SABSA TRAINING CONSULTING
Skip to content

Agentic Security Architecture Masterclass

  • Duration

    1 Day

  • Delivery Mode

    Virtual

Overview

This one day masterclass provides an intensive deep dive into the architectural and engineering concepts around Agentic AI. The course provides a refresher on AI security and the AI Security Services Reference Architecture, and then describes the evolution of LLMs to the current state of understanding of AI agents.

The course studies the risks of Agentic AI, both threat and opportunity driven, and derives the controls and enablers necessary to maintain agentic activity within risk appetite. It covers the governance for agentic AI in the form of an enhanced ISO42001 AI management system, with a delegation approach which takes autonomous agents into account. Agentic identity is discussed together with architecting agentic access and privileges. The course covers the Hindsight approach to agentic memory engineering and presents a series of agentic AI design patterns. It concludes by reviewing the evolving protocols for addressing agents across the internet.

Course
Outline

Refresher on AI Security Architecture

  • AI technology refresher
  • AI Guardrails
  • AI Security Services Reference Architecture (ASSRA)

AI Evolution to Agentic

  • Fake Agents
  • AI Agents are not human
  • The Five Real Agent Components
  • Agentic AI Frameworks
  • The Case for Agentic Senses
  • Practical Session (Deep Agents)

Agentic AI Threats

  • Refresher OWASP Top Ten LLM Threats and MITRE ATLAS
  • OWASP Top Ten Agentic Threats
  • Agentic Control and Enabler Objectives

Agentic AI Governance

  • Agentic AI Security Management
  • Security Policy for Agentic AI
  • From Semantic Convention to SABSA Layered Architecture
  • Agentic Delegation of Authority
  • Rewiring the enterprise for Agentic AI
  • Workshop

Agentic Identity

  • From Service Account to Portable AgentId
  • Delegated authorisation and transitive trust
  • Agentic IAM
  • FAPI profiles

Agentic Design Patterns

  • Agentic Design Patterns
  • Self Adaptive Goal Oriented Execution
  • Practical Session (SAGE)

Architecting Memory

  • Understanding Agentic memory
  • Memory Subsystem Engineering
  • Practical Session (Hindsight)

Monitoring Agentic AI

  • Observability Subsystem
  • Logging and Agentic Ledgers
  • Enhanced Guardrails

Architecting the AgentWeb

  • Agentic Protocols (ANS,A2A, A2AS)
  • AgentDNS and Discovery
  • Adaptive Routing
  • AgentFacts and Capability Cards
  • Autonomy Passport

What's Included

Virtual

  • 1-day virtual classroom training
  • Soft-copy training & workshop materials
  • Attendance Certificate

Agentic Security Architecture Masterclass Dates

June

18jun8:30 am4:30 pmMasterclass: Agentic Security ArchitectureVirtual: North/South America

25jun8:30 am4:30 pmMasterclass: Agentic Security ArchitectureVirtual: UK/Europe/Africa

See full schedule


Course Enquiry

This field is for validation purposes and should be left unchanged.

LEARN SABSA
from the
source.

Knowledge transfer from a team of SABSA® authors & contributors, with multiple SABSA® Practitioner or Masters Certifications.

Meet the Team

Insights &
Resources

Architecting Secure & Responsible AI Webinar: Why Architect AI? – 4 June 2026

In this webinar, we explore the reasons why architecting our AI solutions using SABSA is the key to business success in adopting AI as a fit-for-purpose capability for the enterprise.


Responsible AI Reference Architecture

To be effective, the deployment of AI in enterprises needs to be carried out in a responsible manner, ensuring safety for users and the business, and security of the models and datasets. An AI Reference Architecture can identify and categorise the services required for a safe and secure environment for AI.

Learn more - Responsible AI Reference Architecture

More Resources