Visualising Agent Runs (Langfuse, LangSmith)
Drop into Langfuse or LangSmith UIs to inspect a trace tree and replay failed runs.
Two Leading Tools
You can build tracing yourself, but two products do it well out of the box:
- Langfuse — OSS, self-hostable, framework-agnostic
- LangSmith — closed source, from the LangChain team
Plus Helicone, Phoenix, Weights & Biases for some workflows.
Langfuse Overview
Langfuse gives you:
- Trace tree view with timing
- Per-span inputs/outputs
- Cost and token rollups
- Dataset and eval support
- Prompt versioning
- OSS — run locally with Docker
All lessons in this course
- Why You Need Tracing for Agents
- Logging Tool Calls and Inputs/Outputs
- Latency and Cost per Step
- Visualising Agent Runs (Langfuse, LangSmith)