Exam Bundle

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.

Add evaluation and conditional model-quality steps linked to the model registry approval process. It does not directly address the Alpine Healthcare case: 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. The relevant acceptance criterion for this case is: A fresh ECS task passes its health check and serves a controlled request without depending on SageMaker-only paths.

Select an appropriate SageMaker endpoint scaling metric such as invocations per instance and tune thresholds from measured traffic. It does not directly address the Alpine Healthcare case: 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. The relevant acceptance criterion for this case is: A fresh ECS task passes its health check and serves a controlled request without depending on SageMaker-only paths.

Tune target tracking, cooldown and minimum capacity from observed workload periodicity rather than setting a zero-tolerance threshold. It does not directly address the Alpine Healthcare case: 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. The relevant acceptance criterion for this case is: A fresh ECS task passes its health check and serves a controlled request without depending on SageMaker-only paths.

Only an approved data manifest triggers retraining and repeated notifications do not launch duplicate experiments. This would verify a different operation: Filter EventBridge or S3-trigger inputs to the intended versioned training dataset and apply an idempotent retraining key. That separate action addresses: An automated model retraining workflow starts every time any S3 object changes, including log and metadata files unrelated to training. It cannot establish the required Alpine Healthcare correction for: 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. The decisive acceptance check is instead: A fresh ECS task passes its health check and serves a controlled request without depending on SageMaker-only paths.

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 Alpine Healthcare correction for: 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. The decisive acceptance check is instead: A fresh ECS task passes its health check and serves a controlled request without depending on SageMaker-only paths.

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 Alpine Healthcare correction for: 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. The decisive acceptance check is instead: A fresh ECS task passes its health check and serves a controlled request without depending on SageMaker-only paths.

Implement a controlled canary or blue-green rollout with CloudWatch alarm gates and automatic rollback to the approved prior version. It does not directly address the Juniper Media case: 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. The relevant acceptance criterion for this case is: A fresh ECS task passes its health check and serves a controlled request without depending on SageMaker-only paths.

Define a lightweight readiness and liveness interface distinct from resource-intensive inference operations. It does not directly address the Juniper Media case: 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. The relevant acceptance criterion for this case is: A fresh ECS task passes its health check and serves a controlled request without depending on SageMaker-only paths.

Provision test environments from IaC and implement a reviewed cleanup action with protective rules for shared resources. It does not directly address the Juniper Media case: 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. The relevant acceptance criterion for this case is: A fresh ECS task passes its health check and serves a controlled request without depending on SageMaker-only paths.

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 Juniper Media correction for: 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. The decisive acceptance check is instead: A fresh ECS task passes its health check and serves a controlled request without depending on SageMaker-only paths.

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 Juniper Media correction for: 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. The decisive acceptance check is instead: A fresh ECS task passes its health check and serves a controlled request without depending on SageMaker-only paths.

A deliberately failed transform reports its stage and blocks downstream deployment without losing prior successful artifacts. This would verify a different operation: Split the workflow into traceable SageMaker Pipelines or Step Functions stages with typed inputs, outputs and failure handling. That separate action addresses: A pipeline combines data transformation, training and evaluation in one opaque shell command, obscuring which stage failed. It cannot establish the required Juniper Media correction for: 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. The decisive acceptance check is instead: A fresh ECS task passes its health check and serves a controlled request without depending on SageMaker-only paths.

Insert automated tests and a quality-gate approval stage before promoting an approved model package to production. It does not directly address the Timberline Foods case: An inference workload receives highly variable request bursts and a fixed number of endpoint instances causes long queues at peak. The relevant acceptance criterion for this case is: A synthetic peak test reaches the latency objective while instance count scales back after demand subsides.

Make the retraining input a named immutable dataset manifest and persist it in the pipeline execution parameters. It does not directly address the Timberline Foods case: An inference workload receives highly variable request bursts and a fixed number of endpoint instances causes long queues at peak. The relevant acceptance criterion for this case is: A synthetic peak test reaches the latency objective while instance count scales back after demand subsides.

Use unique version identifiers, idempotent promotion operations and recoverable state tracking around the deployment stage. It does not directly address the Timberline Foods case: An inference workload receives highly variable request bursts and a fixed number of endpoint instances causes long queues at peak. The relevant acceptance criterion for this case is: A synthetic peak test reaches the latency objective while instance count scales back after demand subsides.

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: An inference workload receives highly variable request bursts and a fixed number of endpoint instances causes long queues at peak. The decisive acceptance check is instead: A synthetic peak test reaches the latency objective while instance count scales back after demand subsides.

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 Timberline Foods correction for: An inference workload receives highly variable request bursts and a fixed number of endpoint instances causes long queues at peak. The decisive acceptance check is instead: A synthetic peak test reaches the latency objective while instance count scales back after demand subsides.

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 Timberline Foods correction for: An inference workload receives highly variable request bursts and a fixed number of endpoint instances causes long queues at peak. The decisive acceptance check is instead: A synthetic peak test reaches the latency objective while instance count scales back after demand subsides.

Reference a reviewed immutable ECR image digest alongside the exact model artifact version in the deployment configuration. It does not directly address the Keystone BioLabs case: An inference workload receives highly variable request bursts and a fixed number of endpoint instances causes long queues at peak. The relevant acceptance criterion for this case is: A synthetic peak test reaches the latency objective while instance count scales back after demand subsides.

Define a lightweight readiness and liveness interface distinct from resource-intensive inference operations. It does not directly address the Keystone BioLabs case: An inference workload receives highly variable request bursts and a fixed number of endpoint instances causes long queues at peak. The relevant acceptance criterion for this case is: A synthetic peak test reaches the latency objective while instance count scales back after demand subsides.

Require inspected infrastructure change sets and automated network-policy validation before applying the altered endpoint stack. It does not directly address the Keystone BioLabs case: An inference workload receives highly variable request bursts and a fixed number of endpoint instances causes long queues at peak. The relevant acceptance criterion for this case is: A synthetic peak test reaches the latency objective while instance count scales back after demand subsides.

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 Keystone BioLabs correction for: An inference workload receives highly variable request bursts and a fixed number of endpoint instances causes long queues at peak. The decisive acceptance check is instead: A synthetic peak test reaches the latency objective while instance count scales back after demand subsides.

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 Keystone BioLabs correction for: An inference workload receives highly variable request bursts and a fixed number of endpoint instances causes long queues at peak. The decisive acceptance check is instead: A synthetic peak test reaches the latency objective while instance count scales back after demand subsides.

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 Keystone BioLabs correction for: An inference workload receives highly variable request bursts and a fixed number of endpoint instances causes long queues at peak. The decisive acceptance check is instead: A synthetic peak test reaches the latency objective while instance count scales back after demand subsides.

Remove embedded credentials and use least-privilege runtime IAM roles or approved secret injection with image scanning. It does not directly address the Granite SaaS case: An internal model deployment needs only private enterprise connectivity but is exposed through an unintended public API path. The relevant acceptance criterion for this case is: An authorized private caller reaches inference while an internet test caller cannot discover or invoke the protected endpoint.

Make the retraining input a named immutable dataset manifest and persist it in the pipeline execution parameters. It does not directly address the Granite SaaS case: An internal model deployment needs only private enterprise connectivity but is exposed through an unintended public API path. The relevant acceptance criterion for this case is: An authorized private caller reaches inference while an internet test caller cannot discover or invoke the protected endpoint.

Require the intended registered model package approval state and enforce a deployment role boundary at the promotion stage. It does not directly address the Granite SaaS case: An internal model deployment needs only private enterprise connectivity but is exposed through an unintended public API path. The relevant acceptance criterion for this case is: An authorized private caller reaches inference while an internet test caller cannot discover or invoke the protected endpoint.

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 Granite SaaS correction for: An internal model deployment needs only private enterprise connectivity but is exposed through an unintended public API path. The decisive acceptance check is instead: An authorized private caller reaches inference while an internet test caller cannot discover or invoke the protected endpoint.

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 Granite SaaS correction for: An internal model deployment needs only private enterprise connectivity but is exposed through an unintended public API path. The decisive acceptance check is instead: An authorized private caller reaches inference while an internet test caller cannot discover or invoke the protected endpoint.

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 Granite SaaS correction for: An internal model deployment needs only private enterprise connectivity but is exposed through an unintended public API path. The decisive acceptance check is instead: An authorized private caller reaches inference while an internet test caller cannot discover or invoke the protected endpoint.