Agent: Claude Code, CursorLLM: Claude, GPT-4#llm-evaluation#prompt-engineering#red-teaming#testing#ai-developer-tools
Promptfoo is a CLI and library for evaluating and red-teaming LLM applications. It enables developers to test prompts, compare model performance across GPT, Claude, Gemini, and others, and identify vulnerabilities through automated red teaming. Used by OpenAI and Anthropic, it provides simple declarative configs with command-line and CI/CD integration for secure, reliable AI app development.