Testing Lab

{
  id: "scenario-123",
  name: "Product Inquiry - Enterprise Plan",
  personality: "interested-buyer",  // How the test "customer" behaves
  phoneNumber: "+14155551234",      // Test phone number
  instructions: "Ask about Enterprise plan pricing and features. Show high interest. Request a demo.",
  expectedOutcomePrompt: "Agent should provide pricing, explain key features, and schedule a demo using Calendly.",
  scenarioLanguage: "en-US"
}

"Product Inquiry - Enterprise Plan"
"Support - Password Reset Request"
"Objection Handling - Price Too High"

"interested-buyer"     // Engaged and ready to purchase
"skeptical-prospect"   // Hesitant, asks lots of questions
"angry-customer"       // Frustrated, needs de-escalation
"confused-user"        // Needs extra guidance
"price-sensitive"      // Focused on cost
"technical-buyer"      // Asks detailed technical questions

"Call to inquire about return policy. Provide order number ORD-12345. Ask about timeline for refund."

"Agent should locate order, explain 30-day return policy, initiate return process, and provide return label."

{
  runId: "run-456",
  agentId: "agent-123",
  startedAt: "2024-01-20T10:00:00Z",
  completedAt: "2024-01-20T10:15:30Z",
  totalScenarios: 10,
  passed: 8,
  failed: 2,
  results: [
    {
      scenarioId: "scenario-001",
      scenarioName: "Product Demo Request",
      status: "passed",
      callId: "call-789",
      disposition: "CALENDLY",
      transcript: [...],
      evaluation: {
        matchesExpectedOutcome: true,
        score: 95,
        feedback: "Agent successfully provided pricing, explained features, and scheduled demo."
      }
    },
    {
      scenarioId: "scenario-002",
      scenarioName: "Price Objection",
      status: "failed",
      callId: "call-790",
      disposition: "ENDED",
      evaluation: {
        matchesExpectedOutcome: false,
        score: 60,
        feedback: "Agent did not offer alternative pricing options or discounts as expected."
      }
    }
  ]
}

// Get detailed test result
const result = testResults.results.find(r => r.status === 'failed');

console.log('Scenario:', result.scenarioName);
console.log('Expected:', result.scenario.expectedOutcomePrompt);
console.log('Score:', result.evaluation.score);
console.log('Feedback:', result.evaluation.feedback);

// Review transcript
result.transcript.forEach(turn => {
  console.log(`${turn.speaker}: ${turn.text}`);
});

// Listen to recording
console.log('Recording:', result.recordingUrl);

{
  name: "Perfect Demo Booking",
  personality: "interested-buyer",
  instructions: "You're interested in the product. Answer all questions positively. Book a demo when offered.",
  expectedOutcomePrompt: "Demo successfully booked with CALENDLY disposition"
}

{
  name: "Multiple Interruptions",
  personality: "distracted-customer",
  instructions: "Interrupt the agent frequently. Change topics mid-conversation. Ask unrelated questions.",
  expectedOutcomePrompt: "Agent stays patient, redirects conversation, and attempts to achieve goal"
}

{
  name: "Price Too High",
  personality: "price-sensitive",
  instructions: "Express strong interest but object to the price. Say competitors offer lower pricing.",
  expectedOutcomePrompt: "Agent explains value proposition, offers to schedule call with sales team, or mentions current promotions"
}

{
  name: "CRM System Down",
  personality: "interested-buyer",
  instructions: "Provide information for CRM update. Agent should handle gracefully if CRM tool fails.",
  expectedOutcomePrompt: "Agent acknowledges issue, collects information manually, and promises follow-up"
}

{
  name: "Knowledge Base Query",
  personality: "confused-user",
  instructions: "Ask specific question that requires knowledge base search: 'What's your return policy for opened items?'",
  expectedOutcomePrompt: "Agent uses knowledge-search tool and provides accurate answer from documentation"
}

// Organize scenarios by category
const scenarioCategories = {
  "sales": [
    "demo-booking",
    "price-objection",
    "feature-inquiry"
  ],
  "support": [
    "password-reset",
    "refund-request",
    "technical-issue"
  ],
  "edge-cases": [
    "multiple-interruptions",
    "system-failure",
    "angry-customer"
  ]
};

// In your CI/CD pipeline
async function testAgentBeforeDeployment(agentId: string, versionId: string) {
  // Get all test scenarios
  const scenarios = await getAllScenarios();

  // Run tests
  const results = await runTestScenarios({
    agentId,
    versionId,
    scenarioIds: scenarios.map(s => s.id)
  });

  // Check pass rate
  const passRate = results.passed / results.totalScenarios;

  if (passRate < 0.9) { // Require 90% pass rate
    throw new Error(`Tests failed. Pass rate: ${passRate * 100}%`);
  }

  console.log(`✅ All tests passed. Deploying agent version ${versionId}`);

  // Deploy the version
  await deployAgentVersion(agentId, versionId);
}

# pre-commit hook
#!/bin/bash

# Run tests before allowing commit
echo "Running agent tests..."
node scripts/run-tests.js

if [ $? -ne 0 ]; then
  echo "❌ Tests failed. Fix issues before committing."
  exit 1
fi

echo "✅ Tests passed"