#evaluation
Connecteurs evaluation — déployez-en un et votre agent opère instantanément.
2 apps
#evaluation
2 apps
LangSmith (LLM Observability & Hub)
6 outilsMonitor LLM apps via LangSmith — track traces, audit prompt templates, and manage evaluation datasets.
LangSmith
3 outilsObservability and evaluation platform for LLM applications — monitor traces, debug agent runs, and track performance metrics across your AI stack.