Uses of Interface
com.tnsai.evaluation.spi.Evaluator

Packages that use Evaluator

Package	Description
com.tnsai.evaluation.benchmark	Layer 2: Benchmark engine for running test datasets, collecting results, and detecting regressions against saved baselines.
com.tnsai.evaluation.bridge
com.tnsai.evaluation.evaluators	Layer 1: Evaluators that score agent behavior on specific dimensions.
com.tnsai.evaluation.evaluators.agent	Agent-tier evaluators (TNS-373).
com.tnsai.evaluation.evaluators.geval	G-Eval: LLM-as-judge evaluation using chain-of-thought scoring.
com.tnsai.evaluation.evaluators.multiturn	Multi-turn conversation evaluation metrics.
com.tnsai.evaluation.evaluators.rag	RAG (Retrieval-Augmented Generation) evaluation metrics.
com.tnsai.evaluation.evaluators.safety	Safety evaluation metrics for LLM outputs.
com.tnsai.evaluation.junit

Uses of Evaluator in com.tnsai.evaluation.benchmark

Methods in com.tnsai.evaluation.benchmark with parameters of type Evaluator

Modifier and Type	Method	Description
BenchmarkRunner.Builder	BenchmarkRunner.Builder.evaluator(Evaluator evaluator)

Method parameters in com.tnsai.evaluation.benchmark with type arguments of type Evaluator

Modifier and Type	Method	Description
BenchmarkRunner.Builder	BenchmarkRunner.Builder.evaluators(List<Evaluator> evaluators)

Uses of Evaluator in com.tnsai.evaluation.bridge

Methods in com.tnsai.evaluation.bridge with parameters of type Evaluator

Modifier and Type	Method	Description
TraceEvalBridge.Builder	TraceEvalBridge.Builder.evaluator(Evaluator evaluator)

Method parameters in com.tnsai.evaluation.bridge with type arguments of type Evaluator

Modifier and Type	Method	Description
TraceEvalBridge.Builder	TraceEvalBridge.Builder.evaluators(List<Evaluator> evaluators)

Uses of Evaluator in com.tnsai.evaluation.evaluators

Classes in com.tnsai.evaluation.evaluators that implement Evaluator

Modifier and Type	Class	Description
class	AbstractJudgeEvaluator	Base for single-call LLM-as-judge evaluators: build one prompt, send it to the LLMJudge once, parse the verdict.
final class	CostEfficiencyEvaluator	Evaluates cost efficiency: cost per successful task completion.
final class	InstructionFollowingEvaluator	Evaluates whether the agent followed given instructions.
final class	JsonCorrectnessEvaluator	Evaluates JSON correctness of agent output — parse validity, required fields, and type conformance.
final class	ResponseQualityEvaluator	Evaluates response quality across three dimensions: relevance, completeness, and accuracy.
final class	ToolSelectionEvaluator	Evaluates whether the agent selected the correct tools in the right order.

Uses of Evaluator in com.tnsai.evaluation.evaluators.agent

Classes in com.tnsai.evaluation.evaluators.agent that implement Evaluator

Modifier and Type	Class	Description
final class	PlanAdherenceEvaluator	Agent-tier metric: did the agent stick to its declared plan?
final class	StepEfficiencyEvaluator	Agent-tier metric: did the agent reach the goal without burning extra tool calls?
final class	TaskCompletionEvaluator	Agent-tier metric: did the agent's final state actually solve the task?
final class	ToolCorrectnessEvaluator	Agent-tier metric: were the tools the agent invoked semantically appropriate for the task?

Uses of Evaluator in com.tnsai.evaluation.evaluators.geval

Classes in com.tnsai.evaluation.evaluators.geval that implement Evaluator

Modifier and Type	Class	Description
final class	GEvalEvaluator	G-Eval: LLM-as-judge evaluator using a 2-step chain-of-thought process.

Uses of Evaluator in com.tnsai.evaluation.evaluators.multiturn

Classes in com.tnsai.evaluation.evaluators.multiturn that implement Evaluator

Modifier and Type	Class	Description
final class	ConversationCompletenessEvaluator	Measures whether a multi-turn conversation achieved its stated goal.
final class	KnowledgeRetentionEvaluator	Measures whether the agent retains information from earlier conversation turns.
final class	TurnRelevancyEvaluator	Measures whether the last assistant turn is relevant to the preceding conversation context.

Uses of Evaluator in com.tnsai.evaluation.evaluators.rag

Classes in com.tnsai.evaluation.evaluators.rag that implement Evaluator

Modifier and Type	Class	Description
final class	AnswerRelevancyEvaluator	Measures whether the agent's response actually addresses the user's query.
final class	ContextualPrecisionEvaluator	Measures whether retrieved documents are relevant to the query.
final class	ContextualRecallEvaluator	Measures whether all relevant information needed for the answer was retrieved.
final class	FaithfulnessEvaluator	Measures whether the agent's response is grounded in retrieved documents.

Uses of Evaluator in com.tnsai.evaluation.evaluators.safety

Classes in com.tnsai.evaluation.evaluators.safety that implement Evaluator

Modifier and Type	Class	Description
final class	BiasEvaluator	Detects demographic, cultural, or ideological bias in agent responses.
final class	HallucinationEvaluator	Detects hallucinated content in agent responses by checking factual claims against provided context.
final class	PIILeakageEvaluator	Detects PII leakage in agent responses using regex + checksum validation.
final class	ToxicityEvaluator	Detects toxic, harmful, or offensive content in agent responses.

Uses of Evaluator in com.tnsai.evaluation.junit

Methods in com.tnsai.evaluation.junit with parameters of type Evaluator

Modifier and Type	Method	Description
EvalAssert.EvalAssertion	EvalAssert.assertEval(String agentOutput, Evaluator... evaluators)	Runs evaluators against the agent output and returns an assertion chain.
EvalAssert.EvalAssertion	EvalAssert.assertEval(String agentOutput, Map<String,Object> metadata, Evaluator... evaluators)	Runs evaluators with additional metadata (tool sequences, latency, etc.).