Exam Bundle

A replacement task starts from the approved artifact version without needing an untracked disk originally attached to another node. This would verify a different operation: Use the intended durable artifact storage pattern and reproducible infrastructure definitions rather than node-local attachment assumptions. That separate action addresses: A model deployment relies on one manually created EBS volume that a replacement task cannot attach after failure. It cannot establish the required Highland Education correction for: An edge camera must infer while offline, but the model architecture depends on a continuously reachable cloud real-time endpoint. The decisive acceptance check is instead: The disconnected edge device completes an approved inference and later reports its model version when connectivity returns.

A replay of the execution reads identical object versions and generates a traceable, comparable training run. This would verify a different operation: Make the retraining input a named immutable dataset manifest and persist it in the pipeline execution parameters. That separate action addresses: A scheduled retraining pipeline uses the latest available dataset rather than the dataset cut recorded in its review ticket. It cannot establish the required Highland Education correction for: An edge camera must infer while offline, but the model architecture depends on a continuously reachable cloud real-time endpoint. The decisive acceptance check is instead: The disconnected edge device completes an approved inference and later reports its model version when connectivity returns.

A simulated bad candidate triggers the rollback and the restored endpoint returns the documented prior model responses. This would verify a different operation: Implement a controlled canary or blue-green rollout with CloudWatch alarm gates and automatic rollback to the approved prior version. That separate action addresses: A model's automatic deployment increases error rates, but the pipeline has no health-driven rollback condition or retained previous version. It cannot establish the required Highland Education correction for: An edge camera must infer while offline, but the model architecture depends on a continuously reachable cloud real-time endpoint. The decisive acceptance check is instead: The disconnected edge device completes an approved inference and later reports its model version when connectivity returns.

Include explicitly approved per-segment acceptance checks and fairness review in the conditional deployment gates. It does not directly address the Maplewood Schools case: An edge camera must infer while offline, but the model architecture depends on a continuously reachable cloud real-time endpoint. The relevant acceptance criterion for this case is: The disconnected edge device completes an approved inference and later reports its model version when connectivity returns.

Include stable dataset IDs and idempotency controls in the orchestration design, preserving run lineage and concurrency policies. It does not directly address the Maplewood Schools case: An edge camera must infer while offline, but the model architecture depends on a continuously reachable cloud real-time endpoint. The relevant acceptance criterion for this case is: The disconnected edge device completes an approved inference and later reports its model version when connectivity returns.

Express the approved endpoint, model and networking settings in CloudFormation or AWS CDK infrastructure definitions with reviewed parameters. It does not directly address the Maplewood Schools case: An edge camera must infer while offline, but the model architecture depends on a continuously reachable cloud real-time endpoint. The relevant acceptance criterion for this case is: The disconnected edge device completes an approved inference and later reports its model version when connectivity returns.

Both environments deploy without name collisions and their resource tags and model endpoints remain separate. This would verify a different operation: Parameterize account, Region and environment-specific identifiers and maintain isolated deployment stacks and resource references. That separate action addresses: A team's AWS CDK stack uses the same fixed resource names across development and production and fails when a second environment is deployed. It cannot establish the required Maplewood Schools correction for: An edge camera must infer while offline, but the model architecture depends on a continuously reachable cloud real-time endpoint. The decisive acceptance check is instead: The disconnected edge device completes an approved inference and later reports its model version when connectivity returns.

A test build can publish only its approved artifact and is denied direct modification of the production endpoint. This would verify a different operation: Separate pipeline, build, training and serving roles with narrowly scoped permissions for their specific stages. That separate action addresses: A model project uses one broad IAM role for CodePipeline, training and production inference, enabling build jobs to alter runtime resources. It cannot establish the required Maplewood Schools correction for: An edge camera must infer while offline, but the model architecture depends on a continuously reachable cloud real-time endpoint. The decisive acceptance check is instead: The disconnected edge device completes an approved inference and later reports its model version when connectivity returns.

The pipeline detects an intentionally incompatible model artifact before endpoint deployment occurs. This would verify a different operation: Add an integration test that starts the intended runtime image with the frozen artifact and invokes a representative inference sample. That separate action addresses: A CI stage validates Python syntax but never tests whether the model container can actually load the published model artifact. It cannot establish the required Maplewood Schools correction for: An edge camera must infer while offline, but the model architecture depends on a continuously reachable cloud real-time endpoint. The decisive acceptance check is instead: The disconnected edge device completes an approved inference and later reports its model version when connectivity returns.

Make the retraining input a named immutable dataset manifest and persist it in the pipeline execution parameters. It does not directly address the Lakeside Research case: A high-volume endpoint runs on small CPUs despite a documented model benchmark showing matrix inference benefits from accelerator hardware. The relevant acceptance criterion for this case is: The selected instance family meets throughput and latency targets with a documented cost-per-inference measurement.

Right-size compute per compatible variant using an inference benchmark and represent each selection in the deployment stack. It does not directly address the Lakeside Research case: A high-volume endpoint runs on small CPUs despite a documented model benchmark showing matrix inference benefits from accelerator hardware. The relevant acceptance criterion for this case is: The selected instance family meets throughput and latency targets with a documented cost-per-inference measurement.

Parameterize account, Region and environment-specific identifiers and maintain isolated deployment stacks and resource references. It does not directly address the Lakeside Research case: A high-volume endpoint runs on small CPUs despite a documented model benchmark showing matrix inference benefits from accelerator hardware. The relevant acceptance criterion for this case is: The selected instance family meets throughput and latency targets with a documented cost-per-inference measurement.

A deliberately failing test stops the pipeline and no new production model version is published from that commit. This would verify a different operation: Insert automated tests and a quality-gate approval stage before promoting an approved model package to production. That separate action addresses: A model deployment pipeline deploys directly from each developer commit without checking preprocessing unit tests or model evaluation thresholds. It cannot establish the required Lakeside Research correction for: A high-volume endpoint runs on small CPUs despite a documented model benchmark showing matrix inference benefits from accelerator hardware. The decisive acceptance check is instead: The selected instance family meets throughput and latency targets with a documented cost-per-inference measurement.

A repeated deployment selects the identical container digest and verified model artifact regardless of later tag updates. This would verify a different operation: Reference a reviewed immutable ECR image digest alongside the exact model artifact version in the deployment configuration. That separate action addresses: A deployment includes an inference image tagged latest in Amazon ECR, allowing a later push to silently change model runtime dependencies. It cannot establish the required Lakeside Research correction for: A high-volume endpoint runs on small CPUs despite a documented model benchmark showing matrix inference benefits from accelerator hardware. The decisive acceptance check is instead: The selected instance family meets throughput and latency targets with a documented cost-per-inference measurement.

A fresh staging stack reproduces the approved resource structure and a change set exposes differences before deployment. This would verify a different operation: Express the approved endpoint, model and networking settings in CloudFormation or AWS CDK infrastructure definitions with reviewed parameters. That separate action addresses: An ML application is provisioned by manually clicking SageMaker console settings, so production and staging use different instance types and security groups. It cannot establish the required Lakeside Research correction for: A high-volume endpoint runs on small CPUs despite a documented model benchmark showing matrix inference benefits from accelerator hardware. The decisive acceptance check is instead: The selected instance family meets throughput and latency targets with a documented cost-per-inference measurement.

Build and publish a runtime image for the target supported architecture and pin matching instance and container metadata. It does not directly address the Eastshore Energy case: A high-volume endpoint runs on small CPUs despite a documented model benchmark showing matrix inference benefits from accelerator hardware. The relevant acceptance criterion for this case is: The selected instance family meets throughput and latency targets with a documented cost-per-inference measurement.

Include explicitly approved per-segment acceptance checks and fairness review in the conditional deployment gates. It does not directly address the Eastshore Energy case: A high-volume endpoint runs on small CPUs despite a documented model benchmark showing matrix inference benefits from accelerator hardware. The relevant acceptance criterion for this case is: The selected instance family meets throughput and latency targets with a documented cost-per-inference measurement.

Include stable dataset IDs and idempotency controls in the orchestration design, preserving run lineage and concurrency policies. It does not directly address the Eastshore Energy case: A high-volume endpoint runs on small CPUs despite a documented model benchmark showing matrix inference benefits from accelerator hardware. The relevant acceptance criterion for this case is: The selected instance family meets throughput and latency targets with a documented cost-per-inference measurement.

Both environments deploy without name collisions and their resource tags and model endpoints remain separate. This would verify a different operation: Parameterize account, Region and environment-specific identifiers and maintain isolated deployment stacks and resource references. That separate action addresses: A team's AWS CDK stack uses the same fixed resource names across development and production and fails when a second environment is deployed. It cannot establish the required Eastshore Energy correction for: A high-volume endpoint runs on small CPUs despite a documented model benchmark showing matrix inference benefits from accelerator hardware. The decisive acceptance check is instead: The selected instance family meets throughput and latency targets with a documented cost-per-inference measurement.

A controlled ECS rollout replaces tasks with the intended version and returns successful health checks throughout transition. This would verify a different operation: Version the task definition, container image and service deployment configuration as reviewed infrastructure changes. That separate action addresses: An Amazon ECS model-serving service cannot be updated safely because its task definition and container port are modified directly on running hosts. It cannot establish the required Eastshore Energy correction for: A high-volume endpoint runs on small CPUs despite a documented model benchmark showing matrix inference benefits from accelerator hardware. The decisive acceptance check is instead: The selected instance family meets throughput and latency targets with a documented cost-per-inference measurement.

A replay of transient spikes avoids oscillation while sustained load still triggers the required scale-out action. This would verify a different operation: Tune target tracking, cooldown and minimum capacity from observed workload periodicity rather than setting a zero-tolerance threshold. That separate action addresses: An auto-scaled inference endpoint scales out during every brief request spike and incurs unnecessary instance churn and warm-up overhead. It cannot establish the required Eastshore Energy correction for: A high-volume endpoint runs on small CPUs despite a documented model benchmark showing matrix inference benefits from accelerator hardware. The decisive acceptance check is instead: The selected instance family meets throughput and latency targets with a documented cost-per-inference measurement.

Make the retraining input a named immutable dataset manifest and persist it in the pipeline execution parameters. It does not directly address the Riverton Utilities case: A production team deploys an updated fraud model by replacing the only model artifact, leaving no usable rollback option. The relevant acceptance criterion for this case is: A staged rollback restores the approved prior model version and representative requests return to baseline behavior.

Add an integration test that starts the intended runtime image with the frozen artifact and invokes a representative inference sample. It does not directly address the Riverton Utilities case: A production team deploys an updated fraud model by replacing the only model artifact, leaving no usable rollback option. The relevant acceptance criterion for this case is: A staged rollback restores the approved prior model version and representative requests return to baseline behavior.

Provision test environments from IaC and implement a reviewed cleanup action with protective rules for shared resources. It does not directly address the Riverton Utilities case: A production team deploys an updated fraud model by replacing the only model artifact, leaving no usable rollback option. The relevant acceptance criterion for this case is: A staged rollback restores the approved prior model version and representative requests return to baseline behavior.

The pipeline detects an intentionally incompatible model artifact before endpoint deployment occurs. This would verify a different operation: Add an integration test that starts the intended runtime image with the frozen artifact and invokes a representative inference sample. That separate action addresses: A CI stage validates Python syntax but never tests whether the model container can actually load the published model artifact. It cannot establish the required Riverton Utilities correction for: A production team deploys an updated fraud model by replacing the only model artifact, leaving no usable rollback option. The decisive acceptance check is instead: A staged rollback restores the approved prior model version and representative requests return to baseline behavior.

A risky security-group expansion is blocked during review and a permitted private endpoint change deploys successfully. This would verify a different operation: Require inspected infrastructure change sets and automated network-policy validation before applying the altered endpoint stack. That separate action addresses: A stack update changes an inference endpoint's network settings without showing whether the change broadens inbound access. It cannot establish the required Riverton Utilities correction for: A production team deploys an updated fraud model by replacing the only model artifact, leaving no usable rollback option. The decisive acceptance check is instead: A staged rollback restores the approved prior model version and representative requests return to baseline behavior.

The updated resource inventory shows justified instance families and the service maintains required per-variant latency. This would verify a different operation: Right-size compute per compatible variant using an inference benchmark and represent each selection in the deployment stack. That separate action addresses: A data scientist provisions GPUs for all endpoint variants even though most deployed lightweight models support cost-effective CPU hosting. It cannot establish the required Riverton Utilities correction for: A production team deploys an updated fraud model by replacing the only model artifact, leaving no usable rollback option. The decisive acceptance check is instead: A staged rollback restores the approved prior model version and representative requests return to baseline behavior.

Configure the supported SageMaker VPC subnet, security group and endpoint-access rules for required private dependencies. It does not directly address the Cedarfield Hospitality case: A production team deploys an updated fraud model by replacing the only model artifact, leaving no usable rollback option. The relevant acceptance criterion for this case is: A staged rollback restores the approved prior model version and representative requests return to baseline behavior.

Reference a reviewed immutable ECR image digest alongside the exact model artifact version in the deployment configuration. It does not directly address the Cedarfield Hospitality case: A production team deploys an updated fraud model by replacing the only model artifact, leaving no usable rollback option. The relevant acceptance criterion for this case is: A staged rollback restores the approved prior model version and representative requests return to baseline behavior.

Add evaluation and conditional model-quality steps linked to the model registry approval process. It does not directly address the Cedarfield Hospitality case: A production team deploys an updated fraud model by replacing the only model artifact, leaving no usable rollback option. The relevant acceptance criterion for this case is: A staged rollback restores the approved prior model version and representative requests return to baseline behavior.

A private model startup retrieves the authorized S3 artifact without an unintended public network route. This would verify a different operation: Provision the approved VPC endpoint or controlled network route and its route table and access policies for model-artifact reads. That separate action addresses: A private ML deployment needs an S3 model artifact but the VPC-only environment lacks a suitable S3 endpoint or authorized egress path. It cannot establish the required Cedarfield Hospitality correction for: A production team deploys an updated fraud model by replacing the only model artifact, leaving no usable rollback option. The decisive acceptance check is instead: A staged rollback restores the approved prior model version and representative requests return to baseline behavior.

A test candidate with a critical slice regression is blocked despite acceptable aggregate F1 performance. This would verify a different operation: Include explicitly approved per-segment acceptance checks and fairness review in the conditional deployment gates. That separate action addresses: A quality gate evaluates only global F1 score while a new candidate violates the acceptable error limit for a protected segment. It cannot establish the required Cedarfield Hospitality correction for: A production team deploys an updated fraud model by replacing the only model artifact, leaving no usable rollback option. The decisive acceptance check is instead: A staged rollback restores the approved prior model version and representative requests return to baseline behavior.

A controlled deployment must pass endpoint health, representative inference and alarm checks to reach the completed state. This would verify a different operation: Add post-deployment smoke tests and monitored acceptance gates before the production release is marked successful. That separate action addresses: A team declares its pipeline finished when model training succeeds, though deployment smoke tests and runtime metrics are never observed. It cannot establish the required Cedarfield Hospitality correction for: A production team deploys an updated fraud model by replacing the only model artifact, leaving no usable rollback option. The decisive acceptance check is instead: A staged rollback restores the approved prior model version and representative requests return to baseline behavior.