Browsing Tag
Langfuse
4 posts
LLM-as-judge in production: keeping the budget under control
LLM-as-judge in production: sample, target, calibrate the judge on human examples and monitor its cost to keep the evaluation budget under control.
Choosing an LLM in October 2026: operations criteria before benchmarks
Choosing an LLM in 2026 on operations criteria: latency, hosting, GDPR, OpenTelemetry observability and cost per task, tested with a real pilot.
AI agent cost: measuring tokens, tool calls and latency with OpenTelemetry GenAI
AI agent cost: measure tokens, tool calls and latency with OpenTelemetry gen_ai metrics, then track the budget on a dashboard with dedicated alerts.
Langfuse + OpenLLMetry: LLM observability and tracing for your LLM applications with OpenTelemetry
Trace your LLM applications with Langfuse + OpenLLMetry, then send the same OpenTelemetry spans to Langfuse and your backend through one Collector.