Course Outline
Day 1
Anatomy of a Modern AI Agent
Beyond simple chatbots: understanding agents as autonomous systems for reasoning and action.
Exploration of reactive, proactive, hybrid, and goal-directed agent paradigms.
Core components: perception, planning, memory, tool utilization, and action execution.
Evaluating design tradeoffs between single-agent and multi-agent configurations.
Agent Frameworks and the Modern Stack
Analysis of LangChain, LlamaIndex, AutoGen, and CrewAI, including their respective advantages and limitations.
Comparison with classical frameworks such as JADE and SPADE.
Strategies for selecting a framework based on specific production requirements.
Understanding tool calling, function calling, and structured output mechanisms.
Hands-on: Scaffolding a single Python agent equipped with tool calls.
Multi-Agent System Architectures
Design patterns for centralized, decentralized, hybrid, and layered Multi-Agent Systems (MAS).
FIPA ACL, message-passing protocols, and their modern equivalents.
Coordination patterns: planning, negotiation, and synchronization techniques.
Understanding emergent behavior and self-organization within agent populations.
Decision-Making and Learning in Agents
Applying game theory to cooperative and competitive agent interactions.
Utilizing reinforcement learning within multi-agent environments.
Facilitating transfer learning and knowledge sharing across different agents.
Resolving conflicts and establishing trust between coordinating agents.
Day 2
Multi-Modal Foundations for Agents
Integrating multi-modal AI to create unified workflows across text, image, speech, and video.
Overview of leading multi-modal models: GPT-4 Vision, Gemini, Claude, and Whisper.
Fusion techniques for combining various modalities within an agent's reasoning loop.
Evaluating latency, cost, and accuracy tradeoffs 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 services.
Text-to-speech synthesis for natural voice interaction.
Connecting perception outputs to LLM-driven reasoning and tool selection processes.
Hands-On - Building a Multi-Modal Agent in Python
Defining the agent's task parameters, context window, and tool inventory.
End-to-end integration of GPT-4 Vision and Whisper APIs.
Implementing memory structures, state management, and conversation handling.
Safely adding tool calls that generate 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 within a simulated environment.
Logging agent reasoning, tool calls, and decisions for inspection and auditing purposes.
Day 3
Threat Surface of Production AI Agents
Analyzing the unique vulnerabilities of agentic AI 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 with traditional cybersecurity methodologies.
Adversarial Attacks Hands-On
Understanding adversarial examples and perturbation methods: FGSM, PGD, DeepFool.
Differentiating between white-box and black-box attack scenarios.
Exploring model inversion and membership inference attacks.
Addressing data poisoning and backdoor injection risks 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.
Utilizing defensive distillation and other robustness techniques.
Applying input preprocessing, gradient masking, and regularization methods.
Ensuring differential privacy through 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.
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
Navigating the 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 (Governance, Risk, Compliance) frameworks.
Addressing AI accountability, auditability, and documentation requirements.
Regulatory Compliance for Agentic Systems
EU AI Act: Understanding risk tiers, prohibited uses, and obligations for high-risk systems.
Implications of GDPR and CCPA for agent data pipelines.
Overview of the 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.
Recognizing explainability and transparency as critical security-relevant properties.
Ensuring fairness, preventing downstream harm, and promoting responsible deployment.
Designing inclusive and auditable agent behaviors.
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 logs, audit trails, and forensic readiness for agent actions.
Developing AI security incident response playbooks and recovery procedures.
Analyzing case studies of real-world AI breaches and extracting 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.
Discussing future trends in agentic AI and AI security.
Summary and Next Steps
Requirements
Targeted Audience
This course is designed for AI engineers and architects developing agentic systems for production environments. It also serves cybersecurity, risk, and compliance professionals tasked with ensuring AI assurance in regulated sectors such as finance, healthcare, and consulting. Additionally, senior developers and solution leads seeking to embed multi-modal and multi-agent capabilities into enterprise platforms will benefit from this training.
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
