Graph View
Interactive visualization of AI agent workflows showing component relationships, execution flow, and data dependencies.Graph metadata is added by developers during trace creation. See Development documentation for implementation details.
When to Use
Complex workflows - Multi-step agents, conditional logic, parallel operations Debugging - Trace errors, identify bottlenecks, understand behavior Optimization - Find redundant operations, parallelization opportunities Documentation - Explain architecture, train team membersNode Types
Router - Orchestration and decisions (diamond shape) LLM - Model inference (rounded rectangle, shows model name and tokens) Tool - Function calls (square, shows duration and status) Retrieval - Database/search queries (database icon, shows results) Memory - Storage operations (storage icon, cache hit/miss) Agent - Multi-step reasoning (robot icon, shows iterations)Edge Types
Sequential - Solid lines showing step-by-step execution Parallel - Multiple edges from same source (concurrent operations) Conditional - Labeled edges showing which branch was taken Data Flow - Shows data passing between nodesInteractive Features
Navigation - Drag to pan, scroll to zoom, double-click to center, fit-to-screen button Node Details - Click nodes to see inputs, outputs, execution time, tokens, errors Path Highlighting - Show critical path (bottlenecks), error paths, or data flowKeyboard Shortcuts
Space + Drag pan | +/- zoom | F fit | Click select | H/V/C layouts
Next Steps
Traces and Logs
Detailed trace information
Sessions
Group related traces together
Metrics
Analyze aggregate performance
Alerts
Set up notifications for issues
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