Exam Bundle

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 Harborline Logistics correction for: A platform team deploys a custom PyTorch inference container without the correct SageMaker-compatible serving endpoint contract. The decisive acceptance check is instead: The endpoint becomes healthy and returns a valid prediction for a documented JSON request through the SageMaker invocation API.

The runtime can read its designated artifacts and log streams but cannot modify unrelated CloudFormation stacks. This would verify a different operation: Separate infrastructure deployment roles from runtime execution roles with narrowly scoped resource access policies. That separate action addresses: A deployment template grants one IAM role both model-serving permissions and broad stack-administration privileges unrelated to inference. It cannot establish the required Harborline Logistics correction for: A platform team deploys a custom PyTorch inference container without the correct SageMaker-compatible serving endpoint contract. The decisive acceptance check is instead: The endpoint becomes healthy and returns a valid prediction for a documented JSON request through the SageMaker invocation API.

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 Harborline Logistics correction for: A platform team deploys a custom PyTorch inference container without the correct SageMaker-compatible serving endpoint contract. The decisive acceptance check is instead: The endpoint becomes healthy and returns a valid prediction for a documented JSON request through the SageMaker invocation API.

Express the approved endpoint, model and networking settings in CloudFormation or AWS CDK infrastructure definitions with reviewed parameters. It does not directly address the Silvercrest University case: 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. The relevant acceptance criterion for this case is: The test traffic follows the approved proportion and logs identify exactly which model variant served each request.

Use the intended durable artifact storage pattern and reproducible infrastructure definitions rather than node-local attachment assumptions. It does not directly address the Silvercrest University case: 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. The relevant acceptance criterion for this case is: The test traffic follows the approved proportion and logs identify exactly which model variant served each request.

Pass an immutable ECR image digest as a build artifact to the deployment stage rather than reconstructing a tag. It does not directly address the Silvercrest University case: 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. The relevant acceptance criterion for this case is: The test traffic follows the approved proportion and logs identify exactly which model variant served each request.

Two identical trigger messages resolve to the expected single logical model update without competing untracked releases. This would verify a different operation: Include stable dataset IDs and idempotency controls in the orchestration design, preserving run lineage and concurrency policies. That separate action addresses: A retraining pipeline can be launched twice for the same input data, creating competing model versions with indistinguishable metadata. It cannot establish the required Silvercrest University correction for: 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. The decisive acceptance check is instead: The test traffic follows the approved proportion and logs identify exactly which model variant served each request.

A clean model endpoint starts on the intended instance and no executable-format error appears in the startup logs. This would verify a different operation: Build and publish a runtime image for the target supported architecture and pin matching instance and container metadata. That separate action addresses: An inference platform chooses an EC2 instance family without ensuring that the container architecture matches its CPU instruction set. It cannot establish the required Silvercrest University correction for: 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. The decisive acceptance check is instead: The test traffic follows the approved proportion and logs identify exactly which model variant served each request.

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 Silvercrest University correction for: 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. The decisive acceptance check is instead: The test traffic follows the approved proportion and logs identify exactly which model variant served each request.

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 Pinecrest Hotels case: 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. The relevant acceptance criterion for this case is: The test traffic follows the approved proportion and logs identify exactly which model variant served each request.

Define a lightweight readiness and liveness interface distinct from resource-intensive inference operations. It does not directly address the Pinecrest Hotels case: 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. The relevant acceptance criterion for this case is: The test traffic follows the approved proportion and logs identify exactly which model variant served each request.

Filter EventBridge or S3-trigger inputs to the intended versioned training dataset and apply an idempotent retraining key. It does not directly address the Pinecrest Hotels case: 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. The relevant acceptance criterion for this case is: The test traffic follows the approved proportion and logs identify exactly which model variant served each request.

Two identical trigger messages resolve to the expected single logical model update without competing untracked releases. This would verify a different operation: Include stable dataset IDs and idempotency controls in the orchestration design, preserving run lineage and concurrency policies. That separate action addresses: A retraining pipeline can be launched twice for the same input data, creating competing model versions with indistinguishable metadata. It cannot establish the required Pinecrest Hotels correction for: 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. The decisive acceptance check is instead: The test traffic follows the approved proportion and logs identify exactly which model variant served each request.

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 Pinecrest Hotels correction for: 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. The decisive acceptance check is instead: The test traffic follows the approved proportion and logs identify exactly which model variant served each request.

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 Pinecrest Hotels correction for: 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. The decisive acceptance check is instead: The test traffic follows the approved proportion and logs identify exactly which model variant served each request.

Define a lightweight readiness and liveness interface distinct from resource-intensive inference operations. It does not directly address the Oakridge Public Services case: A low-latency image model deployed to a generic instance experiences unnecessary network delay because request payloads transit a distant AWS Region. The relevant acceptance criterion for this case is: Requests from representative client Regions meet the permitted total latency without violating data-residency controls.

Remove embedded credentials and use least-privilege runtime IAM roles or approved secret injection with image scanning. It does not directly address the Oakridge Public Services case: A low-latency image model deployed to a generic instance experiences unnecessary network delay because request payloads transit a distant AWS Region. The relevant acceptance criterion for this case is: Requests from representative client Regions meet the permitted total latency without violating data-residency controls.

Require the intended registered model package approval state and enforce a deployment role boundary at the promotion stage. It does not directly address the Oakridge Public Services case: A low-latency image model deployed to a generic instance experiences unnecessary network delay because request payloads transit a distant AWS Region. The relevant acceptance criterion for this case is: Requests from representative client Regions meet the permitted total latency without violating data-residency controls.

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 Oakridge Public Services correction for: A low-latency image model deployed to a generic instance experiences unnecessary network delay because request payloads transit a distant AWS Region. The decisive acceptance check is instead: Requests from representative client Regions meet the permitted total latency without violating data-residency controls.

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 Oakridge Public Services correction for: A low-latency image model deployed to a generic instance experiences unnecessary network delay because request payloads transit a distant AWS Region. The decisive acceptance check is instead: Requests from representative client Regions meet the permitted total latency without violating data-residency controls.

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 Oakridge Public Services correction for: A low-latency image model deployed to a generic instance experiences unnecessary network delay because request payloads transit a distant AWS Region. The decisive acceptance check is instead: Requests from representative client Regions meet the permitted total latency without violating data-residency controls.

Add post-deployment smoke tests and monitored acceptance gates before the production release is marked successful. It does not directly address the Harborview Insurance case: A low-latency image model deployed to a generic instance experiences unnecessary network delay because request payloads transit a distant AWS Region. The relevant acceptance criterion for this case is: Requests from representative client Regions meet the permitted total latency without violating data-residency controls.

Require inspected infrastructure change sets and automated network-policy validation before applying the altered endpoint stack. It does not directly address the Harborview Insurance case: A low-latency image model deployed to a generic instance experiences unnecessary network delay because request payloads transit a distant AWS Region. The relevant acceptance criterion for this case is: Requests from representative client Regions meet the permitted total latency without violating data-residency controls.

Pin reviewed source commits or release tags and record their identities with immutable model and image artifacts. It does not directly address the Harborview Insurance case: A low-latency image model deployed to a generic instance experiences unnecessary network delay because request payloads transit a distant AWS Region. The relevant acceptance criterion for this case is: Requests from representative client Regions meet the permitted total latency without violating data-residency controls.

The model container loads from authorized private resources and an unapproved subnet remains unable to reach the endpoint. This would verify a different operation: Configure the supported SageMaker VPC subnet, security group and endpoint-access rules for required private dependencies. That separate action addresses: A SageMaker endpoint runs inside private subnets but the security groups omit the intended dependency paths and container startup fails. It cannot establish the required Harborview Insurance correction for: A low-latency image model deployed to a generic instance experiences unnecessary network delay because request payloads transit a distant AWS Region. The decisive acceptance check is instead: Requests from representative client Regions meet the permitted total latency without violating data-residency controls.

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 Harborview Insurance correction for: A low-latency image model deployed to a generic instance experiences unnecessary network delay because request payloads transit a distant AWS Region. The decisive acceptance check is instead: Requests from representative client Regions meet the permitted total latency without violating data-residency controls.

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 Harborview Insurance correction for: A low-latency image model deployed to a generic instance experiences unnecessary network delay because request payloads transit a distant AWS Region. The decisive acceptance check is instead: Requests from representative client Regions meet the permitted total latency without violating data-residency controls.

Filter EventBridge or S3-trigger inputs to the intended versioned training dataset and apply an idempotent retraining key. It does not directly address the Redstone Aviation case: A multi-model server has frequent model cold loads that exceed the acceptance latency target for its highest-traffic model. The relevant acceptance criterion for this case is: A peak traffic replay meets p95 latency and shows the critical model remains available without repeated cold-load stalls.

Add evaluation and conditional model-quality steps linked to the model registry approval process. It does not directly address the Redstone Aviation case: A multi-model server has frequent model cold loads that exceed the acceptance latency target for its highest-traffic model. The relevant acceptance criterion for this case is: A peak traffic replay meets p95 latency and shows the critical model remains available without repeated cold-load stalls.

Separate pipeline, build, training and serving roles with narrowly scoped permissions for their specific stages. It does not directly address the Redstone Aviation case: A multi-model server has frequent model cold loads that exceed the acceptance latency target for its highest-traffic model. The relevant acceptance criterion for this case is: A peak traffic replay meets p95 latency and shows the critical model remains available without repeated cold-load stalls.

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 Redstone Aviation correction for: A multi-model server has frequent model cold loads that exceed the acceptance latency target for its highest-traffic model. The decisive acceptance check is instead: A peak traffic replay meets p95 latency and shows the critical model remains available without repeated cold-load stalls.

Two identical trigger messages resolve to the expected single logical model update without competing untracked releases. This would verify a different operation: Include stable dataset IDs and idempotency controls in the orchestration design, preserving run lineage and concurrency policies. That separate action addresses: A retraining pipeline can be launched twice for the same input data, creating competing model versions with indistinguishable metadata. It cannot establish the required Redstone Aviation correction for: A multi-model server has frequent model cold loads that exceed the acceptance latency target for its highest-traffic model. The decisive acceptance check is instead: A peak traffic replay meets p95 latency and shows the critical model remains available without repeated cold-load stalls.

The model container loads from authorized private resources and an unapproved subnet remains unable to reach the endpoint. This would verify a different operation: Configure the supported SageMaker VPC subnet, security group and endpoint-access rules for required private dependencies. That separate action addresses: A SageMaker endpoint runs inside private subnets but the security groups omit the intended dependency paths and container startup fails. It cannot establish the required Redstone Aviation correction for: A multi-model server has frequent model cold loads that exceed the acceptance latency target for its highest-traffic model. The decisive acceptance check is instead: A peak traffic replay meets p95 latency and shows the critical model remains available without repeated cold-load stalls.