Generate answers about internal policies.
Do not assert invented clauses or URLs.
Choose two mitigations.
Ground answers in approved sources, cite them, evaluate factuality, and defer or route to humans when evidence is insufficient.
Detailed explanation
Generation is grounded in verifiable data.
Generation is grounded in verifiable data.
Errors can be detected and safely handled.
Errors can be detected and safely handled.
Fluency does not prove facts.
Fluency does not prove facts.
Users cannot verify it and are misled.
Users cannot verify it and are misled.
Try it yourself
An example you can run in a temporary verification environment.
AWS公式AIF-C01 Domain 2.3とAmazon Bedrock Knowledge Basesのグラウンディングを確認する。Expected result
流暢な生成と根拠に基づく回答を区別し、保留条件を設計できる。Key points
- Hallucination
- Grounding
- Citation
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
- Command output formatting can vary slightly by distribution or tool version.
- Run the example in a temporary directory or process when possible.
Foundation review
Read the scope first
Check whether the command acts on the current shell, a new process, an existing process, or a file.
Verify the observable result
Use the supplied command and compare the output with the expected result.