3.3Standard
Display an AI answer to a customer.
Do not make a raw score look like certainty.
Choose two appropriate designs.
× Incorrect
Display explainable evidence signals and avoid calling an uncalibrated internal score a probability; provide verification and human-review paths.
Detailed explanation
CorrectShow evidence availability, retrieval match, and evaluation conditions
Users gain information about limitations.
IncorrectHide uncertainty to emphasize automation
Users cannot judge risk.
IncorrectDisplay the internal score as exact correctness probability
Its meaning and calibration may be unknown.
CorrectAvoid claiming a raw score is a probability and provide review or search options
Unsupported certainty is reduced.
Check official documentation
Compare the following points with the official documentation.
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。
Official references
What to confirm
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
- 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
Uncertainty display
Information about evidence strength, limitations, confidence, or verification shown to a user.
Uncalibrated score
A model value that has not been shown to correspond reliably to an outcome probability.
Question IDAWS-AIF-184
EnvironmentAWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認
Last technical review2026-08-20
Report an error or rights issue