Features
Simulates AI agent interactions across real workflows
Captures tool calls, errors, friction, and latency
Records agent reasoning behind each decision
Provides actionable recommendations to fix issues
Detects install errors and doc mismatches
Tracks agent discovery and task completion
Logs full transparency on every simulation run
Supports multiple AI agent frameworks
Runs daily agent experience tests automatically
Ranks product visibility among AI agents
Monitors usage friction in agent-driven flows
Distributed tracing for LLM agents
Capture prompts, retrievals, tool calls, outputs
Human annotations on traces
Create datasets from traces
Run experiments to compare changes
OpenTelemetry-native instrumentation
Self-host locally, Docker, or Kubernetes
Cloud instances with free tier
Vendor agnostic: any model or framework
3M+ monthly downloads, 9k+ GitHub stars
