Choosing an incident fallback | AWS Certified AI Practitioner (AIF-C01) original practice question

3.3Standard

An external model becomes slow and errors increase.

Switch safely to an alternative.

Choose two responses.

Hint 1: Focus on the requirement

Identify what must change and what must remain unchanged. Then choose the command whose scope matches that requirement.

Hint 2: Check each command's role

Separate commands that display information, change state, remove data, or affect a child process.

Detailed explanation

CorrectSwitch on timeout, errors, or budget conditions to rules, retrieval-only, or another model

Dependency impact is limited.

CorrectDefine quality differences, user notice, retries, and recovery monitoring

The fallback is controlled.

IncorrectRetry the same external API without limit

Failure and cost can amplify.

IncorrectPresent a fallback as identical quality

Users receive a false expectation.

An example you can run in a temporary verification environment.

AWS公式AIF-C01 Domain 3.3の障害対応、フォールバック、可用性を確認する。

外部依存障害時に再試行の増幅を防ぎ、品質差を説明した代替処理へ移行できる。

Foundation review

Check whether the command acts on the current shell, a new process, an existing process, or a file.

Use the supplied command and compare the output with the expected result.

Question IDAWS-AIF-357

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