Vizra ADK Evaluation Framework

Vizra ADK Evaluation Framework

The evaluation framework enables automated testing of AI agents at scale, including LLM-as-a-Judge evaluation patterns.

Core Concepts

Creating Evaluations

Basic Evaluation

<?php

namespace App\Evaluations;

use Vizra\VizraADK\Evaluations\BaseEvaluation;

class CustomerServiceEvaluation extends BaseEvaluation
{
    /**
     * The agent being evaluated
     */
    protected string $agent = 'customer_service';

    /**
     * Evaluation description
     */
    protected string $description = 'Evaluates customer service agent responses';

    /**
     * Define test cases
     */
    public function testCases(): array
    {
        return [
            [
                'name' => 'greeting_response',
                'input' => 'Hello, I need help with my order',
                'assertions' => [
                    'contains_greeting',
                    'offers_assistance',
                    'professional_tone',
                ],
            ],
            [
                'name' => 'refund_request',
                'input' => 'I want a refund for order #12345',
                'context' => [
                    'order_id' => '12345',
                    'order_status' => 'delivered',
                ],
                'assertions' => [
                    'acknowledges_request',
                    'asks_for_reason',
                    'explains_policy',
                ],
            ],
            [
                'name' => 'complaint_handling',
                'input' => 'This is terrible service! I\'ve been waiting for weeks!',
                'assertions' => [
                    'empathetic_response',
                    'apologizes',
                    'offers_solution',
                    'no_defensive_language',
                ],
            ],
        ];
    }
}