“RAG”

Guardrails, evaluation and pre-production red teaming for AI agents, RAG apps and chatbots.

Toolkit for evaluating LLM applications with objective metrics, test data generation and feedback loops

AI observability and eval engineering platform where offline evals become production guardrails

Open-source Python library for evals, red teaming and test generation for agentic systems

IBM model family that judges whether LLM inputs and outputs meet criteria such as jailbreak, harm and hallucination checks.