Course Outline
Day 1
Anatomy of a Modern AI Agent
Exploring agents as autonomous reasoning and acting systems, going beyond traditional chatbots.
Understanding reactive, proactive, hybrid, and goal-directed agent paradigms.
Identifying core components: perception, planning, memory, tool use, and action.
Evaluating design tradeoffs between single-agent and multi-agent structures.
Agent Frameworks and the Modern Stack
Analyzing LangChain, LlamaIndex, AutoGen, and CrewAI, along with their respective tradeoffs.
Comparing these with classical frameworks such as JADE and SPADE.
Selecting the appropriate framework based on specific production requirements.
Utilizing tool calling, function calling, and structured outputs.
Hands-on: Constructing a single Python agent with tool integration.
Multi-Agent System Architectures
Examining centralized, decentralized, hybrid, and layered MAS designs.
Understanding FIPA ACL, message-passing, and modern communication equivalents.
Implementing coordination patterns: planning, negotiation, and synchronization.
Observing 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.
Resolving conflicts and building trust among coordinating agents.
Day 2
Multi-Modal Foundations for Agents
Understanding 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.
Exploring 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
Processing images for agents: classification, captioning, and object detection.
Implementing speech recognition using Whisper ASR and streaming transcription.
Utilizing text-to-speech synthesis for 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.
Safely adding tool calls that produce real-world side effects.
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 why agentic AI is uniquely vulnerable compared to traditional software.
Mapping the attack surface: 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 standards.
Adversarial Attacks Hands-On
Exploring adversarial examples and perturbation methods: FGSM, PGD, DeepFool.
Analyzing white-box versus black-box attack scenarios.
Conducting model inversion and membership inference attacks.
Executing data poisoning and backdoor injection during training.
Performing prompt injection, jailbreaking, and tool misuse in LLM-based agents.
Defensive Techniques and Model Hardening
Implementing adversarial training and data augmentation strategies.
Using defensive distillation and other robustness techniques.
Applying input preprocessing, gradient masking, and regularization.
Utilizing differential privacy, noise injection, and 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 built 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
NIST AI Risk Management Framework: govern, map, measure, manage.
Understanding ISO/IEC 42001 and emerging AI-specific standards.
Mapping AI risks to existing enterprise GRC frameworks.
Meeting AI accountability, auditability, and documentation requirements.
Regulatory Compliance for Agentic Systems
Navigating the EU AI Act: risk tiers, prohibited uses, and obligations for high-risk systems.
Addressing GDPR and CCPA implications for agent data pipelines.
Implementing the U.S. Executive Order on Safe, Secure, and Trustworthy AI.
Adhering to 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.
Ensuring explainability and transparency as critical security properties.
Promoting fairness, preventing downstream harm, and ensuring responsible deployment.
Designing inclusive and auditable agent behavior.
Production Deployment, Monitoring, and Incident Response
Adopting 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.
Utilizing AI security incident response playbooks and recovery procedures.
Studying 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.
Exploring the forward outlook on emerging trends in agentic AI and AI security.
Summary and Next Steps
Requirements
Targeted Audience
AI engineers and architects developing agentic systems for production environments. Cybersecurity, risk, and compliance professionals managing 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
