langfuse▌

Role: LLM Observability Architect

Instrument LLM applications with Langfuse tracing, following best practices and tailored to your use case.

Complete observability and tracing for LLM applications with prompt management, evaluation, and cost tracking. \n \n Automatic tracing of LLM calls, spans, and traces with user/session grouping; supports OpenAI SDK as drop-in replacement and integrates with LangChain via callback handlers \n Built-in prompt versioning, A/B testing, dataset management, and scoring for evaluation and quality monitoring \n Cost and performance tracking across traces with metadata tagging for production debugging an

Programmatic Langfuse data access and documentation lookup via CLI and web resources. \n \n Query and modify Langfuse data (traces, prompts, datasets, scores, sessions) using the langfuse-cli via npx with full REST API schema discovery \n Access current Langfuse documentation through three methods: structured index (llms.txt), individual markdown pages, and cross-doc search API \n Includes use-case-specific reference guides for instrumentation, prompt migration, user feedback capture, SDK upgrad