Operate an internal summarization application in production.
Detect quality degradation, latency, and cost increases early.
Choose two appropriate monitoring practices.
Track operational metrics and run representative quality and safety evaluations regularly; protect sensitive prompt and output logs.
Detailed explanation
Changes can cause regressions even when the service is available.
Investigation and safe communication would be impossible.
Logs can become a data-leak source.
These show user experience, availability, and cost drivers.
Check official documentation
Compare the following points with the official documentation.
AWS公式AIF-C01ガイドDomain 3.4の監視・ログ・評価とAmazon CloudWatchの説明を確認する。
Official references
What to confirm
運用指標と品質指標を分けずに、機密性を考慮して監視する方法を説明できる。
Key points
- Operational metrics
- Quality regression
- Log protection
Notes
- Environment: AWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認
- Compare the definition with the AIF-C01 objective and the service documentation before applying it.
- Keep the concept separate from a particular answer choice or implementation step.
Foundation review
Observability
The ability to infer system state and causes from logs, metrics, traces, and related signals.
Quality regression
A decline in a previously accepted quality or safety measure after a change.