Extract category and urgency from a support request.
A downstream system expects JSON.
Which prompt design is most appropriate?
Specify the schema, allowed values, examples, and output constraints, then validate the generated result.
Detailed explanation
The model can still omit fields or produce invalid syntax.
User input and trusted instructions must be separated.
An explicit schema makes downstream parsing more reliable.
The output shape may vary and parsing can fail.
Check official documentation
Compare the following points with the official documentation.
Amazon BedrockのPrompt Managementまたはモデル推論ガイドで、プロンプトと構造化出力の例を確認する。
Official references
What to confirm
指示、入力データ、出力スキーマ、検証を分けたプロンプト設計を説明できる。
Key points
- Output schema
- Separating input from instructions
- Post-generation validation
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
Parser safety
A schema helps downstream code parse the result, but it does not replace authorization or business validation.
Instruction separation
User-provided text should not be interpreted as a privileged instruction merely because a model generated it.