Exam Bundle

A representative live test receives each decision within the checkout deadline without waiting for a batch schedule. This would verify a different operation: Deploy an appropriately scaled low-latency real-time inference endpoint and route transaction requests through the authorized path. That separate action addresses: A web fraud detector requires low-latency inference for each checkout, but the proposed architecture waits for the next hourly batch transformation. It cannot establish the required Meadowbrook Finance correction for: A model project uses one broad IAM role for CodePipeline, training and production inference, enabling build jobs to alter runtime resources. The decisive acceptance check is instead: A test build can publish only its approved artifact and is denied direct modification of the production endpoint.

The nightly batch finishes inside its approved window and idle endpoint costs are removed from the daily bill. This would verify a different operation: Use SageMaker Batch Transform or an appropriate scheduled batch inference workflow instead of an always-on real-time endpoint. That separate action addresses: A demand forecast model is invoked once overnight for millions of rows, but the team keeps a real-time SageMaker endpoint running all day. It cannot establish the required Meadowbrook Finance correction for: A model project uses one broad IAM role for CodePipeline, training and production inference, enabling build jobs to alter runtime resources. The decisive acceptance check is instead: A test build can publish only its approved artifact and is denied direct modification of the production endpoint.

The representative load test meets latency targets and the chosen hosting cost falls below the idle GPU baseline. This would verify a different operation: Benchmark CPU or suitable serverless hosting and select the deployment offering that meets utilization and latency requirements. That separate action addresses: A team serves a tiny low-traffic model on a provisioned GPU endpoint even though CPU inference meets the request latency target. It cannot establish the required Meadowbrook Finance correction for: A model project uses one broad IAM role for CodePipeline, training and production inference, enabling build jobs to alter runtime resources. The decisive acceptance check is instead: A test build can publish only its approved artifact and is denied direct modification of the production endpoint.

Maintain versioned model artifacts and use a controlled deployment strategy with retained previous endpoint configuration. It does not directly address the Maplewood Schools case: A retraining pipeline can be launched twice for the same input data, creating competing model versions with indistinguishable metadata. The relevant acceptance criterion for this case is: Two identical trigger messages resolve to the expected single logical model update without competing untracked releases.

Use the intended durable artifact storage pattern and reproducible infrastructure definitions rather than node-local attachment assumptions. It does not directly address the Maplewood Schools case: A retraining pipeline can be launched twice for the same input data, creating competing model versions with indistinguishable metadata. The relevant acceptance criterion for this case is: Two identical trigger messages resolve to the expected single logical model update without competing untracked releases.

Provision the approved VPC endpoint or controlled network route and its route table and access policies for model-artifact reads. It does not directly address the Maplewood Schools case: A retraining pipeline can be launched twice for the same input data, creating competing model versions with indistinguishable metadata. The relevant acceptance criterion for this case is: Two identical trigger messages resolve to the expected single logical model update without competing untracked releases.

The test traffic follows the approved proportion and logs identify exactly which model variant served each request. This would verify a different operation: Use a governed endpoint-variant routing or other supported traffic allocation design with versioned model identifiers. That separate action addresses: A product runs several model variants but the frontend hard-codes one endpoint URL and cannot safely direct a controlled share of traffic to a candidate. It cannot establish the required Maplewood Schools correction for: A retraining pipeline can be launched twice for the same input data, creating competing model versions with indistinguishable metadata. The decisive acceptance check is instead: Two identical trigger messages resolve to the expected single logical model update without competing untracked releases.

Health probes confirm readiness without increasing model invocation counts or delaying normal business predictions. This would verify a different operation: Define a lightweight readiness and liveness interface distinct from resource-intensive inference operations. That separate action addresses: A container inference service sends health checks to a path that triggers costly full model predictions and exhausts request capacity during rollouts. It cannot establish the required Maplewood Schools correction for: A retraining pipeline can be launched twice for the same input data, creating competing model versions with indistinguishable metadata. The decisive acceptance check is instead: Two identical trigger messages resolve to the expected single logical model update without competing untracked releases.

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 Maplewood Schools correction for: A retraining pipeline can be launched twice for the same input data, creating competing model versions with indistinguishable metadata. The decisive acceptance check is instead: Two identical trigger messages resolve to the expected single logical model update without competing untracked releases.

Remove embedded credentials and use least-privilege runtime IAM roles or approved secret injection with image scanning. It does not directly address the Highland Education case: A retraining pipeline can be launched twice for the same input data, creating competing model versions with indistinguishable metadata. The relevant acceptance criterion for this case is: Two identical trigger messages resolve to the expected single logical model update without competing untracked releases.

Use the intended durable artifact storage pattern and reproducible infrastructure definitions rather than node-local attachment assumptions. It does not directly address the Highland Education case: A retraining pipeline can be launched twice for the same input data, creating competing model versions with indistinguishable metadata. The relevant acceptance criterion for this case is: Two identical trigger messages resolve to the expected single logical model update without competing untracked releases.

Express the approved endpoint, model and networking settings in CloudFormation or AWS CDK infrastructure definitions with reviewed parameters. It does not directly address the Highland Education case: A retraining pipeline can be launched twice for the same input data, creating competing model versions with indistinguishable metadata. The relevant acceptance criterion for this case is: Two identical trigger messages resolve to the expected single logical model update without competing untracked releases.

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: A retraining pipeline can be launched twice for the same input data, creating competing model versions with indistinguishable metadata. The decisive acceptance check is instead: Two identical trigger messages resolve to the expected single logical model update without competing untracked releases.

Health probes confirm readiness without increasing model invocation counts or delaying normal business predictions. This would verify a different operation: Define a lightweight readiness and liveness interface distinct from resource-intensive inference operations. That separate action addresses: A container inference service sends health checks to a path that triggers costly full model predictions and exhausts request capacity during rollouts. It cannot establish the required Highland Education correction for: A retraining pipeline can be launched twice for the same input data, creating competing model versions with indistinguishable metadata. The decisive acceptance check is instead: Two identical trigger messages resolve to the expected single logical model update without competing untracked releases.

The disconnected edge device completes an approved inference and later reports its model version when connectivity returns. This would verify a different operation: Optimize and package an appropriate model for supported edge execution with a tested offline runtime and update mechanism. That separate action addresses: An edge camera must infer while offline, but the model architecture depends on a continuously reachable cloud real-time endpoint. It cannot establish the required Highland Education correction for: A retraining pipeline can be launched twice for the same input data, creating competing model versions with indistinguishable metadata. The decisive acceptance check is instead: Two identical trigger messages resolve to the expected single logical model update without competing untracked releases.

Use a governed endpoint-variant routing or other supported traffic allocation design with versioned model identifiers. It does not directly address the Eastshore Energy case: A CI stage validates Python syntax but never tests whether the model container can actually load the published model artifact. The relevant acceptance criterion for this case is: The pipeline detects an intentionally incompatible model artifact before endpoint deployment occurs.

Deploy an appropriately scaled low-latency real-time inference endpoint and route transaction requests through the authorized path. It does not directly address the Eastshore Energy case: A CI stage validates Python syntax but never tests whether the model container can actually load the published model artifact. The relevant acceptance criterion for this case is: The pipeline detects an intentionally incompatible model artifact before endpoint deployment occurs.

Evaluate SageMaker multi-model endpoints where model memory and isolation requirements permit compatible shared hosting. It does not directly address the Eastshore Energy case: A CI stage validates Python syntax but never tests whether the model container can actually load the published model artifact. The relevant acceptance criterion for this case is: The pipeline detects an intentionally incompatible model artifact before endpoint deployment occurs.

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 Eastshore Energy correction for: A CI stage validates Python syntax but never tests whether the model container can actually load the published model artifact. The decisive acceptance check is instead: The pipeline detects an intentionally incompatible model artifact before endpoint deployment occurs.

Requests from representative client Regions meet the permitted total latency without violating data-residency controls. This would verify a different operation: Benchmark end-to-end inference latency and select an approved Region or edge design aligned to residency and client location. That separate action addresses: A low-latency image model deployed to a generic instance experiences unnecessary network delay because request payloads transit a distant AWS Region. It cannot establish the required Eastshore Energy correction for: A CI stage validates Python syntax but never tests whether the model container can actually load the published model artifact. The decisive acceptance check is instead: The pipeline detects an intentionally incompatible model artifact before endpoint deployment occurs.

An increasing request rate triggers timely scaling and p95 inference latency remains within the approved limit. This would verify a different operation: Select an appropriate SageMaker endpoint scaling metric such as invocations per instance and tune thresholds from measured traffic. That separate action addresses: A scalable inference endpoint uses CPU utilization as its only target metric despite requests waiting in invocation queues and little CPU usage. It cannot establish the required Eastshore Energy correction for: A CI stage validates Python syntax but never tests whether the model container can actually load the published model artifact. The decisive acceptance check is instead: The pipeline detects an intentionally incompatible model artifact before endpoint deployment occurs.

Compare Lambda, SageMaker asynchronous inference or container hosting based on payload size, memory and duration constraints. It does not directly address the Lakeside Research case: A CI stage validates Python syntax but never tests whether the model container can actually load the published model artifact. The relevant acceptance criterion for this case is: The pipeline detects an intentionally incompatible model artifact before endpoint deployment occurs.

Require inspected infrastructure change sets and automated network-policy validation before applying the altered endpoint stack. It does not directly address the Lakeside Research case: A CI stage validates Python syntax but never tests whether the model container can actually load the published model artifact. The relevant acceptance criterion for this case is: The pipeline detects an intentionally incompatible model artifact before endpoint deployment occurs.

Maintain versioned model artifacts and use a controlled deployment strategy with retained previous endpoint configuration. It does not directly address the Lakeside Research case: A CI stage validates Python syntax but never tests whether the model container can actually load the published model artifact. The relevant acceptance criterion for this case is: The pipeline detects an intentionally incompatible model artifact before endpoint deployment occurs.

Health probes confirm readiness without increasing model invocation counts or delaying normal business predictions. This would verify a different operation: Define a lightweight readiness and liveness interface distinct from resource-intensive inference operations. That separate action addresses: A container inference service sends health checks to a path that triggers costly full model predictions and exhausts request capacity during rollouts. It cannot establish the required Lakeside Research correction for: A CI stage validates Python syntax but never tests whether the model container can actually load the published model artifact. The decisive acceptance check is instead: The pipeline detects an intentionally incompatible model artifact before endpoint deployment occurs.

The test traffic follows the approved proportion and logs identify exactly which model variant served each request. This would verify a different operation: Use a governed endpoint-variant routing or other supported traffic allocation design with versioned model identifiers. That separate action addresses: A product runs several model variants but the frontend hard-codes one endpoint URL and cannot safely direct a controlled share of traffic to a candidate. It cannot establish the required Lakeside Research correction for: A CI stage validates Python syntax but never tests whether the model container can actually load the published model artifact. The decisive acceptance check is instead: The pipeline detects an intentionally incompatible model artifact before endpoint deployment occurs.

Requests from representative client Regions meet the permitted total latency without violating data-residency controls. This would verify a different operation: Benchmark end-to-end inference latency and select an approved Region or edge design aligned to residency and client location. That separate action addresses: A low-latency image model deployed to a generic instance experiences unnecessary network delay because request payloads transit a distant AWS Region. It cannot establish the required Lakeside Research correction for: A CI stage validates Python syntax but never tests whether the model container can actually load the published model artifact. The decisive acceptance check is instead: The pipeline detects an intentionally incompatible model artifact before endpoint deployment occurs.

Benchmark end-to-end inference latency and select an approved Region or edge design aligned to residency and client location. It does not directly address the Cedarfield Hospitality case: A model's automatic deployment increases error rates, but the pipeline has no health-driven rollback condition or retained previous version. The relevant acceptance criterion for this case is: A simulated bad candidate triggers the rollback and the restored endpoint returns the documented prior model responses.

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 model's automatic deployment increases error rates, but the pipeline has no health-driven rollback condition or retained previous version. The relevant acceptance criterion for this case is: A simulated bad candidate triggers the rollback and the restored endpoint returns the documented prior model responses.

Provision test environments from IaC and implement a reviewed cleanup action with protective rules for shared resources. It does not directly address the Cedarfield Hospitality case: A model's automatic deployment increases error rates, but the pipeline has no health-driven rollback condition or retained previous version. The relevant acceptance criterion for this case is: A simulated bad candidate triggers the rollback and the restored endpoint returns the documented prior model responses.

A fresh ECS task passes its health check and serves a controlled request without depending on SageMaker-only paths. This would verify a different operation: Adapt the container entrypoint, model artifact retrieval and health interface to the actual selected ECS deployment environment. That separate action addresses: A new model is deployed to ECS but its container expects SageMaker environment paths and does not satisfy the container orchestration service's HTTP health contract. It cannot establish the required Cedarfield Hospitality correction for: A model's automatic deployment increases error rates, but the pipeline has no health-driven rollback condition or retained previous version. The decisive acceptance check is instead: A simulated bad candidate triggers the rollback and the restored endpoint returns the documented prior model responses.

A known request traverses the versioned preprocessing and prediction stages and produces the expected output after deployment. This would verify a different operation: Use a supported SageMaker inference pipeline or reviewed multi-container design with compatible input and output contracts. That separate action addresses: An inference service chains preprocessing and prediction in application code that cannot be versioned with the SageMaker deployed model. It cannot establish the required Cedarfield Hospitality correction for: A model's automatic deployment increases error rates, but the pipeline has no health-driven rollback condition or retained previous version. The decisive acceptance check is instead: A simulated bad candidate triggers the rollback and the restored endpoint returns the documented prior model responses.

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 Cedarfield Hospitality correction for: A model's automatic deployment increases error rates, but the pipeline has no health-driven rollback condition or retained previous version. The decisive acceptance check is instead: A simulated bad candidate triggers the rollback and the restored endpoint returns the documented prior model responses.