Module 1: Introduction to Agentic AI
Evolution from rule-based AI to agentic systems
What is Agentic AI?
Key characteristics: autonomy, planning, reasoning, action
Agentic AI vs Chatbots vs RPA

Module 2: Core Components of an AI Agent
Goals and objectives

Perception and inputs
Reasoning and planning engines
Action and execution layers
Memory (short-term and long-term)

Module 3: Role of LLMs in Agentic AI
LLMs as reasoning engines
Prompting for agent behavior
System prompts vs task prompts
Managing context and state

Module 4: Agent Architectures & Patterns
Single-agent vs multi-agent systems
Reactive vs deliberative agents
Planner–Executor–Evaluator pattern
Tool-using and self-reflective agents

Module 5: Tools, APIs & Environment Interaction
Tool calling and function execution
API integration fundamentals
Browsing, code execution, and data access
Feedback loops and monitoring

Module 6: Memory, State & Learning
Stateless vs stateful agents
Vector databases and memory stores
Knowledge retrieval (RAG basics)
Agent improvement through feedback

Module 7: Use Cases & Applications
Business process automation
IT operations and DevOps agents
Data analysis and reporting agents
Customer support and virtual assistants

Module 8: Risks, Ethics & Governance
Hallucinations and error propagation
Prompt injection and security risks
Human-in-the-loop design
Responsible and compliant AI usage

Module 9: Evaluation & Performance
Measuring agent effectiveness
Reliability and cost considerations
Debugging agent behavior
Monitoring and logging strategies

Module 10: Hands-On Labs & Mini Project
Designing a basic AI agent
Creating goal-driven workflows
Agent testing and optimisation
Mini project or case study presentation.