1.3Standard
Compare a new model with the production model.
Keep user responses on the current model.
Choose two practices.
× Incorrect
Send a copy of production inputs to the new model without serving its response, while controlling privacy, cost, latency, and stop conditions.
Detailed explanation
CorrectDefine minimization, cost, latency, retention, and stop conditions
The comparison is operationally controlled.
IncorrectMix outputs without identifying their model version
Comparison and accountability are lost.
CorrectSend the same input to the new model without returning its response
Production-like data can be evaluated safely.
IncorrectReturn the new response without review
That is not a shadow deployment.
Check official documentation
Compare the following points with the official documentation.
AWS公式AIF-C01 Domain 1.3のデプロイ方式とモデル評価を確認する。
Official references
What to confirm
本番相当の入力で新モデルを安全に比較できる。
Key points
- Shadow
- Comparison
- Stop condition
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
Shadow deployment
Sending production inputs to a new version while keeping its outputs away from users.
Staged rollout
Increasing a new version's traffic gradually while monitoring its behavior.
Question IDAWS-AIF-319
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