Essentials

IriusRisk - Threat Modeling Agentic AI Essentials
(IR-TM2AI-E)

A fast, focused introduction to securing agentic AI. In 35 minutes, you’ll learn what an agent really is, where its key risks emerge, and how to model its critical components in IriusRisk. You’ll leave with a clear, practical blueprint for making agentic automation safe, auditable, and controlled—without the buzzwords or complexity.

  • Course duration

    ~ 45 minutes

  • Chapters

    4

  • Difficulty

    Advanced

  • Cost

    Free of charge

  • Certification

    Included

  • Badge

    Included

    Learning Objective

    •  • Understand what agentic AI is, how it differs from basic LLM usage, and why this shift introduces new security considerations.
    •  • Recognize the core layers and Trust Zones of an agentic architecture and represent them in a simplified DFD.
    •  • Identify the most critical agent-specific threats using IriusRisk.
    •  • Apply a minimal, high-impact set of controls for the Agentic AI component.
    •  • Use IriusRisk to quickly capture these components, threats, and controls to support early visibility and safe adoption of agentic AI.

    Target Audience

    • Security/AppSec & AI Security: architects, red/blue teams securing agentic systems.
    • ML/AI & MLOps: engineers building/operating agents, RAG, tooling.
    • DevOps & Cloud: integrating agent actions into production workflows.
    • Software/Systems Architects: designing high-impact, automated services.
    • Product & Eng Managers; GRC/Compliance: owning risk, controls, and auditability.

    Course Master

    Agentic AI marks a new frontier, systems that act, decide, and shape outcomes. Threat modeling is our compass, ensuring this power is guided with intent, not left to drift into unintended consequences.
    George Makrodimitris
    Head of Software Adoption / Course Master