Evaluate AI That Actually Works

import { Evaluation } from 'evals.do';

const agentEvaluation = new Evaluation({
    name: 'Customer Support Agent Evaluation',
    description: 'Evaluate the performance of customer support agent responses',
    target: 'customer-support-agent',
    metrics: [
      {
        name: 'accuracy',
        description: 'Correctness of information provided',
        scale: [0, 5],
        threshold: 4.0
      },
      {
        name: 'helpfulness',
        description: 'How well the response addresses the customer need',
        scale: [0, 5],
        threshold: 4.2
      },
      {
        name: 'tone',
        description: 'Appropriateness of language and tone',
        scale: [0, 5],
        threshold: 4.5
      }
    ],
    dataset: 'customer-support-queries',
    evaluators: ['human-review', 'automated-metrics']
  });