Package datadog.trace.api.aiguard

Class AIGuard.Evaluation

java.lang.Object

datadog.trace.api.aiguard.AIGuard.Evaluation

Enclosing class:

AIGuard

public static class AIGuard.Evaluation
extends Object

Represents the result of an AIGuard security evaluation, containing both the recommended action and the reasoning behind the decision.

The evaluation provides three possible actions:

• AIGuard.Action.ALLOW - Content is safe to proceed
• AIGuard.Action.DENY - Content should be blocked
• AIGuard.Action.ABORT - Execution should be immediately terminated

Constructor Summary

Constructors

Constructor	Description
Evaluation(AIGuard.Action action, String reason, List<String> tags, Map<String,Number> tagProbs, List<?> sds)	Creates a new evaluation result.

Method Summary

Modifier and Type	Method	Description
AIGuard.Action	getAction()	Returns the recommended action for the evaluated content.
String	getReason()	Returns the human-readable reasoning for the evaluation decision.
List<?>	getSds()	Returns the list of Sensitive Data Scanner findings.
Map<String,Number>	getTagProbabilities()	Returns a map from tag to their probability (e.g.
List<String>	getTags()	Returns the list of tags associated with the evaluation (e.g.

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Details

Evaluation

public Evaluation(AIGuard.Action action,
 String reason,
 List<String> tags,
 Map<String,Number> tagProbs,
 List<?> sds)

Creates a new evaluation result.

Parameters:

action - the recommended action for the evaluated content

reason - human-readable explanation for the decision

tags - list of tags associated with the evaluation (e.g. indirect-prompt-injection)

tagProbs - map of tags associated to their probability

sds - list of Sensitive Data Scanner findings

Method Details

getAction

public AIGuard.Action getAction()

Returns the recommended action for the evaluated content.

Returns:

the action (ALLOW, DENY, or ABORT)

getReason

public String getReason()

Returns the human-readable reasoning for the evaluation decision.

Returns:

explanation of why this action was recommended

getTags

public List<String> getTags()

Returns the list of tags associated with the evaluation (e.g. indirect-prompt-injection)

Returns:

list of tags.

getTagProbabilities

public Map<String,Number> getTagProbabilities()

Returns a map from tag to their probability (e.g. [indirect-prompt-injection: 0.25])

Returns:

map of tag probabilities.

getSds

public List<?> getSds()

Returns the list of Sensitive Data Scanner findings.

Returns:

list of SDS findings.