Topic lessonTopic: Bedrock inference, retrieval and operating decisions
Test Amazon Bedrock Guardrails coverage and false decisions
Guardrails evaluate policies on supported paths with appropriate configuration. Verify expected denials and preservation of legitimate use.
Use harmless synthetic inputs to verify the policy version and both kinds of decision.
The cases use fictional inputs.
What to predict
Guardrails evaluate policies on supported paths with appropriate configuration. Verify expected denials and preservation of legitimate use.
- Inputs → CoverageAlign conditions
- Coverage → DecisionCompare outcomes
- Decision → CorrectionVerify the decision
- Inputs
- Synthetic glossary request
- Coverage
- Fictional sensitive classification label
- Decision
- Policy coverage on a new path is unknown
- Correction
- A legitimate term was rejected
Compare the cases
| Case | Conditions | Decision |
|---|---|---|
| an ordinary request | Synthetic glossary request | Verify expected allowance |
| a covered policy case | Fictional sensitive classification label | Verify expected rejection and its scope |
| a new invocation path | Policy coverage on a new path is unknown | Inspect policy version and input-output coverage |
| a false rejection | A legitimate term was rejected | Preserve conditions for the policy owner |
Acceptance and limits
Evidence applies to the tested configuration. Quality, permissions, approval and data classification require separate checks.
Fix the invocation path and version.
Test allowed and rejected fixtures.
Include false decisions in acceptance.
Check your understanding
Choose an option to see the result and explanation.
Check, then explain in your own words
- Fix the invocation path and version.
- Test allowed and rejected fixtures.
- Include false decisions in acceptance.
Check your understanding: Use harmless synthetic inputs to verify the policy version and both kinds of decision.
Evidence applies to the tested configuration. Quality, permissions, approval and data classification require separate checks.
Include false decisions in acceptance.
Sources and conditions checked
The official references used in this lesson are collected here with their scope, conditions and corresponding sections. Independent expert review and live AWS comparison have not been performed.
Scope and conditionsGuardrails evaluate policies on supported paths with appropriate configuration. Verify expected denials and preservation of legitimate use.
Used in this lessonWhat to predict Acceptance and limits