Agent Judge Evaluation

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

const agent = new Agent({ name: "writer", model: openai(process.env.OPENAI_MODEL ?? "gpt-6.1-sol") });

const evaluator = new AgentJudgeEval({
  name: "writing-quality",
  agent,
  judge: openai(process.env.OPENAI_FAST_MODEL ?? "gpt-6-luna"),
  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" },
  ],
});

try {
  const result = await evaluator.run();
  console.log(`${result.passed}/${result.total} passed`);
  if (result.failed > 0) process.exitCode = 1;
} finally {
  await agent.close();
}