How to jailbreak AI agents? | MLOps World GenAI Summit

Live session from MLOps World: How to red team AI agents. This session covers: → Why traditional security approaches fail with AI agents → Real jailbreak techniques that work on production systems (prompt injection, hallucination exploits, data exfiltration) → How to build automated red teaming into your AI security workflow → Post-testing: creating golden evaluation datasets to catch regressions Useful resources: - UI documentation: https://docs.giskard.ai/hub/ui/scan/index.html - SDK documentation: https://docs.giskard.ai/hub/sdk/scans.html - Free trial: https://www.giskard.ai/contact