Course Outline
Day 1
Anatomy of a Modern AI Agent
Exploring agents as autonomous reasoning and acting systems, beyond traditional chatbots.
Understanding reactive, proactive, hybrid, and goal-directed agent paradigms.
Examining core components: perception, planning, memory, tool use, and action.
Evaluating the tradeoffs between single-agent and multi-agent designs.
Agent Frameworks and the Modern Stack
Analyzing LangChain, LlamaIndex, AutoGen, and CrewAI, including their respective tradeoffs.
Comparing these with classical frameworks like JADE and SPADE.
Selecting the appropriate framework based on production requirements.
Understanding tool calling, function calling, and structured outputs.
Hands-on: Scaffolding a single Python agent with tool calls.
Multi-Agent System Architectures
Exploring centralized, decentralized, hybrid, and layered MAS designs.
Studying FIPA ACL, message-passing protocols, and their modern equivalents.
Identifying coordination patterns such as planning, negotiation, and synchronization.
Investigating emergent behavior and self-organization 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.
Addressing conflict resolution and trust mechanisms among coordinating agents.
Day 2
Multi-Modal Foundations for Agents
Viewing multi-modal AI as a unified workflow spanning text, image, speech, and video.
Reviewing leading multi-modal models: GPT-4 Vision, Gemini, Claude, and Whisper.
Applying fusion techniques to combine modalities within an agent's reasoning loop.
Balancing latency, cost, and accuracy tradeoffs in multi-modal pipelines.
Building the Perception Layer
Implementing image processing for agents, including classification, captioning, and object detection.
Utilizing Whisper ASR for speech recognition and streaming transcription.
Enabling text-to-speech synthesis and natural voice interaction.
Connecting perception outputs to 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.
Integrating GPT-4 Vision and Whisper APIs end-to-end.
Implementing memory, state management, and conversation handling.
Adding tool calls that produce real-world side effects safely.
Hands-On - Orchestrating a Multi-Agent System
Composing specialized agents using AutoGen or CrewAI.
Defining roles, responsibilities, and inter-agent communication protocols.
Managing resource allocation and coordination in a simulated environment.
Logging agent reasoning, tool calls, and decisions for inspection and audit.
Day 3
Threat Surface of Production AI Agents
Identifying what makes agentic AI uniquely vulnerable compared to traditional software.
Mapping the attack surface across data, model, prompt, tool, output, and interface layers.
Conducting threat modeling for agent-based systems with autonomous tool use.
Comparing AI cybersecurity practices to traditional cybersecurity methodologies.
Adversarial Attacks Hands-On
Executing adversarial examples and perturbation methods: FGSM, PGD, DeepFool.
Analyzing white-box versus black-box attack scenarios.
Performing model inversion and membership inference attacks.
Addressing data poisoning and backdoor injection during training.
Handling prompt injection, jailbreaking, and tool misuse in LLM-based agents.
Defensive Techniques and Model Hardening
Implementing adversarial training and data augmentation strategies.
Applying defensive distillation and other robustness techniques.
Utilizing input preprocessing, gradient masking, and regularization.
Ensuring differential privacy, noise injection, and managing privacy budgets.
Employing 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.
Applying defenses iteratively and re-evaluating attack success rates.
Stress-testing tool-call pathways and prompt injection vectors.
Day 4
Risk Management Frameworks for AI
Navigating the NIST AI Risk Management Framework: govern, map, measure, manage.
Reviewing ISO/IEC 42001 and emerging AI-specific standards.
Mapping AI risks to existing enterprise GRC frameworks.
Addressing AI accountability, auditability, and documentation requirements.
Regulatory Compliance for Agentic Systems
Understanding the EU AI Act: risk tiers, prohibited uses, and obligations for high-risk systems.
Assessing GDPR and CCPA implications for agent data pipelines.
Reviewing the U.S. Executive Order on Safe, Secure, and Trustworthy AI.
Applying 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.
Recognizing explainability and transparency as critical security-relevant properties.
Ensuring fairness, preventing downstream harm, and deploying responsibly.
Designing inclusive and auditable agent behavior.
Production Deployment, Monitoring, and Incident Response
Implementing secure deployment patterns for single and multi-agent systems.
Establishing continuous monitoring for drift, anomalies, and abuse.
Maintaining logging, audit trails, and forensic readiness for agent actions.
Developing AI security incident response playbooks and recovery strategies.
Analyzing case studies of real-world AI breaches and extracting lessons learned.
Capstone and Synthesis
Reviewing the multi-modal multi-agent system constructed throughout the course.
Conducting an end-to-end pipeline review: design, build, secure, govern, deploy.
Performing a self-assessment of the system against NIST AI RMF functions.
Exploring the forward outlook on emerging trends in agentic AI and AI security.
Summary and Next Steps
Requirements
Targeted Audience
AI engineers and architects responsible for developing agentic systems for production environments. Cybersecurity, risk management, and compliance professionals tasked with 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
