Skip to Content

What does Langfuse add on top of your logger?

Category: Observability & Tracing

Answer

Langfuse captures every LLM call with its prompt, response, token usage, and latency, then maps parent/child relationships across LangGraph nodes. You can replay a real session, surface prompt regressions, and run evals against golden traces.

Concrete examples from the fca project context

Example 1

@observe() decorator wraps any function; Langfuse times it.

Example 2

CallbackHandler on ChatGroq/LangChain captures prompts + completions automatically.

Example 3

Tracing should be enabled in BOTH dev and prod, not just dev.

Data flow / flow chart

call -> Langfuse trace span (model, tokens, latency)
  Parent chain links LangGraph nodes

Takeaway

Always-on tracing is cheap insurance. Dev-only tracing doesn’t help when prod goes down.