Red Team any AI agent, whatever its API | Giskard Hub v.3.0

If your agent takes a list of dictionaries, returns a structured verdict, or isn't a chatbot at all, Giskard Hub v3 can red team it. 🎯 What's new: - Any API format — Configure your agent's real request and response schema. - Any input shape — A single string, a list of strings, a dictionary, a list of dictionaries. You define how conversation history is assembled. - Any output shape — Point the Hub at whatever field your endpoint actually returns. - Beyond conversational agents — Fraud detection classifiers, email generators, extraction pipelines. If it's an agentic system, it's testable. - Same testing suite, unchanged — Red teaming scans, evaluations, and continuous testing all run on top of your custom schema. 📖 Documentation: https://docs.giskard.ai/hub/ui 🚀 Request a demo: https://www.giskard.ai/contact #AIsecurity #RedTeaming #LLMEvaluation #AIagents