Provide examples for request classification.
Stabilize format and decisions.
Choose two prompt practices.
Select accurate, representative, boundary examples with expected outputs, remove personal data and errors, and version the examples.
Detailed explanation
A wrong example can guide decisions.
Context, cost, and contradictions also grow.
The task and format are clearer.
Leakage and misleading guidance are reduced.
Check official documentation
Compare the following points with the official documentation.
AWS公式AIF-C01 Domain 2.1・2.3のプロンプト例示、コンテキスト、データ保護を確認する。
Official references
What to confirm
例示の品質・個人情報・文脈長を考慮してfew-shot入力を設計できる。
Key points
- Examples
- Boundary
- Version
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
Few-shot prompting
Showing a small number of input and output examples to communicate a task pattern.
Boundary example
An example that clarifies behavior near a decision or policy boundary.