Measure the quality of email drafts.
Automated metrics cannot capture every contextual or safety issue.
Choose two appropriate practices.
Automate mechanical checks and use people for contextual correctness, usefulness, and safety with explicit criteria.
Detailed explanation
Rules can efficiently inspect large volumes.
Rules can efficiently inspect large volumes.
Humans can judge context and ambiguous effects.
Humans can judge context and ambiguous effects.
Policies and expert review may be required.
Policies and expert review may be required.
Results become inconsistent and hard to reproduce.
Results become inconsistent and hard to reproduce.
Try it yourself
An example you can run in a temporary verification environment.
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。Expected result
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
- Command output formatting can vary slightly by distribution or tool version.
- Run the example in a temporary directory or process when possible.
Foundation review
Read the scope first
Check whether the command acts on the current shell, a new process, an existing process, or a file.
Verify the observable result
Use the supplied command and compare the output with the expected result.