Display an AI answer to a customer.
Do not make a raw score look like certainty.
Choose two appropriate designs.
Display explainable evidence signals and avoid calling an uncalibrated internal score a probability; provide verification and human-review paths.
Detailed explanation
Users gain information about limitations.
Users gain information about limitations.
Unsupported certainty is reduced.
Unsupported certainty is reduced.
Its meaning and calibration may be unknown.
Its meaning and calibration may be unknown.
Users cannot judge risk.
Users cannot judge risk.
Try it yourself
An example you can run in a temporary verification environment.
AWS公式AIF-C01 Domain 3.3・4.2の生成AI評価、透明性、不確実性を確認する。Expected result
スコアと確率の違い、利用者向けの確認導線を説明できる。Key points
- Uncertainty
- Evidence
- Overtrust
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.