LLM Observability and LLMOps: Tracing, Evals, Drift
An LLM observability and LLMOps architecture: OpenTelemetry GenAI traces, spans, online evals, and drift detection for production LLM and agent systems.
LLM Evaluation Pipelines: LLM-as-Judge Done Right (2026)
Build an LLM evaluation pipeline that you can trust — golden sets, LLM-as-judge pitfalls, calibration, drift detection, and a reference workflow.