Skip to main content
Test prompt changes against real production traces before deployment.

​
Workflow

1. Capture baseline: 
await lumina.createReplaySet({
  name: 'Pre-prompt-change',
  filters: {
    service: 'chat-api',
    timeRange: '24h',
    sampleSize: 100,
  },
});
2. Make changes: Update your prompts or code. 3. Replay: 
await lumina.replayTraces({
  replaySetId: 'replay_001',
});
4. Compare: View side-by-side diffs with semantic scoring.

​
Use Cases

  • Prompt engineering
  • Model changes
  • Infrastructure testing
  • A/B testing

​
Cost Considerations

Replay makes real LLM API calls: 
100 traces × $0.01 per call = $1.00
Use simulation mode for testing without costs: 
await lumina.replayTraces({
  replaySetId: 'replay_001',
  mode: 'simulation',
});