Course Outline
Day 1
Anatomy of a Modern AI Agent
Beyond chatbots: understanding agents as autonomous reasoning and acting systems
Agent paradigms: reactive, proactive, hybrid, and goal-directed approaches
Core components: perception, planning, memory, tool utilisation, and action
Design trade-offs between single-agent and multi-agent systems
Agent Frameworks and the Modern Stack
Overview of LangChain, LlamaIndex, AutoGen, and CrewAI, including their respective trade-offs
Comparison with classical frameworks such as JADE and SPADE
Selecting the appropriate framework based on production requirements
Mechanisms for tool calling, function calling, and structured outputs
Hands-on: scaffolding a single Python agent equipped with tool calls
Multi-Agent System Architectures
Architectural designs: centralized, decentralized, hybrid, and layered Multi-Agent Systems (MAS)
FIPA ACL, message-passing protocols, and their modern equivalents
Coordination patterns: planning, negotiation, and synchronization
Emergent behaviour and self-organisation within agent populations
Decision-Making and Learning in Agents
Applying game theory to cooperative and competitive agent interactions
Implementing reinforcement learning in multi-agent environments
Facilitating transfer learning and knowledge sharing across agents
Establishing conflict resolution mechanisms and trust among coordinating agents
Day 2
Multi-Modal Foundations for Agents
Leveraging multi-modal AI as a unified workflow encompassing text, image, speech, and video
Leading multi-modal models: GPT-4 Vision, Gemini, Claude, and Whisper
Techniques for fusing modalities within an agent's reasoning loop
Balancing latency, cost, and accuracy in multi-modal pipelines
Building the Perception Layer
Image processing capabilities for agents: classification, captioning, and object detection
Speech recognition using Whisper ASR and streaming transcription
Text-to-speech synthesis enabling natural voice interaction
Integrating perception outputs with LLM-driven reasoning and tool selection
Hands-On - Building a Multi-Modal Agent in Python
Defining the agent's task, context window, and tool inventory
End-to-end integration of GPT-4 Vision and Whisper APIs
Implementing memory management, state handling, and conversation flow
Safely executing tool calls that produce real-world side effects
Hands-On - Orchestrating a Multi-Agent System
Composing specialised agents using AutoGen or CrewAI
Defining roles, responsibilities, and inter-agent communication protocols
Managing resource allocation and coordination in simulated environments
Logging agent reasoning, tool calls, and decisions for inspection and auditing
Day 3
Threat Surface of Production AI Agents
Understanding why agentic AI faces unique vulnerabilities compared to traditional software
Mapping the attack surface: data, model, prompt, tool, output, and interface layers
Conducting threat modelling for agent-based systems with autonomous tool use
Differentiating AI cybersecurity practices from traditional cybersecurity methods
Adversarial Attacks Hands-On
Exploring adversarial examples and perturbation methods: FGSM, PGD, DeepFool
Analyzing white-box versus black-box attack scenarios
Understanding model inversion and membership inference attacks
Addressing data poisoning and backdoor injection during training phases
Mitigating prompt injection, jailbreaking, and tool misuse in LLM-based agents
Defensive Techniques and Model Hardening
Implementing adversarial training and data augmentation strategies
Utilizing defensive distillation and other robustness techniques
Applying input preprocessing, gradient masking, and regularization
Incorporating differential privacy, noise injection, and managing privacy budgets
Enabling federated learning and secure aggregation for distributed training
Hands-On with the Adversarial Robustness Toolbox
Simulating attacks against the multi-modal agent constructed on Day 2
Measuring robustness under perturbation and quantifying performance degradation
Iteratively applying defenses and re-evaluating attack success rates
Stress-testing tool-call pathways and identifying prompt injection vectors
Day 4
Risk Management Frameworks for AI
NIST AI Risk Management Framework: govern, map, measure, and manage
Understanding ISO/IEC 42001 and emerging AI-specific standards
Aligning AI risks with existing enterprise GRC frameworks
Meeting AI accountability, auditability, and documentation requirements
Regulatory Compliance for Agentic Systems
EU AI Act: navigating risk tiers, prohibited uses, and obligations for high-risk systems
Implications of GDPR and CCPA on agent data pipelines
U.S. Executive Order on Safe, Secure, and Trustworthy AI
Sector-specific guidance for finance, healthcare, and public services
Managing third-party risk and supplier AI tool usage
Ethics, Bias, and Explainability
Detecting and mitigating bias across agent perception and reasoning processes
Positioning explainability and transparency as critical security-relevant properties
Ensuring fairness, preventing downstream harm, and promoting responsible deployment
Designing inclusive and auditable agent behaviours
Production Deployment, Monitoring, and Incident Response
Implementing secure deployment patterns for single and multi-agent systems
Establishing continuous monitoring for drift, anomalies, and potential abuse
Maintaining logging, audit trails, and forensic readiness for agent actions
Developing AI security incident response playbooks and recovery procedures
Examining case studies of real-world AI breaches and key lessons learned
Capstone and Synthesis
Reviewing the multi-modal multi-agent system developed throughout the course
Conducting an end-to-end pipeline review: design, build, secure, govern, deploy
Self-assessing the system against NIST AI RMF functions
Looking forward to emerging trends in agentic AI and AI security
Summary and Next Steps
Requirements
Targeted Audience
AI engineers and architects designing agentic systems for production environments. Cybersecurity, risk management, and compliance professionals tasked with ensuring AI assurance in regulated sectors such as finance, healthcare, and consulting. Senior developers and solution leads integrating multi-modal and multi-agent capabilities into enterprise platforms.
Testimonials (3)
The trainer is patient and very helpful. He knows the topic well.
CLIFFORD TABARES - Universal Leaf Philippines, Inc.
Course - Agentic AI for Business Automation: Use Cases & Integration
Good mixvof knowledge and practice
Ion Mironescu - Facultatea S.A.I.A.P.M.
Course - Agentic AI for Enterprise Applications
The mix of theory and practice and of high level and low level perspectives
