Ask a model to explain an answer.
Avoid disclosing secrets or internal instructions unnecessarily.
Choose two appropriate practices.
Return useful evidence, concise rationale, and uncertainty while protecting system instructions, secrets, and internal logs; generated explanations also require validation.
Detailed explanation
The user gets decision support without unnecessary internal data.
Generated text must not expose protected information.
This can expose secrets or confuse users.
An explanation is also generated content and can be wrong.
Check official documentation
Compare the following points with the official documentation.
AWS公式AIF-C01 Domain 2.3・4.2のプロンプト、透明性、機密保護を確認する。
Official references
What to confirm
説明の有用性と、内部情報を無制限に公開しない設計を説明できる。
Key points
- Useful rationale
- Secret protection
- Validation
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
Explanation summary
A concise description of relevant evidence, limitations, and uncertainty behind a result.
Confidential boundary
Information such as secrets, private instructions, or internal logs that must not be disclosed.