3.3Standard
Measure the quality of email drafts.
Automated metrics cannot capture every contextual or safety issue.
Choose two appropriate practices.
× Incorrect
Automate mechanical checks and use people for contextual correctness, usefulness, and safety with explicit criteria.
Detailed explanation
CorrectHave people assess representative outputs for correctness, usefulness, and safety
Humans can judge context and ambiguous effects.
IncorrectGive reviewers no criteria
Results become inconsistent and hard to reproduce.
CorrectAutomatically check format, length, and prohibited terms
Rules can efficiently inspect large volumes.
IncorrectDeclare legal compliance from an automated score alone
Policies and expert review may be required.
Check official documentation
Compare the following points with the official documentation.
AWS公式AIF-C01ガイドDomain 3.3の生成AI評価とResponsible AIを確認する。
Official references
What to confirm
自動評価と人手評価の役割分担を説明できる。
Key points
- Automation
- Human review
- Criteria
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
Automated evaluation
Applying repeatable rules or metrics to measure outputs at scale.
Human evaluation
A reviewer judging context-dependent quality, usefulness, correctness, or safety.
Question IDAWS-AIF-123
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