Package com.tnsai.evaluation.evaluators

package com.tnsai.evaluation.evaluators

Layer 1: Evaluators that score agent behavior on specific dimensions.

Since:

0.1.0

Related Packages

Package	Description
com.tnsai.evaluation	TnsAI Evaluation Framework - unified evaluation, benchmarking, and quality gating.
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.

Classes

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