AG-018Agent · Final resultlayaeval.AgentCorrectness

Agent Correctness

Is the final result the correct one?

Simulation state:

When it passes

Matches the expected result.

Threshold satisfied: evaluation score >= 3.0.

When it fails

Differs from it.

Violation detected: execution flagged for human review or fallback routing.

SDK Specification

Parameter	Value	Description
Class	AgentCorrectness	Python evaluator class in layaeval
Required Fields	"task", "final_result", "ground_truth"	Arguments expected in the call signature
Default Threshold	>= 3.0	Passes when quality score is at or above this value
Category	Agent Evaluation	Final result (Is the last message true, complete and correct?)

Python Example

pip install layaeval

agent-correctness.py

1from layaeval import AgentCorrectness
2
3metric = AgentCorrectness(threshold=3.0)  # passes at or above 3.0
4
5res = metric(
6    task="Book a hotel in Paris for 2 guests on Mar 4.",
7    final_result="Booked Hotel Lumière, Mar 4, 2 guests.",
8    ground_truth="Paris",
9)
10
11print(res.passed, res.value, res.confidence)

Related Agent Checks

Other checks in Final result

View all 42 checks →

AG-014Read →

Agent Groundedness

Is the final answer backed by what the tools returned?

AG-015Read →

Agent Hallucination

Did the agent claim results that never happened?

AG-016Read →

Agent Response Relevance

Does the final message answer the user's request?

AG-017Read →

Answer Completeness

Did the final reply cover every part of the task?