Inventorying AI dependencies | AWS Certified AI Practitioner (AIF-C01) original practice question

3.3Standard

An AI feature depends on providers, models, indexes, tools, keys, and data.

Understand outage impact.

Choose two practices.

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.

モデル・埋め込み・検索・プロンプト・ツール・外部API・鍵・データの所有者と版を一覧化する: Change and impact are traceable.
各依存のSLA・クォータ・障害・代替・更新期限・連絡先を定期レビューする: Recovery and migration are prepared.
AIモデルだけを管理し、検索や鍵はアプリの詳細なので対象外にする: Failure paths are missing.
依存が変わっても一覧を更新しない: Decisions use stale data.

Detailed explanation

CorrectList model, embedding, retrieval, prompt, tool, API, key, and data owners and versions

Change and impact are traceable.

CorrectReview SLA, quota, outage, alternative, renewal, and contact for each dependency

Recovery and migration are prepared.

IncorrectManage only the model and treat search and keys as application details

Failure paths are missing.

IncorrectNever update the inventory after dependencies change

Decisions use stale data.

An example you can run in a temporary verification environment.

AWS公式AIF-C01 Domain 3.3の依存関係、可用性、変更管理を確認する。

モデル以外の検索・認証・外部APIを含むAIサプライチェーンを追跡できる。

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-509

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