Module 1: Introduction to Agentic AI

• What is Agentic AI vs traditional AI
• Agent vs workflow vs chatbot vs RAG
• When NOT to use agents
• Real-world use cases & industry impact

Module 2: How Agents Think & Act

• Autonomy & decision loops
• Planning → reasoning → acting → learning cycle
• Tools, memory, environment interaction
• Single-agent vs multi-agent systems

Module 3: LLMs as the Brain

• Prompting strategies for agent reasoning
• Function calling & tool usage
• Structured outputs

Module 4: Memory & Knowledge

• Short-term vs long-term memory
• Vector databases & embeddings
• RAG vs agent memory

Module 5: Building a Simple Task Agent

• Travel planner agent
• Meeting scheduler agent

Module 6: Agents with Tools & APIs

• Web search & retrieval tools
• Database interaction
• Automation workflows

Module 7: Planning & Multi-Step Execution

• Task decomposition
• Chain-of-thought & planning
• Error handling & retries

Module 8: Multi-Agent Collaboration

• Role-based agents
• Planner–Executor pattern
• Supervisor agent architecture

Module 9: Agent Frameworks Overview

• CrewAI
• LangGraph / LangChain agents
• Microsoft AutoGen
• SmolAgents

Module 10: Visual Automation & Orchestration

• n8n / workflow tools
• MCP & tool integration
• Event-driven agents

Module 11: Scaling Agent Systems

• Cloud deployment patterns
• Observability & logging
• Cost & performance optimization

Module 12: Safety, Guardrails & Reliability

• Prompt injection risks
• Tool misuse prevention
• Human-in-the-loop systems
• Compliance & governance