2.1Standard
Stabilize output format and use current internal knowledge.
The knowledge changes frequently.
Choose two designs.
× Incorrect
Use retrieval for changing facts and evaluate fine-tuning for repeated formats or patterns; authorization remains an independent control.
Detailed explanation
CorrectRetrieve current internal facts instead of embedding them permanently in weights
Freshness and deletion are easier to manage.
IncorrectImplement permissions only in a prompt
Authorization needs an independent control.
CorrectEvaluate fine-tuning when consistent patterns or formats require adaptation
Training data and reproducibility are managed.
IncorrectFine-tune every frequently changing fact
Updates and deletion become difficult.
Check official documentation
Compare the following points with the official documentation.
AWS公式AIF-C01 Domain 2.1・2.3の基盤モデル適応、RAG、認可を確認する。
Official references
What to confirm
知識更新・形式適応・権限を混同せず方式を選べる。
Key points
- RAG
- Fine-tuning
- Authorization
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
Fine-tuning
Updating model weights with task-specific examples to adapt behavior or format.
Retrieval-augmented generation
Supplying retrieved external information to a model as context for generation.
Question IDAWS-AIF-321
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