About Course

About Course

The AI Agents & Agentic AI with Python program is a practical, industry-oriented training program designed to help learners build intelligent AI applications, AI agents, RAG systems, agentic workflows and multi-agent solutions using Python.

The program starts with Core Python Programming and API Fundamentals, providing the programming foundation required to work with modern AI technologies. Learners then progress through Generative AI, LLM APIs, Prompt Engineering, RAG, AI Agents, Tool Calling, LangChain, LangGraph, Multi-Agent Systems and Model Context Protocol (MCP).

The program focuses strongly on hands-on development and real-world implementation. Learners will build multiple AI-powered applications and progressively develop complete Agentic AI solutions.

The program is designed for developers and technology professionals who want to move into AI Engineering, Generative AI Development and Agentic AI Development.

Who Should Enroll

• Fresh Graduates with basic programming knowledge

• Python Developers

• Software Developers

• Full Stack Developers

• Automation / Test Engineers with programming experience

• Web Developers

• IT Professionals transitioning into AI

• Developers interested in Generative AI and AI Agents

• Students pursuing careers in AI Engineering

• Professionals looking to upgrade their software development skills with AI

No prior experience in Generative AI, Machine Learning, RAG, LangChain, LangGraph or AI Agents is required.

MODULE 1 – CORE PYTHON PROGRAMMING

Topics Covered

Introduction to Python

• Introduction to Python

• Python Installation & Environment Setup

• Python IDEs and Development Environment

• Variables and Data Types

• Operators

• Input and Output

• Type Conversion

• Writing and Executing Python Programs

Python Data Structures

• Strings

• Lists

• Tuples

• Sets

• Dictionaries

• Data manipulation techniques

• Nested data structures

Control Flow & Problem Solving

• Conditional Statements

• for Loops

• while Loops

• break and continue

• Nested Loops

• Logical Problem Solving

• Coding Exercises

Functions & Modular Programming

• Functions

• Parameters and Arguments

• Return Values

• Default and Keyword Arguments

• Variable-Length Arguments

• Scope and Namespace

• Lambda Functions

• Modules

• Packages

• Import Mechanisms

Object-Oriented Programming

• Classes and Objects

• Constructors

• Instance and Class Variables

• Encapsulation

• Inheritance

• Polymorphism

• Abstraction

• Static Methods

• Class Methods

Advanced Python

• List, Dictionary and Set Comprehensions

• Iterators

• Generators

• Decorators

• File Handling

• Exception Handling

• Context Managers

• Virtual Environments

• Package Management

Hands-on

• Python programming exercises

• Problem-solving exercises

• File processing application

• OOP-based application

• API data processing using Python

• Mini Python project

Tools & Technologies Covered

Python | VS Code | Jupyter Notebook | pip | Virtual Environment

Expected Outcomes

Students will be able to:

• Develop Python programs confidently

• Apply object-oriented programming

• Build modular Python applications

• Work with Python data structures

• Handle files and exceptions

• Create reusable Python components

• Develop a strong programming foundation for AI application development

MODULE 2 – API FUNDAMENTALS & PYTHON API INTEGRATION

Topics Covered

API Fundamentals

• What is an API?

• Client-Server Architecture

• REST API Fundamentals

• HTTP and HTTPS

• HTTP Request and Response

• HTTP Methods

  • GET

  • POST

  • PUT

  • PATCH

  • DELETE

• HTTP Status Codes

• Headers

• Query Parameters

• Path Parameters

JSON & Data Exchange

• JSON fundamentals

• JSON Objects and Arrays

• Serialization and Deserialization

• Working with structured API responses

• Parsing JSON using Python

API Authentication

• API Keys

• Bearer Tokens

• Basic Authentication

• Authentication Headers

• Environment Variables

• Secure API Key Management

Working with APIs using Python

• Python requests library

• Sending GET and POST requests

• Passing parameters

• Sending JSON payloads

• Processing API responses

• Handling API errors

• API timeout and retry concepts

AI API Integration

• Understanding AI Model APIs

• Connecting Python applications to AI APIs

• Sending prompts through APIs

• Receiving structured responses

• Managing API requests

• Token and usage awareness

Hands-on

• Consume public REST APIs

• Build a Python API client

• Create a weather/data API application

• Integrate an AI API with Python

• Build a simple Python-based AI assistant

Tools & Technologies Covered

Python | REST APIs | HTTP | JSON | Requests | API Keys | AI APIs

Expected Outcomes

Students will be able to:

• Understand REST API architecture

• Work with HTTP methods and responses

• Consume APIs using Python

• Handle JSON data

• Securely manage API credentials

• Integrate AI APIs into Python applications

MODULE 3 – GENERATIVE AI & LARGE LANGUAGE MODELS

Topics Covered

Generative AI Fundamentals

• Introduction to Generative AI

• Traditional AI vs Generative AI

• Generative AI applications

• LLM-powered applications

• Capabilities and limitations of LLMs

Understanding LLMs

• What are Large Language Models?

• Tokens

• Context Windows

• Model Parameters

• Model Training – conceptual understanding

• Inference

• Transformer Architecture – conceptual overview

• Attention Mechanism – conceptual overview

Working with LLMs

• LLM providers

• Cloud-based LLMs

• Open-source LLMs

• Model selection

• Temperature and generation parameters

• Context management

LLM APIs

• Connecting to LLM APIs

• Sending prompts

• Processing responses

• Structured responses

• Error handling

• Token usage and cost awareness

Hands-on

• LLM API integration

• Build a basic AI chatbot

• Build a text summarization application

• Build an AI content generation application

• Experiment with different models and parameters

Tools & Technologies Covered

Python | OpenAI | Anthropic | Gemini | LLM APIs

Expected Outcomes

Students will be able to:

• Understand the fundamentals of Generative AI

• Explain the basic working of LLMs

• Work with LLM APIs

• Build basic LLM-powered applications

• Select appropriate models for different use cases

MODULE 4 – PROMPT ENGINEERING & LLM APPLICATION DEVELOPMENT

Topics Covered

Prompt Engineering Fundamentals

• Prompt design principles

• Clear instructions

• Context and constraints

• Zero-Shot Prompting

• One-Shot Prompting

• Few-Shot Prompting

• Role-based prompting

• Structured prompting

Advanced Prompting

• Prompt templates

• Task decomposition

• Output formatting

• Structured outputs

• Prompt optimization

• Prompt testing and evaluation

LLM Application Development

• Conversation management

• Context management

• System and user instructions

• Dynamic prompts

• Response validation

• Function Calling

• Tool Calling

• Structured data extraction

AI Application Architecture

• LLM application workflow

• User input

• Prompt processing

• Model interaction

• Tool execution

• Response generation

Hands-on

• Build an AI chatbot

• Build a document summarizer

• Structured data extraction application

• Function-calling application

• AI-powered business assistant

Tools & Technologies Covered

Python | LLM APIs | Prompt Engineering | Function Calling | Structured Outputs

Expected Outcomes

Students will be able to:

• Design effective prompts

• Build structured LLM applications

• Implement function and tool calling

• Manage context

• Create AI-powered business applications

MODULE 5 – RETRIEVAL AUGMENTED GENERATION (RAG)

Topics Covered

RAG Fundamentals

• What is RAG?

• Why RAG is required

• LLM limitations

• RAG architecture

• Retrieval vs Generation

• Enterprise Knowledge Systems

Document Processing

• Document loading

• PDF and text processing

• Document cleaning

• Text extraction

• Chunking strategies

• Metadata handling

Embeddings

• What are embeddings?

• Creating embeddings

• Semantic representation

• Similarity measurement

• Semantic Search

Vector Databases

• Vector database concepts

• Vector storage

• Indexing

• Similarity Search

• Retrieval pipelines

Building RAG Applications

• Retrieval workflow

• Context construction

• Prompt augmentation

• Response generation

• RAG evaluation basics

• Handling irrelevant information

• Improving retrieval quality

Hands-on

Project – AI Knowledge Assistant

• Upload documents

• Process documents

• Generate embeddings

• Store vectors

• Retrieve relevant information

• Generate contextual responses

• Build a conversational document assistant

Tools & Technologies Covered

Python | Embeddings | Vector Databases | RAG | OpenAI / Anthropic / Gemini

Expected Outcomes

Students will be able to:

• Understand RAG architecture

• Build document-based AI applications

• Implement semantic search

• Work with vector databases

• Develop enterprise knowledge assistants

MODULE 6 – AI AGENTS & TOOL-CALLING

Topics Covered

Understanding AI Agents

• What is an AI Agent?

• AI Assistant vs AI Agent

• Generative AI vs Agentic AI

• Agent architecture

• Agent goals

• Agent state

• Agent reasoning and planning

Agent Components

• LLM

• Instructions

• Tools

• Memory

• Planning

• Execution

• Observation

• Decision Making

Tool & Function Calling

• Function Calling

• Tool Calling

• Defining tools

• Tool selection

• Tool execution

• Tool results

• Multiple tools

• Error handling

Agent Workflows

• Task decomposition

• Planning

• Execution

• Validation

• Iterative workflows

• Agent loops

• Human approval

Types of AI Agents

• Research Agent

• Coding Agent

• Data Analysis Agent

• Customer Support Agent

• Automation Agent

Hands-on

Project – AI Task Automation Agent

• Understand user objective

• Break task into steps

• Select tools

• Execute tools

• Process results

• Validate output

• Generate final response

Tools & Technologies Covered

Python | LLM APIs | Function Calling | Tool Calling | AI Agents

Expected Outcomes

Students will be able to:

• Understand AI Agent architecture

• Build tool-using AI Agents

• Implement function calling

• Design agent workflows

• Automate multi-step tasks using AI

MODULE 7 – LANGCHAIN FOR AI APPLICATIONS & AGENTS

Topics Covered

LangChain Fundamentals

• Introduction to LangChain

• LangChain architecture

• Models

• Prompts

• Chains

• Runnables

• Output Parsers

LangChain & RAG

• Document loaders

• Text splitters

• Embeddings

• Retrievers

• Vector stores

• Retrieval chains

LangChain Agents

• Agent architecture

• Tools

• Tool calling

• Agent execution

• Agent memory

• Agent workflows

Building AI Applications

• AI chatbot

• RAG application

• Tool-using Agent

• Business automation agent

Hands-on

• Build a LangChain RAG application

• Build a tool-using Agent

• Build a research assistant

• Build an AI business assistant

Tools & Technologies Covered

LangChain | Python | LLM APIs | Vector Databases

Expected Outcomes

Students will be able to:

• Develop LLM applications using LangChain

• Build RAG applications

• Integrate tools with Agents

• Create reusable AI application components

MODULE 8 – AGENTIC WORKFLOWS WITH LANGGRAPH

Topics Covered

LangGraph Fundamentals

• Introduction to LangGraph

• Graph-based AI workflows

• Nodes

• Edges

• State

• State management

• Workflow execution

Agentic Workflows

• Sequential workflows

• Conditional workflows

• Dynamic routing

• Agent orchestration

• Planning and execution

• State persistence

Advanced Agent Workflows

• Human-in-the-loop

• Checkpoints

• Error handling

• Retry workflows

• Agent validation

• Multi-step workflows

Agent Design Patterns

• Router Pattern

• Planner-Executor Pattern

• Supervisor Pattern

• Reflection Pattern

• Human-in-the-loop Pattern

Hands-on

Project – Intelligent Workflow Agent

• Analyze a task

• Create an execution plan

• Route tasks

• Select appropriate tools

• Execute workflow

• Validate results

• Request human approval

• Generate final output

Tools & Technologies Covered

LangGraph | Python | LangChain | LLM APIs

Expected Outcomes

Students will be able to:

• Build stateful AI workflows

• Orchestrate multiple AI tasks

• Implement conditional routing

• Build human-in-the-loop systems

• Develop advanced Agentic AI workflows

MODULE 9 – MULTI-AGENT AI SYSTEMS

Topics Covered

Multi-Agent Fundamentals

• Single-Agent vs Multi-Agent Systems

• Multi-Agent architecture

• Agent specialization

• Agent roles and responsibilities

Agent Collaboration

• Agent-to-Agent communication

• Task delegation

• Result sharing

• Agent coordination

• Parallel execution

Multi-Agent Architectures

• Supervisor Agent

• Worker Agents

• Planner Agent

• Research Agent

• Analysis Agent

• Report Agent

Multi-Agent Orchestration

• Workflow design

• Agent routing

• Result aggregation

• Validation

• Conflict handling

Hands-on

Project – Multi-Agent Business Assistant

Supervisor Agent

↓

Research Agent
Data Analysis Agent
Content/Report Agent

↓

Final Response

Students will build a complete multi-agent workflow involving task distribution, collaboration and result aggregation.

Tools & Technologies Covered

Python | LangGraph | LangChain | LLM APIs | Multi-Agent Architecture

Expected Outcomes

Students will be able to:

• Design multi-agent architectures

• Create specialized AI Agents

• Implement agent collaboration

• Build supervisor-worker architectures

• Develop multi-agent business workflows

MODULE 10 – MODEL CONTEXT PROTOCOL (MCP)

Topics Covered

MCP Fundamentals

• What is Model Context Protocol?

• Why MCP is important

• MCP architecture

• MCP Clients

• MCP Servers

• MCP Tools

• MCP Resources

MCP & AI Agents

• Connecting Agents with external tools

• Tool discovery

• Tool execution

• External system integration

• Database and API integration

Building MCP Solutions

• MCP server concepts

• Creating MCP tools with Python

• Connecting AI Agents to MCP

• Using MCP-enabled tools

• Security considerations

Hands-on

Project – MCP-Powered AI Agent

• Create an MCP tool

• Connect the tool to an AI Agent

• Access external information

• Execute actions through tools

• Generate intelligent responses

Tools & Technologies Covered

Python | MCP | AI Agents | APIs | External Tools

Expected Outcomes

Students will be able to:

• Understand MCP architecture

• Build basic MCP tools

• Connect Agents to external systems

• Use MCP to extend Agent capabilities

MODULE 11 – ADVANCED AGENTIC AI

Topics Covered

Agent Memory

• Why Agents need memory

• Short-Term Memory

• Long-Term Memory

• Conversation Memory

• Persistent State

• Memory management

Agent Planning

• Task decomposition

• Planning strategies

• Goal-based execution

• Dynamic planning

Reflection & Self-Correction

• Reflection patterns

• Output validation

• Self-correction

• Retry mechanisms

• Error recovery

Agent Evaluation

• Agent response evaluation

• Tool-call accuracy

• RAG evaluation

• Hallucination detection

• Basic evaluation strategies

Guardrails & Reliability

• Input validation

• Output validation

• Safety controls

• Handling hallucinations

• Error handling

• Human approval

Optimization

• Token optimization

• Context optimization

• Cost management

• Response latency

• Model selection

Hands-on

• Build a memory-enabled Agent

• Implement Agent validation

• Add retry and error recovery

• Evaluate Agent responses

• Optimize Agent cost and performance

Tools & Technologies Covered

Python | LangGraph | RAG | Agent Evaluation | Guardrails

Expected Outcomes

Students will be able to:

• Build more reliable AI Agents

• Implement Agent memory

• Add validation and error recovery

• Evaluate Agent performance

• Optimize AI applications for cost and performance

MODULE 12 – REAL-WORLD AI AGENT PROJECTS

Project 1 – Enterprise Knowledge Assistant

Technologies: Python + LLM + RAG + Vector Database

• Document ingestion

• Document processing

• Embeddings

• Retrieval

• Context generation

• Conversational interface

Project 2 – AI Research Agent

Technologies: Python + LLM + Tools + Agent Workflow

• Task understanding

• Research planning

• Information gathering

• Tool/API usage

• Analysis

• Report generation

Project 3 – Multi-Agent Business Automation System

Technologies: Python + LangGraph + Multi-Agent Architecture

• Supervisor Agent

• Research Agent

• Analysis Agent

• Report Agent

• Task delegation

• Agent collaboration

• Result validation

Project 4 – MCP-Enabled Enterprise AI Agent

Technologies: Python + AI Agent + MCP + APIs

• Business problem identification

• Agent architecture

• Tool integration

• MCP integration

• External system interaction

• Human approval workflow

• End-to-end implementation

TOOLS & TECHNOLOGIES COVERED

Python
VS Code
Jupyter Notebook
Git & GitHub
REST APIs
JSON
OpenAI
Anthropic
Google Gemini
LLM APIs
Pydantic
LangChain
LangGraph
RAG
Embeddings
Vector Databases
MCP
AI Agents
Multi-Agent Systems

PRACTICAL APPROACH

• Hands-on Python programming

• API integration exercises

• LLM API development

• Prompt engineering exercises

• RAG implementation

• AI Agent development

• Tool and Function Calling

• LangChain application development

• LangGraph Agentic workflows

• Multi-Agent system development

• MCP integration

• Agent evaluation and optimization

• Multiple real-world projects

• GitHub portfolio development

EXPECTED OUTCOMES OF THE PROGRAM

By the end of this program, learners will be able to:

• Develop applications using Python

• Work with REST APIs and AI APIs

• Build LLM-powered applications

• Design and optimize prompts

• Build Retrieval Augmented Generation applications

• Work with embeddings and vector databases

• Develop intelligent AI Agents

• Implement Function Calling and Tool Calling

• Build Agentic workflows using LangGraph

• Develop Multi-Agent systems

• Integrate external tools using MCP

• Implement Agent memory and state management

• Build human-in-the-loop workflows

• Evaluate and optimize AI Agents

• Develop end-to-end Agentic AI applications

• Build a professional AI project portfolio

CAREER OPPORTUNITIES

Upon successful completion of this program, learners can pursue roles such as:

• AI Engineer

• Generative AI Developer

• Agentic AI Developer

• AI Application Developer

• LLM Application Developer

• Python AI Developer

• RAG Developer

• AI Automation Engineer

• AI Solutions Engineer

• AI Product Engineer

• Conversational AI Developer

• AI Agent Developer

PROGRAM TECHNOLOGY PATH

Core Python
↓
API Fundamentals
↓
Generative AI & LLMs
↓
Prompt Engineering
↓
LLM Applications
↓
RAG
↓
AI Agents
↓
LangChain
↓
LangGraph
↓
Multi-Agent Systems
↓
MCP
↓
Advanced Agentic AI
↓
Real-World AI Agent Projects