SpanGuardrailAssessment
Result of a single guardrail assessment, covering either the input (customer/user message) or the output (LLM response) of a Bedrock Converse call.
Contents
- action
-
Outcome of the guardrail assessment.
Type: String
Valid Values:
NONE | BLOCKED | MASKEDRequired: Yes
- guardrailId
-
Unique AI Guardrail identifier.
Type: String
Length Constraints: Minimum length of 1. Maximum length of 4096.
Required: Yes
- guardrailName
-
Customer-defined display name of the AI Guardrail resource.
Type: String
Length Constraints: Minimum length of 1. Maximum length of 4096.
Required: Yes
- source
-
Content source the guardrail was evaluated against.
Type: String
Valid Values:
INPUT | OUTPUTRequired: Yes
- policies
-
Per-policy assessment results. Absent or empty when action is NONE.
Type: Array of GuardrailPolicyResult objects
Array Members: Minimum number of 0 items. Maximum number of 50 items.
Required: No
See Also
For more information about using this API in one of the language-specific AWS SDKs, see the following:
