An internal help-desk bot cannot find evidence for an answer.
A wrong answer could stop a business process.
Which design is most appropriate?
Show that evidence is missing, do not finalize the response, and escalate to a human reviewer.
Detailed explanation
A human can verify the answer before it affects the user.
A human can verify the answer before it affects the user.
A plausible but unsupported answer can cause harm.
A plausible but unsupported answer can cause harm.
Users cannot judge uncertainty and may over-trust the result.
Users cannot judge uncertainty and may over-trust the result.
Logs are needed for analysis and improvement.
Logs are needed for analysis and improvement.
Try it yourself
An example you can run in a temporary verification environment.
AWS公式AIF-C01ガイドDomain 3.4の人間の監督・安全な失敗を確認する。Expected result
不確実性を検出し、自動処理を止めて人へ引き継ぐ運用を説明できる。Key points
- Uncertainty
- Fallback
- Human review
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.