Last year, AI agents were everywhere—and I was skeptical. Today, I'm building them into my security workflow. This talk shares that journey, along with hard-won lessons on what works, what doesn't, and what you should never automate.

You'll walk away with actionable guidance on creating your first AI Cyber Agent, understanding where these tools genuinely add value versus where they introduce risk. We’ll explore how to design agents that act as force multipliers for individual analysts, streamlining everything from log analysis to reporting. We'll cover practical use cases, common mistakes to avoid, and the ethical and operational boundaries every security professional should respect when deploying autonomous systems.