A practical guide to RAG evaluation, evaluation metrics, RAGAS, and LLM evaluation. Learn how to measure and improve your RAG systems.

It's Official: Agenta Is Now SOC2 Type 2 Compliant

Enforce JSON and schema-validated responses straight from the Agenta playground.

Today we're launching the Prompt & Configuration Registry. It's a place to manage all your LLM prompts and configurations.

Agenta helps teams build better LLM applications. Today, we're releasing Custom Workflows - a way to connect your entire application to Agenta's playground and evaluation tools.

Agenta helps you build LLM applications with our playground for prompt engineering and evaluation tools. Now, we're making it possible to use virtually any model you have access to, no matter where it's hosted.

We're excited to share that our first-ever Launch Week is happening next week, April 15-19!

For teams building production-grade LLM applications, a systematic approach to prompt management is no longer optional—it's essential infrastructure. Here's why it matters and how to get it right.

Streamling your prompt engineering with Playground 2.0. An integrated LLM playground for testing and comparing prompts and models.

Explore why prompt management is crucial for scaling AI applications from pilots to production.

Agenta secures SOC2 Type 1 certification, ensuring your LLM development data stays protected with enterprise-level security. Build your AI applications with confidence.

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).