3.1Standard
A voice assistant must answer within 200 ms.
Maintain quality while meeting the target.
Choose two comparisons.
× Incorrect
Measure p50 and p95 latency, output length, quality, and safety under the same inputs, then evaluate smaller models, streaming, and caching.
Detailed explanation
CorrectEvaluate a smaller model, shorter output, streaming, and caching
Several configurations can meet the requirement.
CorrectMeasure p50 and p95 latency, output length, quality, and safety for each model
Slow tail requests are visible.
IncorrectMinimize latency while ignoring quality and safety
User impact and risk increase.
IncorrectIf average latency is 200 ms, p95 is guaranteed to be 200 ms
Tail latency can be higher.
Check official documentation
Compare the following points with the official documentation.
Amazon Bedrock公式モデル選択、推論性能、AIF-C01 Domain 3.1を確認する。
Official references
What to confirm
平均値だけでなくテール遅延と品質・安全性を含めてモデルを選べる。
Key points
- p95
- Streaming
- Quality
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
p95 latency
The time within which 95 percent of requests complete, exposing slower tail behavior.
Streaming response
Returning generated output incrementally instead of waiting for the complete response.
Question IDAWS-AIF-242
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