Where do you view endpoint latency and invocation metrics?
Why A is the answer
Amazon CloudWatch
SageMaker AI publishes endpoint metrics to CloudWatch.
In detail
- CloudWatch shows latency and invocation metrics.
- Set alarms on these metrics.
Use case
An illustrative scenario, not a real incident.
An engineer opens CloudWatch and sees that latency rose after a release.
See it in different ways
sequenceDiagram participant E as Endpoint participant S as Captured data in S3 participant M as Model Monitor participant C as CloudWatch E->>S: Capture requests and responses M->>S: Compare with the baseline M->>C: Publish violations C-->>E: Alarm starts retraining
sequenceDiagram participant E as Endpoint participant S as S3 participant M as Model Monitor participant C as CloudWatch E->>S: Data capture M->>S: Compares with the baseline M->>C: Publishes metrics C-->>M: Alarm on drift
sequenceDiagram participant P0 as Endpoint participant P1 as CloudWatch participant P2 as Engineer P0->>P1: Latency and invocations P2-->>P1: View metrics
Key point: Endpoint metrics go to CloudWatch.
Why the other options are wrong
- B. AWS CloudTrail
- CloudTrail records API calls.
- C. SageMaker Experiments
- Experiments track runs.
- D. AWS Config
- Config tracks configuration.