Generative AI & Agentic AI

1 – Introduction to Generative AI

• What is Artificial Intelligence, Machine Learning, and Generative AI
• Evolution of AI technologies
• History of Generative AI (GANs to Large Language Models)
• Overview of AI-generated content (text, image, audio, video)
• Real-world applications across industries
• Ethical considerations and responsible AI

 

 2 – Applications of Generative AI

• AI in software development
• AI in business analysis and product management
• AI in marketing, customer service, and automation
• Use cases in healthcare, finance, and education
• Demonstration of AI-generated content

 

 3 – Generative Models Overview

• Discriminative vs Generative Models
• Overview of Generative Adversarial Networks (GANs)
• Variational Autoencoders (VAEs)
• Transformer models
• Key differences and practical use cases

 

 4 – Understanding Large Language Models (LLMs)

• What are Large Language Models
• GPT architecture basics
• Tokenization and embeddings
• How LLMs are trained
• Popular models: GPT, LLaMA, Claude, Gemini
• Limitations of LLMs (hallucinations, bias)

 

 5 – Prompt Engineering Basics

• What is a prompt
• Structure of an effective prompt
• Zero-shot prompting
• One-shot prompting
• Few-shot prompting
• Examples of good vs bad prompts

 

 

 

 6 – Advanced Prompt Engineering

• Role-based prompting
• Chain-of-thought prompting
• Prompt templates for analysis and coding
• Prompt optimization techniques
• AI prompting for business tasks

 

 7 – Hands-on with ChatGPT

• Getting started with ChatGPT
• Prompt templates for:
  • Coding
  • Summarization
  • Brainstorming
  • Documentation
• Productivity hacks using GPT
• Using AI for requirement documentation

 

 8 – Data Preparation for AI

• Importance of data in AI systems
• Data transformation concepts
• Data scaling and encoding
• Handling categorical data
• Date and time operations
• Data cleaning fundamentals

 

 9 – Exploratory Data Analysis (EDA)

• Understanding datasets
• Data merging and joining
• Grouping and aggregation
• Identifying trends and patterns
• Case study: Superstore Sales / IPL dataset

 

 10 – Statistics & Probability for AI

• Descriptive statistics
  • Mean
  • Median
  • Mode
  • Standard deviation
• Introduction to probability theory
• Probability distributions
  • Normal distribution
  • Binomial distribution
  • Poisson distribution

 

 11 – Data Visualization

• Importance of data visualization
• Matplotlib visualization techniques
  • Line chart
  • Bar chart
  • Pie chart
  • Scatter plot
  • Histogram
• Seaborn visualizations
  • Boxplot
  • Heatmap
  • Pairplot
• Visual storytelling with datasets

 

 12 – Introduction to AI Agents

• What are AI agents
• Components of an AI agent
  • Reasoning
  • Memory
  • Tools
• Difference between traditional automation and AI agents
• Examples of AI agents in business

 

 13 – Agentic AI Concepts

• What is Agentic AI
• Autonomous decision-making systems
• Multi-agent collaboration
• Agent orchestration
• Real-world examples of Agentic AI

 

 14 – Building AI Agents with CrewAI

• Overview of CrewAI framework
• Roles of agents in CrewAI
• Task orchestration
• Creating multi-agent workflows
• Example use case: research and reporting agent

 

 15 – No-Code AI Automation with n8n

• Introduction to n8n automation platform
• Workflow automation concepts
• Drag-and-drop automation pipelines
• Integrating APIs and AI services
• Building automated AI workflows

 

 16 – AI + RPA Integration using UiPath

• Overview of Robotic Process Automation
• AI integration with UiPath
• UiPath AI Center overview
• Automating document processing with AI
• Business automation use cases

 

 17 – Retrieval Augmented Generation (RAG)

• What is Retrieval Augmented Generation
• Why RAG is used in enterprise AI
• Knowledge base integration
• Vector databases and embeddings
• Building AI assistants using RAG

 

 18 – Fine-Tuning Concepts

• What is fine-tuning
• Difference between fine-tuning and prompt tuning
• When fine-tuning is required
• Introduction to model customization
• Fine-tuning use cases in enterprise AI

 

 19 – Cloud AI Platforms

• Overview of AI infrastructure
• AWS AI services

• • AWS Bedrock
  • Amazon SageMaker

• Google Cloud AI services

• • Vertex AI
  • Generative AI Studio

• Deploying AI models on cloud

 

 20 – Capstone Project: Building an Agentic AI Solution

• Designing an end-to-end AI solution
• Building an AI agent workflow
• Integrating LLMs with automation tools
• Implementing AI agents using CrewAI / n8n
• Demonstration and presentation of projects