Exam Bundle

A representative maximum-size request completes under the chosen platform's supported limits without truncating the response. This would verify a different operation: Compare Lambda, SageMaker asynchronous inference or container hosting based on payload size, memory and duration constraints. That separate action addresses: An inference service needs quick per-document processing with substantial response payloads but a proposed Lambda implementation exceeds its documented resource or duration limits. It cannot establish the required Alpine Healthcare correction for: A container inference service sends health checks to a path that triggers costly full model predictions and exhausts request capacity during rollouts. The decisive acceptance check is instead: Health probes confirm readiness without increasing model invocation counts or delaying normal business predictions.

Representative models load on demand and per-model latency and isolation checks meet the accepted limits at reduced aggregate cost. This would verify a different operation: Evaluate SageMaker multi-model endpoints where model memory and isolation requirements permit compatible shared hosting. That separate action addresses: A production endpoint hosts hundreds of small customer-specific models on separate instances, creating high fixed infrastructure cost. It cannot establish the required Alpine Healthcare correction for: A container inference service sends health checks to a path that triggers costly full model predictions and exhausts request capacity during rollouts. The decisive acceptance check is instead: Health probes confirm readiness without increasing model invocation counts or delaying normal business predictions.

The selected instance family meets throughput and latency targets with a documented cost-per-inference measurement. This would verify a different operation: Compare supported CPU, GPU or inference-optimized instances using matched representative throughput and latency tests. That separate action addresses: A high-volume endpoint runs on small CPUs despite a documented model benchmark showing matrix inference benefits from accelerator hardware. It cannot establish the required Alpine Healthcare correction for: A container inference service sends health checks to a path that triggers costly full model predictions and exhausts request capacity during rollouts. The decisive acceptance check is instead: Health probes confirm readiness without increasing model invocation counts or delaying normal business predictions.

Design the artifact sharing, replication and KMS policies explicitly for each trusted cross-account stage. It does not directly address the Juniper Media case: A container inference service sends health checks to a path that triggers costly full model predictions and exhausts request capacity during rollouts. The relevant acceptance criterion for this case is: Health probes confirm readiness without increasing model invocation counts or delaying normal business predictions.

Use a governed endpoint-variant routing or other supported traffic allocation design with versioned model identifiers. It does not directly address the Juniper Media case: A container inference service sends health checks to a path that triggers costly full model predictions and exhausts request capacity during rollouts. The relevant acceptance criterion for this case is: Health probes confirm readiness without increasing model invocation counts or delaying normal business predictions.

Require the intended registered model package approval state and enforce a deployment role boundary at the promotion stage. It does not directly address the Juniper Media case: A container inference service sends health checks to a path that triggers costly full model predictions and exhausts request capacity during rollouts. The relevant acceptance criterion for this case is: Health probes confirm readiness without increasing model invocation counts or delaying normal business predictions.

The selected instance family meets throughput and latency targets with a documented cost-per-inference measurement. This would verify a different operation: Compare supported CPU, GPU or inference-optimized instances using matched representative throughput and latency tests. That separate action addresses: A high-volume endpoint runs on small CPUs despite a documented model benchmark showing matrix inference benefits from accelerator hardware. It cannot establish the required Juniper Media correction for: A container inference service sends health checks to a path that triggers costly full model predictions and exhausts request capacity during rollouts. The decisive acceptance check is instead: Health probes confirm readiness without increasing model invocation counts or delaying normal business predictions.

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 Juniper Media correction for: A container inference service sends health checks to a path that triggers costly full model predictions and exhausts request capacity during rollouts. The decisive acceptance check is instead: Health probes confirm readiness without increasing model invocation counts or delaying normal business predictions.

Representative models load on demand and per-model latency and isolation checks meet the accepted limits at reduced aggregate cost. This would verify a different operation: Evaluate SageMaker multi-model endpoints where model memory and isolation requirements permit compatible shared hosting. That separate action addresses: A production endpoint hosts hundreds of small customer-specific models on separate instances, creating high fixed infrastructure cost. It cannot establish the required Juniper Media correction for: A container inference service sends health checks to a path that triggers costly full model predictions and exhausts request capacity during rollouts. The decisive acceptance check is instead: Health probes confirm readiness without increasing model invocation counts or delaying normal business predictions.

Maintain versioned model artifacts and use a controlled deployment strategy with retained previous endpoint configuration. It does not directly address the Timberline Foods case: A staging ML endpoint is left running after automated integration tests because infrastructure teardown is not tied to the testing lifecycle. The relevant acceptance criterion for this case is: A pipeline test creates and removes only its temporary resources and no unused endpoint remains after the workflow completes.

Choose autoscaled real-time hosting with appropriate minimum capacity and measured scaling response to the traffic pattern. It does not directly address the Timberline Foods case: A staging ML endpoint is left running after automated integration tests because infrastructure teardown is not tied to the testing lifecycle. The relevant acceptance criterion for this case is: A pipeline test creates and removes only its temporary resources and no unused endpoint remains after the workflow completes.

Add post-deployment smoke tests and monitored acceptance gates before the production release is marked successful. It does not directly address the Timberline Foods case: A staging ML endpoint is left running after automated integration tests because infrastructure teardown is not tied to the testing lifecycle. The relevant acceptance criterion for this case is: A pipeline test creates and removes only its temporary resources and no unused endpoint remains after the workflow completes.

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 Timberline Foods correction for: A staging ML endpoint is left running after automated integration tests because infrastructure teardown is not tied to the testing lifecycle. The decisive acceptance check is instead: A pipeline test creates and removes only its temporary resources and no unused endpoint remains after the workflow completes.

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 Timberline Foods correction for: A staging ML endpoint is left running after automated integration tests because infrastructure teardown is not tied to the testing lifecycle. The decisive acceptance check is instead: A pipeline test creates and removes only its temporary resources and no unused endpoint remains after the workflow completes.

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 Timberline Foods correction for: A staging ML endpoint is left running after automated integration tests because infrastructure teardown is not tied to the testing lifecycle. The decisive acceptance check is instead: A pipeline test creates and removes only its temporary resources and no unused endpoint remains after the workflow completes.

Add evaluation and conditional model-quality steps linked to the model registry approval process. It does not directly address the Keystone BioLabs case: A staging ML endpoint is left running after automated integration tests because infrastructure teardown is not tied to the testing lifecycle. The relevant acceptance criterion for this case is: A pipeline test creates and removes only its temporary resources and no unused endpoint remains after the workflow completes.

Optimize and package an appropriate model for supported edge execution with a tested offline runtime and update mechanism. It does not directly address the Keystone BioLabs case: A staging ML endpoint is left running after automated integration tests because infrastructure teardown is not tied to the testing lifecycle. The relevant acceptance criterion for this case is: A pipeline test creates and removes only its temporary resources and no unused endpoint remains after the workflow completes.

Adapt the container entrypoint, model artifact retrieval and health interface to the actual selected ECS deployment environment. It does not directly address the Keystone BioLabs case: A staging ML endpoint is left running after automated integration tests because infrastructure teardown is not tied to the testing lifecycle. The relevant acceptance criterion for this case is: A pipeline test creates and removes only its temporary resources and no unused endpoint remains after the workflow completes.

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 Keystone BioLabs correction for: A staging ML endpoint is left running after automated integration tests because infrastructure teardown is not tied to the testing lifecycle. The decisive acceptance check is instead: A pipeline test creates and removes only its temporary resources and no unused endpoint remains after the workflow completes.

Representative models load on demand and per-model latency and isolation checks meet the accepted limits at reduced aggregate cost. This would verify a different operation: Evaluate SageMaker multi-model endpoints where model memory and isolation requirements permit compatible shared hosting. That separate action addresses: A production endpoint hosts hundreds of small customer-specific models on separate instances, creating high fixed infrastructure cost. It cannot establish the required Keystone BioLabs correction for: A staging ML endpoint is left running after automated integration tests because infrastructure teardown is not tied to the testing lifecycle. The decisive acceptance check is instead: A pipeline test creates and removes only its temporary resources and no unused endpoint remains after the workflow completes.

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 Keystone BioLabs correction for: A staging ML endpoint is left running after automated integration tests because infrastructure teardown is not tied to the testing lifecycle. The decisive acceptance check is instead: A pipeline test creates and removes only its temporary resources and no unused endpoint remains after the workflow completes.

Insert automated tests and a quality-gate approval stage before promoting an approved model package to production. It does not directly address the Granite SaaS case: A stack update changes an inference endpoint's network settings without showing whether the change broadens inbound access. The relevant acceptance criterion for this case is: A risky security-group expansion is blocked during review and a permitted private endpoint change deploys successfully.

Compare Lambda, SageMaker asynchronous inference or container hosting based on payload size, memory and duration constraints. It does not directly address the Granite SaaS case: A stack update changes an inference endpoint's network settings without showing whether the change broadens inbound access. The relevant acceptance criterion for this case is: A risky security-group expansion is blocked during review and a permitted private endpoint change deploys successfully.

Split the workflow into traceable SageMaker Pipelines or Step Functions stages with typed inputs, outputs and failure handling. It does not directly address the Granite SaaS case: A stack update changes an inference endpoint's network settings without showing whether the change broadens inbound access. The relevant acceptance criterion for this case is: A risky security-group expansion is blocked during review and a permitted private endpoint change deploys successfully.

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 Granite SaaS correction for: A stack update changes an inference endpoint's network settings without showing whether the change broadens inbound access. The decisive acceptance check is instead: A risky security-group expansion is blocked during review and a permitted private endpoint change deploys successfully.

A destination test role retrieves the artifact and decrypts it while an unrelated account remains denied. This would verify a different operation: Design the artifact sharing, replication and KMS policies explicitly for each trusted cross-account stage. That separate action addresses: A cross-account promotion pipeline copies model artifacts but loses the KMS permissions required for the destination account to load them. It cannot establish the required Granite SaaS correction for: A stack update changes an inference endpoint's network settings without showing whether the change broadens inbound access. The decisive acceptance check is instead: A risky security-group expansion is blocked during review and a permitted private endpoint change deploys successfully.

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 Granite SaaS correction for: A stack update changes an inference endpoint's network settings without showing whether the change broadens inbound access. The decisive acceptance check is instead: A risky security-group expansion is blocked during review and a permitted private endpoint change deploys successfully.

Choose SageMaker asynchronous inference or a supported job-based flow with input-output object locations and completion handling. It does not directly address the Westhaven Retail case: A stack update changes an inference endpoint's network settings without showing whether the change broadens inbound access. The relevant acceptance criterion for this case is: A risky security-group expansion is blocked during review and a permitted private endpoint change deploys successfully.

Maintain versioned model artifacts and use a controlled deployment strategy with retained previous endpoint configuration. It does not directly address the Westhaven Retail case: A stack update changes an inference endpoint's network settings without showing whether the change broadens inbound access. The relevant acceptance criterion for this case is: A risky security-group expansion is blocked during review and a permitted private endpoint change deploys successfully.

Deploy an appropriately scaled low-latency real-time inference endpoint and route transaction requests through the authorized path. It does not directly address the Westhaven Retail case: A stack update changes an inference endpoint's network settings without showing whether the change broadens inbound access. The relevant acceptance criterion for this case is: A risky security-group expansion is blocked during review and a permitted private endpoint change deploys successfully.

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 Westhaven Retail correction for: A stack update changes an inference endpoint's network settings without showing whether the change broadens inbound access. The decisive acceptance check is instead: A risky security-group expansion is blocked during review and a permitted private endpoint change deploys successfully.

An oversized test input is queued, processed and retrieved asynchronously without the client's synchronous timeout. This would verify a different operation: Choose SageMaker asynchronous inference or a supported job-based flow with input-output object locations and completion handling. That separate action addresses: An image analysis API accepts infrequent large payloads with long processing times but times out when called synchronously through a normal endpoint. It cannot establish the required Westhaven Retail correction for: A stack update changes an inference endpoint's network settings without showing whether the change broadens inbound access. The decisive acceptance check is instead: A risky security-group expansion is blocked during review and a permitted private endpoint change deploys successfully.

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 Westhaven Retail correction for: A stack update changes an inference endpoint's network settings without showing whether the change broadens inbound access. The decisive acceptance check is instead: A risky security-group expansion is blocked during review and a permitted private endpoint change deploys successfully.