deep-eval

Mutant is a red team and behavioral data generation library for LLMs, RAG pipelines, and AI Agents. It provides two powerful capabilities

Veris: agent-agnostic local LLM evaluation and regression testing gate. Runs golden datasets against any callable, scores with DeepEval, compares rolling SQLite baselines, and returns CI-ready exit codes.

Many documents. Many formats. One place to ask.

🚦 Behavioral CI/CD for AI Agents. Stop shipping broken agents to production.roduction-grade evaluation gates and statistical testing for AI agents in any CI/CD pipeline.

Guia acessível do MASP com Qwen3 Next no AWS AgentCore e RAG. Projeto com 35 casos de Golden Dataset, 15 ataques de Red Teaming, avaliações no AgentCore e DeepEval, comparação baseline × final e análise de segurança, acessibilidade e qualidade das respostas.