Hands-On Agile Coaching | Azure Data Engineer With Microsoft Fabric & Data Analytics

Course Overview

The Generative AI Program is designed to cover essential areas, including mastering Python, LLMs, RAG and Agentic AI. Participants will gain expertise in implementing and creating GenAI based applications, with deploying applications in Azure, and ensuring robust data security.

This curriculum provides a comprehensive and hands-on understanding of Generative AI, AI agents and Agentic AI applications, upskilling and preparing you to become a proficient Generative AI Engineer.

Ignite your Generative AI career with HAC. Enroll today and embark on a transformative learning journey!

Course Objectives

This course aims to equip learners with a strong foundation and hands-on expertise in Generative AI, Large Language Models, and Agentic AI. Participants will explore the inner workings of LLMs, master prompt engineering, build intelligent AI agents, and implement advanced pipelines like RAG and MCP. The focus is on developing practical, ethical, and scalable AI solutions using modern tools such as LangChain, LLaMA, Groq, Agno, and Chromadb.

Get a deep dive into essential subjects like Azure Cosmo DB, Azure Synapse, Azure Databricks, Azure Stream Analytics, Azure HDInsight, and Azure Data Factory.
Understand the fundamentals and evolution of AI & Generative AI.
Learn the architecture and working of Large Language Models (LLMs).
Master transformers, tokenization, and attention mechanisms.
Design effective prompts and optimize prompt performance.
Build LangChain-based AI workflows and pipelines.
Work with vector databases and similarity search using Chromadb.
Implement Retrieval-Augmented Generation (RAG) systems.
Develop intelligent single and multi-agent systems using Agentic AI.
Fine-tune and evaluate AI models with LoRA and Agno frameworks.
Apply responsible and ethical AI practices in real-world projects.

Hurry up and join our Microsoft Azure Data Engineer Certification Course today to propel your career to greater heights.

Key Topics Covered :

Module 1: Python for AI/ML
Python Programming
- Variables & Data Types
- Operators
- Data Structures
- Functions
- Conditional Flow statements
- Lambda, Map, Filter & Reduce functions
- Types of Errors & Error Handling
Python modules for AI
- Mathematical Computing using NumPy
- creating 1d, 2d and 3d arrays
- Accessing Array Elements
- Indexing, Slicing, Iteration
- Data Analysis using Pandas
- Understanding Pandas
- Series & DataFrames
- DataFrame Operations
- Handling Missing data
- Filtering, Grouping and Joining
- Loading Data from Datasets to DataFrames
- Data Visualization using Matplotlib & Seaborn
- Different types of Plots & Charts
Module 2: Statistics & EDA
- Descriptive Statistics & Inferential Statistics
- Data & Variables in Statistics
- Measures of Central Tendency (Mean, Median & Mode)
- Variance & Standard Deviation
- Univariate Analysis (Histograms, Box plots & Bar charts)
- Bivariate/Multivariate Analysis (Line plots, Scatter plots, Heat maps)
- Probability Distribution & Central Limit Theorem
- Normal distribution & Standard Normal distribution
- Outlier detection
- Confidence Intervals & Hypothesis Testing
- Correlation & Regression.
Capstone Projects:
- Food Hub Aggregator EDA
- Retail Data Insights
Module 3: AI & Generative AI Fundamentals
- Introduction to AI
- Introduction to Generative AI
- Generative AI Evolution
- Traditional AI vs Generative AI
- Types of GenAI models
- GenAI vs AI agents vs Agentic AI
- Real-world applications of Gen AI
- Popular GenAI tools
- Large language models (LLMs)
- Vector database
- RAG
Module 4: LLMs and Transformers
- Introduction to LLMs
- LLMs in the AI landscape
- What can a Language Model do
- Traditional models vs LLM
- Popular LLMs: GPT, BERT, Claude, LLaMA
- LLMs Architecture: Transformers
- Encoder & Decoder
- Tokenization
- Vector Embeddings
- Positional Encoding
- Self-Attention
- Working with ChatGPT, Copilot, Hugging Face LLMs
Module 5: Prompt Engineering
- Introduction to Prompt Engineering
- Types of prompts
- Few-shot and zero-shot prompts
- Chain-of-thought prompts
- Designing effective prompts: CRAFT framework
- Evaluating prompt performance and bias
- Prompt optimization tools and techniques
- Hands-on: zero-shot, one-shot, and few-shot prompts
Module 6: LangChain
- Introduction to Langchain
- Langchain ecosystem
- Langchain installation/setup
- LLMs using Langchain
- Prompt Templates and Chains
- Output Parser
- Hands-on Langchain scenarios
Module 7: Vector Database
- Introduction to Vector databases
- Traditional databases vs Vector databases
- in data storage and retrieval
- and similarity search
- High dimensional vector space
- Chromadb vector database
- Working with Chromadb
- Chromadb operations
- Distance metrics: cosine similarity, dot product, Euclidean
- Add, update, delete, query operations
- Metadata filtering
Module 8: Retrieval Augmented Generation (RAG)
- How RAG works
- RAG vs traditional LLM generation
- Two-phase Architecture: Retrieval + Generation
- Document loaders
- Text splitters
- Retrieval & Answer generation
- Streamlit UI
- Use of Embedding models
- Building a RAG based pipeline
Module 9: AI Agents & Agentic AI
- Introduction to AI agents
- Single-agent vs multi-agent systems
- Introduction to Agentic AI
- How Agentic AI works
- AI Agents vs Agentic AI
- Real-world applications
- Building your first Agent using Llama & Agno
- Reasoning models
- Building reasoning model using Agno
- Multi-modal Agents (text, image, video)
- Frameworks: Google ADK, Smol agents
- Multi-Agent systems & design patterns
- Building Multi-Agent systems
- Route agent
Module 10: Model Context Protocol (MCP)
- Introduction to MCP
- Prebuilt MCP Servers
- A2A Protocol
- Build your first MCP Server
Module 11: Agentic AI – Evaluation & Fine-Tuning
- Introduction to Agentic AI Evaluation
- Functional Evaluation using Agno
- Safety and Guardrails
- Operational Metrics
- Performance evaluation using Agno
- Fine-Tuning basics
- Low Rank Adaptation (LoRA)
- Quantization (QLoRA)
- Fine tuning Llama with Unsloth
Module 12: AI Workflows using N8N
- Build AI Chat Agent
- Content Creation with N8N AI Agent
- Marketing Automation with N8N
Module 13: Multi-Agents with Crew AI
- Introduction to Crew AI
- Building Hierarchical Agent structures
- Building Multi-Agent systems
Module 14: Generative AI on Azure Cloud
- Building Gen AI models using Azure OpenAI
- Building Chat applications using OpenAI GPT models
- Building images using DALL·E model

Hands-On Labs & Agentic Scenarios

Building Custom GPTs using ChatGPT
Creating & working with SQL Data Analyst GPT
Creating Resume Improver GPT
AI Email Generator
AI Blog Generator with OpenAI SDK
Text Summarizer with Copilot
AI Language Translator
Code Explainer [with ChatGPT & Copilot]
Spam Detection with Hugging Face
Context window, Temperature
LLM Hallucinations
Langchain installation
Groq and Ollama setup
Prompting with Langchain
Calling LLMs from Langchain
Prompt Templates and Chains
Output Parser
Chromadb installation/set up
Chromadb operations
Add, Update, Delete and Query
working with Metadata Filtering
Building your first agent with LLama & Agno
Building Reasoning Agents with Agno
Multimodal Agents
Building MCP Server
Building Multi-Agent system
LLM evaluation and fine-tuning

Capstone Real-time Projects

Project-1: Creating SQL Data Analysis Custom GPT using ChatGPT
Project-2: Training Deck using NotebookLM and Gamma AI
Project-3: Property buying decision using ChatGPT, Gemini, Preplexity
Project-4: Real Estate RAG Agent
Project-5: E-Commerce RAG
Project-6: AI chatbot using N8N
Project-7: Invoice automation using N8N
Project-8: Multi-Agentic system
Project-9: Chat Agent with Azure OpenAI
Projetc-10: AI agent with Microsoft Phi SLM
Project-11: Design Website Landing Page using Lovable AI
Project-12: Project Tracker Automation with Notion & Zapier
Project-13: Retail Data Insights using Pandas & Matplotlib
Project-14: Uber Eats EDA using Pandas, Statistics & Seaborn

Bonuses

GenAI & Agentic AI Interview questions & answers
Real-time scenarios and solutions
AWS certified Generative AI Developer certification support
Resume/CV preparation
Building Project Portfolio
LinkedIn profile optimization
Placement Assistance
On-Job Support

Target Jobs

Generative AI Engineer/Developer
Agentic AI Specialist/Consultant
AI Engineer
LLM Engineer
Prompt Engineer
AI Automation Engineer/Consultant

Program Outcome

Transition your career to GenAI & Agentic AI roles.
Land high-paying AI and GenAI jobs globally.
Up to ~300X times increment in your current salary.
Switch to Top IT & Product based companies.
Have a secured career and work in a Future trend job.
Become a top & highly paid IT professional.

FAQ

A:The HAC program is a comprehensive, practical training course designed to help learners master Generative AI, Large Language Models (LLMs), and Agentic AI through real-world, hands-on projects using tools like LangChain, LLaMA, Agno, Groq, and Chromadb.

A: This course is ideal for students, developers, data scientists, AI enthusiasts, and professionals who want to gain in-depth practical skills in Generative AI, LLMs, and Agentic AI applications.

A: Basic programming knowledge (preferably in Python) is recommended, but the course is structured to guide learners from foundational AI concepts to advanced implementations step by step.

A: Unlike theoretical programs, HAC is hands-on and project-driven. Learners build real AI systems such as RAG pipelines, multi-agent architectures, and LangChain-based applications using modern frameworks and tools.

A: You’ll work with OpenAI APIs, Hugging Face, LangChain, LLaMA, Groq, Agno, and Chromadb, along with frameworks for transformers, vector databases, and prompt optimization.

A: By the end, participants will be able to design, develop, and deploy Generative AI models, AI agents, and multi-agent systems, and understand how to fine-tune, evaluate, and scale them ethically.

A:Learners will build prompt-based AI models, LangChain-powered chatbots, RAG pipelines, vector database search systems, and Agentic AI applications using LLaMA and Agno frameworks.

A: The course is divided into 12 modules, starting with AI fundamentals and progressing to advanced topics like transformers, prompt engineering, RAG systems, multi-agent systems, and ethics in GenAI.

A: Yes. Participants who complete all modules and projects successfully will receive a certificate of completion, validating their expertise in Generative AI and Agentic AI technologies.

A:Graduates will gain in-demand skills to pursue roles such as AI Engineer, Prompt Engineer, LLM Developer, Data Scientist, or AI Researcher, and will be equipped to contribute to real-world AI innovation and enterprise projects.