In this product update we introduce LLM observability, prompt management, and a new interface to configure LLM-as-a-judge evaluators.

Agenta introduces open-source LLM observability and LLM monitoring for LLM applications. It allows you to trace inputs, outputs, and meta-data with two-lines of code. It is OpenTelemetry compliant and comes with many integrations out of the box (OpenAI, LiteLLM, LangChain, Instructor and more).