Agent Judge Evaluation

import { AgentJudgeEval } from "@agentium/eval";
import { Agent, openai } from "@agentium/core";

const agent = new Agent({ name: "writer", model: openai("gpt-4o") });

const eval = new AgentJudgeEval({
  name: "writing-quality",
  agent,
  judge: openai("gpt-4o-mini"),
  criteria: [
    "Response is grammatically correct",
    "Response is concise (under 200 words)",
    "Response directly answers the question",
  ],
  scoringMode: "numeric",
  cases: [
    { name: "explain-recursion", input: "Explain recursion in simple terms" },
  ],
});

const result = await eval.run();