課程簡介
Day 1
Anatomy of a Modern AI Agent
Beyond chatbots, agents as autonomous reasoning and acting systems
Reactive, proactive, hybrid, and goal-directed agent paradigms
Core components: perception, planning, memory, tool use, action
Single-agent versus multi-agent design tradeoffs
Agent Frameworks and the Modern Stack
LangChain, LlamaIndex, AutoGen, CrewAI and their tradeoffs
Comparison with classical frameworks such as JADE and SPADE
Choosing a framework based on production requirements
Tool calling, function calling, and structured outputs
Hands-on: scaffolding a single Python agent with tool calls
Multi-Agent System Architectures
Centralized, decentralized, hybrid, and layered MAS designs
FIPA ACL, message-passing, and modern equivalents
Coordination patterns: planning, negotiation, synchronization
Emergent behavior and self-organization in agent populations
Decision-Making and Learning in Agents
Game theory for cooperative and competitive agent interactions
Reinforcement learning in multi-agent environments
Transfer learning and knowledge sharing across agents
Conflict resolution and trust between coordinating agents
Day 2
Multi-Modal Foundations for Agents
Multi-modal AI as a unified workflow across text, image, speech, and video
Leading multi-modal models: GPT-4 Vision, Gemini, Claude, Whisper
Fusion techniques for combining modalities inside an agent's reasoning loop
Latency, cost, and accuracy tradeoffs in multi-modal pipelines
Building the Perception Layer
Image processing for agents: classification, captioning, object detection
Speech recognition with Whisper ASR and streaming transcription
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
Wiring up GPT-4 Vision and Whisper APIs end-to-end
Implementing memory, state, and conversation management
Adding tool calls that produce real-world side effects safely
Hands-On - Orchestrating a Multi-Agent System
Composing specialized agents with AutoGen or CrewAI
Defining roles, responsibilities, and inter-agent communication protocols
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
What makes agentic AI uniquely vulnerable compared to traditional software
Attack surface: data, model, prompt, tool, output, and interface layers
Threat modeling for agent-based systems with autonomous tool use
Comparing AI cybersecurity practices to traditional cybersecurity
Adversarial Attacks Hands-On
Adversarial examples and perturbation methods: FGSM, PGD, DeepFool
White-box versus black-box attack scenarios
Model inversion and membership inference attacks
Data poisoning and backdoor injection during training
Prompt injection, jailbreaking, and tool misuse in LLM-based agents
Defensive Techniques and Model Hardening
Adversarial training and data augmentation strategies
Defensive distillation and other robustness techniques
Input preprocessing, gradient masking, and regularization
Differential privacy, noise injection, and privacy budgets
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 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
ISO/IEC 42001 and emerging AI-specific standards
Mapping AI risk to existing enterprise GRC frameworks
AI accountability, auditability, and documentation requirements
Regulatory Compliance for Agentic Systems
EU AI Act: risk tiers, prohibited uses, and obligations for high-risk systems
GDPR and CCPA implications for agent data pipelines
U.S. Executive Order on Safe, Secure, and Trustworthy AI
Sector-specific guidance for finance, healthcare, and public services
Third-party risk and supplier AI tool usage
Ethics, Bias, and Explainability
Bias detection and mitigation across agent perception and reasoning
Explainability and transparency as security-relevant properties
Fairness, downstream harm, and responsible deployment
Designing inclusive, auditable agent behavior
Production Deployment, Monitoring, and Incident Response
Secure deployment patterns for single and multi-agent systems
Continuous monitoring for drift, anomalies, and abuse
Logging, audit trails, and forensic readiness for agent actions
AI security incident response playbooks and recovery
Case studies of real-world AI breaches and lessons learned
Capstone and Synthesis
Reviewing the multi-modal multi-agent system built across the course
End-to-end pipeline review: design, build, secure, govern, deploy
Self-assessment of the system against NIST AI RMF functions
Forward outlook on emerging trends in agentic AI and AI security
Summary and Next Steps
最低要求
Targeted Audience
AI engineers and architects building agentic systems for production use. Cybersecurity, risk, and compliance professionals responsible for AI assurance in regulated industries such as finance, healthcare, and consulting. Senior developers and solution leads embedding multi-modal and multi-agent capabilities into enterprise platforms.
客戶評論 (3)
培訓師很有耐心，也非常樂於助人。他對主題非常瞭解。
CLIFFORD TABARES - Universal Leaf Philippines, Inc.
課程 - Agentic AI for Business Automation: Use Cases & Integration
機器翻譯
知識與實踐的良好結合
Ion Mironescu - Facultatea S.A.I.A.P.M.
課程 - Agentic AI for Enterprise Applications
機器翻譯
理論與實踐的結合，以及高層與底層視角的融合
Ion Mironescu - Facultatea S.A.I.A.P.M.
課程 - Autonomous Decision-Making with Agentic AI
機器翻譯
