domains / families / software-engineering / langfuse

langfuse

authentic

Expert in Langfuse - the open-source LLM observability platform.

When to use

• Use when an application already needs Langfuse tracing, prompt management or evaluation, or when debugging missing/duplicated spans. Do not add an observability service merely because an LLM is present; start from the incident or product d…

When not to use

• SDK methods and integrations evolve; server version, Python SDK version and JS package versions are separate compatibility facts.
• Traces expose observable operations, not hidden chain-of-thought or proof of answer correctness.
• Masking one exporter does not sanitize every log or exporter in the application.
• Sampling, queue loss and shutdown behavior affect trace completeness; evaluate them explicitly.
• This skill does not create accounts, change production prompt labels, upload datasets or configure external telemetry without task authorization.

Skill page

Source