Automating AI agents security and evaluation at enterprise scale
May 20, 2026 — 08:30 am - 09:00 am
AI Startup Summit - Stage 2
Already registered? Log in now to personalize your experience!
Description
Discover how to secure production AI agents with automated continuous red teaming. This masterclass covers detecting vulnerabilities (hallucinations, data leaks), grounding evaluations via Knowledge Bases, and using multi-turn attacks simulations.
Giskard provides a security layer for AI, automating LLM vulnerability testing during development and after deployment. It enables enterprises to build and run robust, secure GenAI systems, trusted...
