Course curriculum

  • 1

    Module 1 : AI Agents - Introduction

    • Definition of AI Agents

    • Importance of AI Agents in Modern AI

    • Real-World Applications

    • How AI Agents Work

    • Types of Environments for AI Agents

    • Evolution of AI Agents
  • 2

    Module 2 : Agentic AI Paradigm

    • Introduction to the Agentic AI Paradigm

    • Key Characteristics of Agentic AI

    • Core Components of Agentic AI Systems

    • Comparison with Other AI Paradigms

    • Architectures and Frameworks in Agentic AI

    • Challenges in Developing Agentic AI Systems

    • Economic Impact
  • 3

    Module 3 : Agent Capabilities

    • Perception and Recognition Capability

    • Decision-Making and Problem Solving Capability

    • Learning and Adaptation Capability

    • Action and Interaction Capability

    • Multimodal Functionality in AI Agents

    • Tools and Frameworks for AI Agents

    • Data Processing Capabilities

    • Retrieval-Augmented Generation (RAGs)

    • Database Integration for AI Agents (Examples: Supabase, Firebase, MongoDB, and PostgreSQL)

    • Advanced Agent Capabilities (Adaptive and Self-Learning Agents, Collaboration in Multi-Agent Systems (MAS), Long-Term Memory and Context Awareness)
  • 4

    Module 4 : Automation and Workflow Optimization

    • Introduction to AI Automation and Workflow Optimization

    • Core Components of AI-Driven Workflow Optimization

    • Types of Workflows Optimized by AI Agents and use case applications

    • Automation Techniques Leveraged by AI Agents

    • Tools and Platforms for AI Workflow Automation (e.g., Zapier, UiPath, Blue Prism, n8n, Langgraph, pydantic)

    • Advanced Capabilities in AI Automation (Dynamic Task Scheduling and Context-Aware Automation, Proactive Agents, Adaptive Workflows)
  • 5

    Module 5: AI Strategy for Businesses

    • Identifying AI opportunities in your business

    • Frameworks for AI adoption in organizations

    • Aligning AI implementation with business goals

    • Overcoming common challenges in AI adoption
  • 6

    Module 6 : Frameworks

    • Introduction

    • HuggingFace

    • Ollama+DeepSeekV3

    • AutoGen

    • LangChain

    • CrewAI

    • LangGraph

    • Pydantic AI

    • AutoGPT

    • Comparison of frameworks
  • 7

    Module 7: Post Deployment

    • Monitoring, Evaluation, and Debugging

    • AgentBench

    • AgentOps

    • LangSmith

    • Langfuse

    • Logfire in Pydantic AI

    • Metrics

    • Monitoring Demo
  • 8

    Module 8: AI Governance & Risk Management

    • How to assess AI risks in business operations

    • Governance frameworks for responsible AI use

    • Strategies for mitigating AI risks
  • 9

    Module 9: Evaluating AI Agent Performance (Business Metrics)

    • How to measure the success of AI Agents in business settings

    • Key performance indicators (KPIs) for AI-driven automation

    • Understanding AI reliability, efficiency, and user experience

    • Case studies on AI performance evaluation
  • 10

    Module 10: AI Agents Security

    • Introduction to AI Agents Security

    • Vulnerabilities & Mitigation

    • Guardrails

    • Tools
  • 11

    Module 11: Future Trends in Agentic AI

    • Emerging technologies in AI Agents

    • The role of AI Agents in the future of work

    • Predictions for AI in the next 5–10 years

    • How businesses can stay ahead in the AI revolution
  • 12

    Module 12: Ethical Design of AI Agents

    • Ethical Design of AI Agents

    • Addressing Challenges
  • 13

    Module 13: Technology Stack

    • Technology Stack for Building Agentic AI Systems & Architecture
  • 14

    Module 14: Use Cases

    • Siemens AG

    • Mayo Clinic

    • JPMorgan Chase

    • Amazon

    • BP (British Petroleum)

    • Pearson

    • Netflix
  • 15

    Study Material

    • Study Material