Explain an AI decision to developers, business users, and customers.
Do not show the same technical material to everyone.
Which design is appropriate?
Tailor purpose, evidence, limits, responsibility, and recourse to what each audience needs to decide safely.
Detailed explanation
Different users need different information to make informed decisions.
Different users need different information to make informed decisions.
Raw weights are not a meaningful explanation for most users.
Raw weights are not a meaningful explanation for most users.
This encourages overconfidence and misuse.
This encourages overconfidence and misuse.
Without explanation and recourse, transparency is lost.
Without explanation and recourse, transparency is lost.
Try it yourself
An example you can run in a temporary verification environment.
AWS公式AIF-C01ガイドDomain 4.2の透明性・説明可能性を確認する。Expected result
同じ説明を全員へ出すのではなく、利用者の役割に合わせる理由を説明できる。Key points
- Audience
- Evidence
- Limits and recourse
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.