Eval tools
Braintrust, Langfuse, Promptfoo, Ragas, DeepEval, Vellum, Inspect AI — running eval suites in dev and CI.
Observability tools
Langfuse, LangSmith, Helicone, Arize Phoenix, Braintrust — logging, tracing, cost tracking for every LLM call.
Evals & observability
How you measure and monitor LLM systems in development and production.