Developers set up observability in your application. See Development documentation for setup instructions.
What We Track
Inference Spans - Full lifecycle of prompt execution- Token usage and costs
- Response times
- Model information
- Completion status
- Tool name and parameters
- Execution duration
- Success/failure status
- Return values
- Time to first token
- Tokens per second
- Total streaming duration
- Organize by user interaction
- Track multi-step workflows
- Monitor batch processing
- Analyze performance patterns
- Cost thresholds
- Latency monitoring
- Error rate tracking
- Evaluation score monitoring
- Notifications via Slack or webhooks
Key Features
Real-Time Monitoring - View traces and metrics as they happen in your application. Graph Visualization - Interactive visual representation of complex workflows, showing component relationships, execution flow, and dependencies. Cost Tracking - Understand your LLM spending across models, users, and time periods. Performance Analysis - Identify bottlenecks and optimize response times. Quality Assurance - Track evaluation scores and manually annotate traces for quality assessment. Flexible Integration - Works with any AI framework through OpenTelemetry standard.Next Steps
Traces and Logs
Track execution and debug issues
Graph View
Visualize complex workflows
Sessions
Group related traces together
Alerts
Get notified of critical issues
Metrics
Analyze usage and performance
Have Questions?
We’re here to help! Choose the best way to reach us:
- Join our Discord community for quick answers and discussions
- Email us at [email protected] for support
- Schedule an Enterprise Demo to learn about our business solutions