3.3Standard
Operate a generation service for quality and latency.
Make user promises measurable.
Choose two definitions.
× Incorrect
Define success, p95 latency, timeouts, grounded-answer rate, and safety failures with measurement windows, exclusions, alerts, and responses.
Detailed explanation
CorrectDefine success, p95 latency, timeouts, grounded-answer rate, and safety failure rate
AI-specific quality is measured.
CorrectDocument target, window, exclusions, alerts, and actions for violations
Operations become consistent.
IncorrectNever revisit an SLO after model changes
Performance and usage conditions change.
IncorrectCount HTTP 200 as the only success
Content and quality failures are missed.
Check official documentation
Compare the following points with the official documentation.
AWS公式AIF-C01 Domain 3.3の監視、SLO、生成AI運用を確認する。
Official references
What to confirm
AIサービスの技術性能と回答品質を同じ運用目標へ落とし込める。
Key points
- SLO
- p95
- Grounding
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
SLO
A measurable service-level objective that an operation aims to achieve.
p95 latency
The response time at or below which 95 percent of requests complete.
Question IDAWS-AIF-356
EnvironmentAWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認
Last technical review2026-08-20
Report an error or rights issue