in subnets with internet egress although its required datasets and dependencies are private AWS services. The relevant acceptance criterion for this case is: The inference container accesses authorized model artifacts privately and an external egress test remains blocked.

Evaluate SageMaker Managed Spot Training with checkpointing and compare interruption risk and effective completion cost. It does not directly address the Bluehaven Transit case: A production inference container is placed in subnets with internet egress although its required datasets and dependencies are private AWS services. The relevant acceptance criterion for this case is: The inference container accesses authorized model artifacts privately and an external egress test remains blocked.

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 Bluehaven Transit case: A production inference container is placed in subnets with internet egress although its required datasets and dependencies are private AWS services. The relevant acceptance criterion for this case is: The inference container accesses authorized model artifacts privately and an external egress test remains blocked.

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 Bluehaven Transit correction for: A production inference container is placed in subnets with internet egress although its required datasets and dependencies are private AWS services. The decisive acceptance check is instead: The inference container accesses authorized model artifacts privately and an external egress test remains blocked.

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 Bluehaven Transit correction for: A production inference container is placed in subnets with internet egress although its required datasets and dependencies are private AWS services. The decisive acceptance check is instead: The inference container accesses authorized model artifacts privately and an external egress test remains blocked.

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 Bluehaven Transit correction for: A production inference container is placed in subnets with internet egress although its required datasets and dependencies are private AWS services. The decisive acceptance check is instead: The inference container accesses authorized model artifacts privately and an external egress test remains blocked.

Enable appropriate tuning-job completion limits and early termination policies where supported for the selected metric. It does not directly address the Brookside Manufacturing case: A production inference container is placed in subnets with internet egress although its required datasets and dependencies are private AWS services. The relevant acceptance criterion for this case is: The inference container accesses authorized model artifacts privately and an external egress test remains blocked.

Create a SageMaker Model Monitor data-quality baseline and schedule inference feature-distribution checks against it. It does not directly address the Brookside Manufacturing case: A production inference container is placed in subnets with internet egress although its required datasets and dependencies are private AWS services. The relevant acceptance criterion for this case is: The inference container accesses authorized model artifacts privately and an external egress test remains blocked.

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 Brookside Manufacturing case: A production inference container is placed in subnets with internet egress although its required datasets and dependencies are private AWS services. The relevant acceptance criterion for this case is: The inference container accesses authorized model artifacts privately and an external egress test remains blocked.

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 Brookside Manufacturing correction for: A production inference container is placed in subnets with internet egress although its required datasets and dependencies are private AWS services. The decisive acceptance check is instead: The inference container accesses authorized model artifacts privately and an external egress test remains blocked.

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 Brookside Manufacturing correction for: A production inference container is placed in subnets with internet egress although its required datasets and dependencies are private AWS services. The decisive acceptance check is instead: The inference container accesses authorized model artifacts privately and an external egress test remains blocked.

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 Brookside Manufacturing correction for: A production inference container is placed in subnets with internet egress although its required datasets and dependencies are private AWS services. The decisive acceptance check is instead: The inference container accesses authorized model artifacts privately and an external egress test remains blocked.

Inspect SageMaker service quotas and scaling target limits and request justified quota changes before increasing traffic. It does not directly address the Harborline Logistics case: An S3 bucket holding labeled training images allows anonymous object reads because a legacy public-read policy was copied into production. The relevant acceptance criterion for this case is: An anonymous request is denied while a permitted training role retrieves its intended objects successfully.

Update monitored endpoint or variant configuration and baseline references as part of the versioned deployment process. It does not directly address the Harborline Logistics case: An S3 bucket holding labeled training images allows anonymous object reads because a legacy public-read policy was copied into production. The relevant acceptance criterion for this case is: An anonymous request is denied while a permitted training role retrieves its intended objects successfully.

Monitor predicted probability buckets against observed outcome frequencies using suitable delayed labels and calibration baselines. It does not directly address the Harborline Logistics case: An S3 bucket holding labeled training images allows anonymous object reads because a legacy public-read policy was copied into production. The relevant acceptance criterion for this case is: An anonymous request is denied while a permitted training role retrieves its intended objects successfully.

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 Harborline Logistics correction for: An S3 bucket holding labeled training images allows anonymous object reads because a legacy public-read policy was copied into production. The decisive acceptance check is instead: An anonymous request is denied while a permitted training role retrieves its intended objects successfully.

A controlled prediction from the new variant appears in the correct monitoring dataset and the old variant is not mistaken for current. This would verify a different operation: Update monitored endpoint or variant configuration and baseline references as part of the versioned deployment process. That separate action addresses: A risk model is deployed with a new model version but its SageMaker Model Monitor schedule continues capturing only the old endpoint variant. It cannot establish the required Harborline Logistics correction for: An S3 bucket holding labeled training images allows anonymous object reads because a legacy public-read policy was copied into production. The decisive acceptance check is instead: An anonymous request is denied while a permitted training role retrieves its intended objects successfully.

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 Harborline Logistics correction for: An S3 bucket holding labeled training images allows anonymous object reads because a legacy public-read policy was copied into production. The decisive acceptance check is instead: An anonymous request is denied while a permitted training role retrieves its intended objects successfully.

Update monitored endpoint or variant configuration and baseline references as part of the versioned deployment process. It does not directly address the Northgate Telecom case: An S3 bucket holding labeled training images allows anonymous object reads because a legacy public-read policy was copied into production. The relevant acceptance criterion for this case is: An anonymous request is denied while a permitted training role retrieves its intended objects successfully.

Review artifact location, cache or image-layer design and choose a supported reuse strategy consistent with version integrity. It does not directly address the Northgate Telecom case: An S3 bucket holding labeled training images allows anonymous object reads because a legacy public-read policy was copied into production. The relevant acceptance criterion for this case is: An anonymous request is denied while a permitted training role retrieves its intended objects successfully.

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: An S3 bucket holding labeled training images allows anonymous object reads because a legacy public-read policy was copied into production. The relevant acceptance criterion for this case is: An anonymous request is denied while a permitted training role retrieves its intended objects successfully.

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: An S3 bucket holding labeled training images allows anonymous object reads because a legacy public-read policy was copied into production. The decisive acceptance check is instead: An anonymous request is denied while a permitted training role retrieves its intended objects successfully.

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 Northgate Telecom correction for: An S3 bucket holding labeled training images allows anonymous object reads because a legacy public-read policy was copied into production. The decisive acceptance check is instead: An anonymous request is denied while a permitted training role retrieves its intended objects successfully.

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 Northgate Telecom correction for: An S3 bucket holding labeled training images allows anonymous object reads because a legacy public-read policy was copied into production. The decisive acceptance check is instead: An anonymous request is denied while a permitted training role retrieves its intended objects successfully.

Apply reviewed S3 lifecycle transition and expiration policies aligned to audit retention and replay requirements. It does not directly address the Pinecrest Hotels case: A model deployment can write arbitrary CloudWatch Logs groups because its inference IAM role includes broad administrative logging permissions. The relevant acceptance criterion for this case is: The runtime writes to the intended log stream but cannot modify an unrelated service's logging resources.

Evaluate SageMaker Managed Spot Training with checkpointing and compare interruption risk and effective completion cost. It does not directly address the Pinecrest Hotels case: A model deployment can write arbitrary CloudWatch Logs groups because its inference IAM role includes broad administrative logging permissions. The relevant acceptance criterion for this case is: The runtime writes to the intended log stream but cannot modify an unrelated service's logging resources.

Enable appropriate tuning-job completion limits and early termination policies where supported for the selected metric. It does not directly address the Pinecrest Hotels case: A model deployment can write arbitrary CloudWatch Logs groups because its inference IAM role includes broad administrative logging permissions. The relevant acceptance criterion for this case is: The runtime writes to the intended log stream but cannot modify an unrelated service's logging resources.

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 Pinecrest Hotels correction for: A model deployment can write arbitrary CloudWatch Logs groups because its inference IAM role includes broad administrative logging permissions. The decisive acceptance check is instead: The runtime writes to the intended log stream but cannot modify an unrelated service's logging resources.

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 Pinecrest Hotels correction for: A model deployment can write arbitrary CloudWatch Logs groups because its inference IAM role includes broad administrative logging permissions. The decisive acceptance check is instead: The runtime writes to the intended log stream but cannot modify an unrelated service's logging resources.

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 Pinecrest Hotels correction for: A model deployment can write arbitrary CloudWatch Logs groups because its inference IAM role includes broad administrative logging permissions. The decisive acceptance check is instead: The runtime writes to the intended log stream but cannot modify an unrelated service's logging resources.