This Generative AI, AI Agents & Agentic AI program is designed to help learners move from foundational concepts to practical implementation. The course covers Python essentials, Large Language Models, prompt engineering, retrieval-augmented generation, and the design of intelligent AI agents for real-world use cases.
Through hands-on labs and projects, participants will build GenAI applications, create agent-based workflows, explore multi-agent collaboration, and understand how to evaluate, guardrail, and deploy AI systems responsibly. The curriculum is structured to prepare learners for modern roles in Generative AI, AI automation, and Agentic AI development.
Ignite your future in Generative AI and Agentic AI with HAC. Enroll today and build the skills that power the next wave of intelligent applications.
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 such as RAG and MCP.
The focus is on developing practical, ethical, and scalable AI solutions using modern tools including
LangChain, LLaMA, Groq, Agno, and ChromaDB.
Understand the fundamentals of AI, Generative AI, and Agentic AI.
Learn the architecture and working principles of Large Language Models (LLMs).
Master transformers, tokenization, attention mechanisms, and prompt design.
Build prompt-engineered AI agents and structured agent workflows.
Create Retrieval-Augmented Generation (RAG) systems using embeddings and vector databases.
Develop full-stack RAG applications with FastAPI and Streamlit.
Design multi-agent systems using CrewAI and connected workflows with MCP.
Implement guardrails, evaluation strategies, and testing practices for AI systems.
Explore fine-tuning and local model deployment as an alternative to hosted LLM APIs.
Apply responsible and ethical AI practices in real-world projects.
Hurry up and join our Generative AI, AI Agents & Agentic AI course today
to propel your career to greater heights.
Show More
9 Weeks Schedule: GenAI Coverage
A comprehensive hands-on journey from Prompt Engineering and Python foundations to RAG systems, Multi-Agent AI, Claude Code, MCP, and LLM Fine-Tuning — Day 1 through Day 18.
9 weeks · 18 days · 125 topics · 65 hands-on labs
Day 1 – Saturday
Learn how to engineer prompts that reliably produce high-quality AI outputs. Understand the core differences between zero, one, and few-shot approaches.
Topics Covered
What is Prompt Engineering and why it matters
Zero-shot, one-shot, and few-shot prompting
System prompts vs user prompts
Role-based prompting and persona design
CRAFT and RISE frameworks
Bias detection and responsible prompting
Hands-On
Design prompts for 5 different business scenarios
Compare zero-shot vs few-shot on the same task
Build an AI Blog Generator using structured prompts
Day 2 – Sunday
Move from basic prompting to building persistent, customized AI tools without writing code. Learn how to package system instructions, specialized knowledge bases, and specific capabilities into custom GPTs or Google Gems that solve repeatab…
Topics Covered
Introduction to no-code AI customization
Anatomy of a Custom GPT and Google Gem
Writing effective system instructions for custom agents
Configuring knowledge retrieval (uploading enterprise files to custom models)
Actions and API integration basics for no-code environments
Business use cases for custom micro-agents
Hands-On
Build a custom GPT or Google Gem tailored to a business use case (e.g., a Customer Support Assistant or Technical Code Reviewer)
Upload a custom knowledge base document and test the agent's retrieval capabilities
Day 3 – Saturday
Explore how Chain-of-Thought prompting improves reasoning in complex, multi-step tasks. Understand the limits of model context windows and learn how to iteratively evaluate prompt performance to ensure reliable, structured outputs.
Topics Covered
Chain-of-Thought (CoT) and Tree-of-Thought prompting
Context window management, token budgets, and truncation strategies
Mitigating model hallucinations
Prompt evaluation and iteration techniques
Model benchmarking: Comparing ChatGPT, Gemini, Claude, and Mistral on complex reasoning tasks
Hands-On
Build a complex Chain-of-Thought prompt for a logical business problem
Conduct a multi-model evaluation exercise to analyze how different models handle identical instruction sets
Day 4 – Sunday
Understand what makes an autonomous AI agent fundamentally different from a simple conversational chatbot.
Topics Covered
What is an AI Agent? Agent vs chatbot vs autonomous workflow
The ReAct agent pattern: Reason + Act
Evolution of AI: Rule-based systems → ML → DL → Transformers → LLMs → Agents
Real-world applications of autonomous agent workflows across industries
Introduction to tool-calling and function execution concepts
Hands-On
Map out a complex business workflow into separate agent roles (e.g., Planner, Researcher, Writer)
Mock-test a manual ReAct loop using a standard LLM interface to simulate tool execution
Day 5 – Saturday
Set up a professional Python development environment from scratch. Learn the difference between IDEs, notebooks, and the terminal, and understand when to use each.
Topics Covered
What is an IDE? VS Code, PyCharm, Jupyter Notebook
Python installation and virtual environments
pip package manager and library ecosystem
Python basics: variables, data types, control flow
Functions, modules, and file I/O
What is a Python library vs framework vs module
Hands-On
Install VS Code and configure the Python extension
Create and activate a virtual environment
Write your first functional Python script
Day 6 – Sunday
Get hands-on with NumPy, the backbone of numerical computing in Python. Master Pandas, Python's most powerful data manipulation library, to load, inspect, filter, and aggregate real-world datasets—a critical prerequisite for feeding unstruc…
Topics Covered
Introduction to NumPy: arrays and operations
NumPy broadcasting and mathematical functions
Introduction to Pandas: Series and DataFrames
Data loading: CSV, Excel, JSON
Data exploration: head, info, describe, dtypes
Filtering, sorting, and grouping data
Handling missing values and data cleaning
Hands-On
NumPy array operations and mathematical functions exercise
Load, clean, filter, and aggregate a sales dataset using Pandas to answer analytical questions
Day 7 – Saturday
Understand how text is converted into numerical vectors (embeddings) that capture semantic meaning. Learn the difference between dense and sparse representations and why vector databases are essential for AI applications.
Topics Covered
What are embeddings? Word2Vec, GloVe, Sentence Transformers
Dense vs sparse vectors
Introduction to vector databases: Chroma, FAISS, Pinecone
Generate embeddings using OpenAI text-embedding-3-small
Set up ChromaDB locally
Store 50 documents and run similarity search
Metadata filtering exercise
Compare chunking strategies on a long document
Day 8 – Sunday
Understand why Retrieval Augmented Generation (RAG) was created and how it solves the hallucination and knowledge cutoff problems of LLMs. Study the complete RAG pipeline from document ingestion through retrieval to answer generation.
Topics Covered
Why RAG? Solving LLM hallucination and knowledge cutoff
Introduction to LlamaIndex as an alternative to LangChain
Hands-On
Build a basic RAG pipeline with Lang Chain + ChromaDB
Load a PDF and answer questions from it
Experiment with chunk size and overlap
Replicate the same pipeline with LlamaIndex
Day 9 – Saturday
Go beyond prompt engineering to context engineering: learn how to manage what information enters the LLM context window strategically. Understand token budgets, truncation strategies, and how to handle long conversation histories.
Topics Covered
What is Context Engineering? Beyond prompt engineering
Context window management: token budgets and truncation
Conversation history management in production
Building a FastAPI backend for a RAG application
REST API design: /query, /upload, /health endpoints
Session management and multi-turn conversation context
Error handling and logging in AI applications
Hands-On
Build a FastAPI backend with LangChain RAG pipeline
Create /upload endpoint to ingest documents
Build /query endpoint with context-aware responses
Test all endpoints with Postman or curl
Day 10 – Sunday
Build a clean, interactive chat UI using Streamlit. Learn to use Streamlit's chat elements, file uploader, and session state to create a responsive document Q&A interface.
Topics Covered
Introduction to Streamlit: building data apps fast
Streamlit components: text input, file upload, chat elements
Connecting Streamlit frontend to FastAPI backend
State management in Streamlit (st.session_state)
Deploying to Streamlit Cloud
Environment variables and secrets management
End-to-end testing of a full RAG application
Hands-On
Build a document Q&A chat interface in Streamlit
Connect frontend to FastAPI backend
Add file upload and conversation history
Deploy complete app to Streamlit Cloud
Day 11 – Saturday
Understand why naive RAG fails in production and learn the advanced techniques that address poor retrieval quality. Study BM25 sparse retrieval, hybrid search, and how combining dense and sparse approaches improves recall.
Topics Covered
Limitations of naive RAG: retrieval quality problems
BM25 sparse retrieval: TF-IDF principles
Hybrid search: combining dense + sparse retrieval
Reranking with Cohere Rerank and cross-encoders
Multi-query retrieval and query expansion
Parent-child document retrieval
Contextual compression and LLM-based extractors
Evaluation metrics: MRR, NDCG, Precision@K
Hands-On
Implement BM25 retrieval with rank_bm25
Build a hybrid search pipeline (BM25 + vector)
Add Cohere Reranker to your RAG pipeline
Compare naive vs advanced RAG retrieval quality
Day 12 – Sunday
Learn how knowledge graphs capture structured relationships between entities and how GraphRAG combines graph traversal with vector search for richer retrieval. Set up Neo4j and write basic Cypher queries.
Topics Covered
Introduction to Knowledge Graphs: nodes, edges, relationships
GraphRAG: combining knowledge graphs with vector retrieval
Neo4j basics and Cypher query language
Building a graph-based retriever with LangChain
CLI tool architecture using argparse and rich library
Combining Knowledge Graph + Vector Search in one CLI tool
Advanced RAG CLI: multi-strategy retrieval
Hands-On
Set up Neo4j and load sample knowledge graph data
Write Cypher queries to traverse the graph
Build a CLI RAG tool with argparse
Combine knowledge graph + vector search in one query pipeline
Day 13 – Saturday
Understand the architecture of multi-agent systems and why distributing work across specialized agents produces better results than a single generalist agent. Learn CrewAI's core concepts: Crew, Agent, Task, and Process.
Topics Covered
What are Multi-Agent Systems (MAS)?
Agent roles: Planner, Researcher, Writer, Critic
Agent communication and task delegation patterns
Introduction to CrewAI: Crew, Agent, Task, Process
Sequential vs hierarchical vs collaborative processes
Tool integration in CrewAI agents
LangGraph vs CrewAI: when to use which
Hands-On
Install CrewAI and configure API keys
Build a 3-agent research crew (Researcher, Analyst, Writer)
Add web search tool to your agents
Run a sequential content generation pipeline
Day 14 – Sunday
Build advanced CrewAI workflows with a manager agent that delegates tasks hierarchically. Add memory systems so agents retain knowledge across runs, and create custom tools that extend agent capabilities.
Topics Covered
Hierarchical process with manager agent
Memory systems in CrewAI: short-term, long-term, entity memory
Custom tool creation for CrewAI agents
Async agents and parallel task execution
Human-in-the-loop with CrewAI
Structured output schemas and output callbacks
Deploying a multi-agent pipeline with FastAPI
Hands-On
Build a full blog research-to-publish multi-agent system
Implement manager agent for task delegation
Add structured JSON output validation with Pydantic
Deploy a CrewAI pipeline with FastAPI
Day 15 – Saturday
Understand the Claude model family and how to use the Anthropic API with messages, system prompts, and tool use. Install and explore Claude Code, Anthropic's agentic coding tool.
Topics Covered
Claude model family: Haiku, Sonnet, Opus
Claude API: messages, system prompts, tools and tool use
What makes Claude different: Constitutional AI design
Introduction to Claude Code: agentic coding in the terminal
CLAUDE.md: defining project context and coding standards
Hooks in Claude Code: pre and post tool hooks
Skills in Claude: what they are and how to create custom skills
Context window management in Claude Code
Hands-On
Set up Claude API and make your first API call
Install Claude Code and explore commands
Write a CLAUDE.md for an existing project
Create a custom Skill for a repetitive code task
Use Claude Code to build a small utility autonomously
Day 16 – Sunday
Learn the Model Context Protocol (MCP), the open standard that lets Claude connect to external tools, databases, and services.
Topics Covered
What is MCP (Model Context Protocol)?
MCP architecture: Host, Client, Server
Built-in MCP servers: filesystem, browser, web search
Building a custom MCP server
Connecting Claude to external tools via MCP
Introduction to Harness Engineering
Designing automated test harnesses for AI code generation
Auto-correct loops: capturing test errors to prompt models for automatic self-healing
Safety and responsible use of Claude in production
Hands-On
Set up an MCP server with filesystem access
Connect Claude to a custom MCP tool
Build an automated Python test harness that executes code generated by Claude Code
Program an explicit auto-correct script that captures traceback errors and programmatically prompts Claude to patch its own code until all unit tests pass
Day 17 – Saturday
Learn why production AI systems need guardrails to prevent harmful outputs, PII leakage, and prompt injection attacks. Implement input and output validators using Guardrails AI and NeMo Guardrails.
Topics Covered
Why AI safety matters in production systems
Input and output guardrails: PII detection, toxicity filtering
Prompt injection attacks and defences
Introduction to Guardrails AI and NeMo Guardrails
Responsible AI principles: fairness, accountability, transparency
A/B testing LLM outputs and monitoring in production
Hands-On
Set up Guardrails AI with a custom validation schema
Detect and block PII in LLM outputs
Evaluate a RAG pipeline with RAGAS
Build an LLM evaluation dashboard with LangSmith
Day 18 – Sunday
Understand why organizations run models locally for privacy, cost reduction, and low latency. Install Ollama, download open-source models including Llama 3 and Mistral, and integrate them into your LangChain pipelines.
Topics Covered
Why run models locally? Privacy, cost, and latency
Introduction to Ollama: downloading and running local LLMs
Local model families: Llama 3, Mistral, Phi-3, Gemma
Knowledge distillation: teacher-student model concept
Fine-tuning LLMs: full fine-tune vs LoRA vs QLoRA
Preparing a fine-tuning dataset
Fine-tuning with Hugging Face PEFT + TRL and Unsloth
Evaluating a fine-tuned model vs base model
Hands-On
Download and run Llama 3 locally with Ollama
Integrate local model with LangChain
Prepare a custom fine-tuning dataset
Fine-tune a small model with QLoRA using Unsloth
Compare base vs fine-tuned model responses
Projects Covered in the 9-Week Batch
Foundations Mini-Project: Python and data-handling exercises to build the working muscle needed for the rest of the bootcamp.
Prompt-Engineered First Agent: A simple LLM-powered agent built using structured prompting techniques — the first hands-on encounter with agent design.
RAG-Based Q&A System: A retrieval-augmented generation pipeline using embeddings and a vector database to answer questions over custom documents.
Full-Stack RAG Application: A deployable RAG app with a FastAPI backend and Streamlit frontend, taking the earlier RAG pipeline to a usable product.
Advanced RAG CLI Tool: A command-line tool incorporating BM25 keyword search, reranking, and knowledge graphs for higher-quality retrieval.
Multi-Agent System (CrewAI): A team of collaborating AI agents built with CrewAI, each with a defined role, working together on a shared task.
Claude & MCP Build: A hands-on project using Claude Code, Skills, Hooks, and the Model Context Protocol to build a connected AI workflow.
Guardrails & Evaluation Project: An evaluation and safety layer added to an existing AI system, covering guardrails, LLM evaluation, and testing practices.
Fine-Tuning & Local Models Exercise: Hands-on work fine-tuning and running local open-source models as an alternative to hosted LLM APIs.
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.
Show More
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.
Nitesh is based in London and comes with strong hands-on expertise in Generative AI, AI automation, and data-driven analytics. He has trained many students globally on GenAI concepts, AI model development, and practical AI implementation using the latest AI tools and technologies. He has also successfully trained students from UK universities and learners across 30+ countries.
His core expertise includes AI-driven analytics and real-world AI projects involving NLP, LangChain, Large Language Models (LLMs), AI agents, and AI automation solutions that enhance reporting, intelligent decision-making, and enterprise business workflows.
With a practical, implementation-focused, and industry-oriented teaching approach, Nitesh is passionate about helping students build real-world AI skills aligned with current global market demand.
Bestseller
