AI AGENTS & AGENTIC AI FOR PYTHON DEVELOPERS

0.0

(0)

0 Enrolled

About Course

The AI Agents & Agentic AI with Python Developers program is a practical, industry-oriented training program designed for Python developers who want to build LLM-powered applications, RAG systems, AI Agents, Agentic workflows, Multi-Agent systems and MCP-enabled applications.

The program focuses on the transition from traditional software development to AI Application Engineering and Agentic AI Development.

Learners will work with modern LLM APIs and Python-based AI frameworks to design, develop, integrate and evaluate intelligent applications capable of reasoning, using tools, retrieving information, executing multi-step workflows and collaborating through multiple specialized agents.

The program follows a hands-on, project-based approach, with learners building progressively more advanced AI applications throughout the training.

WHO SHOULD ENROLL

Python Developers
Software Developers
Full Stack Developers
Backend Developers
AI/ML Developers
Automation Engineers with Python experience
Test Automation Engineers with Python experience
Data Scientists with Python experience
Software Engineers transitioning into AI
IT Professionals looking to move into Generative AI
Developers interested in AI Agents and Agentic AI

Prerequisites

Good understanding of Core Python Programming
Familiarity with REST APIs and JSON
Basic understanding of software development concepts
Basic Git/GitHub knowledge is recommended

No prior experience in Generative AI, LLMs, RAG, LangChain, LangGraph, MCP or AI Agents is required.

MODULE 1 – GENERATIVE AI & LARGE LANGUAGE MODELS

Topics Covered

Generative AI Fundamentals

Introduction to Generative AI
Generative AI vs Traditional AI
Generative AI application landscape
LLM-powered applications
Capabilities and limitations of LLMs
AI application architecture

Large Language Models

What are Large Language Models?
LLM architecture – conceptual understanding
Transformer architecture – overview
Attention mechanism – conceptual understanding
Tokens and tokenization
Context windows
Parameters and model behavior
Training vs inference
Model limitations and hallucinations

LLM Models & Providers

Commercial vs Open-Source LLMs
Model selection
Understanding model capabilities
Context and token limitations
Model parameters
Temperature and generation controls

Hands-on

Work with multiple LLM APIs
Compare model responses
Build a basic LLM-powered Python application
Experiment with prompts and model parameters

Tools & Technologies Covered

Python | OpenAI | Anthropic | Google Gemini | LLM APIs

Expected Outcomes

Students will be able to:

Understand modern Generative AI architecture
Explain the fundamentals of LLMs
Select appropriate LLMs for applications
Integrate LLM APIs into Python applications
Build basic LLM-powered applications

MODULE 2 – PROMPT ENGINEERING & LLM APPLICATION DEVELOPMENT

Topics Covered

Prompt Engineering

Prompt Engineering fundamentals
Role-based prompting
Instruction design
Context and constraints
Zero-Shot Prompting
One-Shot Prompting
Few-Shot Prompting
Structured prompting
Prompt templates

Advanced Prompting

Task decomposition
Chain-of-thought concepts
Output formatting
Structured outputs
Prompt optimization
Prompt testing
Prompt evaluation

LLM Application Development

System and user instructions
Conversation management
Context management
Dynamic prompts
Response validation
Structured data extraction
Function Calling
Tool Calling

Hands-on

Build an AI chatbot
Build an AI content assistant
Build a structured information extraction application
Implement function calling
Build an AI 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 application context
Build practical AI-powered applications

MODULE 3 – RETRIEVAL AUGMENTED GENERATION (RAG)

Topics Covered

RAG Fundamentals

What is RAG?
Why RAG is required
LLM knowledge limitations
RAG architecture
Retrieval vs Generation
Enterprise Knowledge Applications

Document Processing

Document loading
PDF and text processing
Document cleaning
Text extraction
Text chunking
Chunking strategies
Metadata management

Embeddings

Understanding embeddings
Creating embeddings
Semantic representation
Similarity search
Semantic retrieval

Vector Databases

Vector database concepts
Vector storage
Indexing
Similarity search
Retrieval pipelines

RAG Application Development

Retrieval workflow
Context construction
Prompt augmentation
Response generation
RAG evaluation
Improving retrieval quality
Handling irrelevant context

Hands-on

Project – Enterprise Knowledge Assistant

Document ingestion
Document processing
Embedding generation
Vector storage
Semantic search
Context retrieval
Answer generation
Conversational knowledge assistant

Tools & Technologies Covered

Python | RAG | Embeddings | Vector Databases | LLM APIs

Expected Outcomes

Students will be able to:

Design RAG architecture
Process and index documents
Implement semantic search
Build vector-based retrieval systems
Develop enterprise knowledge assistants

MODULE 4 – 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
Planning and execution

Agent Components

LLM
Instructions
Tools
Memory
Planning
Execution
Observation
Decision making

Tool & Function Calling

Function Calling
Tool Calling
Defining tools
Tool schemas
Tool selection
Tool execution
Tool results
Multiple tools
Tool error handling

Agentic Workflows

Task decomposition
Planning
Execution
Validation
Agent loops
Iterative execution
Human approval

Agent Use Cases

Research Agents
Coding Agents
Data Analysis Agents
Customer Support Agents
Business Automation Agents

Hands-on

Project – AI Task Automation Agent

Students build an Agent capable of:

Understanding a user objective
Breaking the objective into tasks
Selecting appropriate tools
Executing tools
Processing results
Validating outputs
Producing the final response

Tools & Technologies Covered

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

Expected Outcomes

Students will be able to:

Design AI Agent architecture
Build tool-using Agents
Implement Function and Tool Calling
Create multi-step Agent workflows
Automate tasks using AI

MODULE 5 – LANGCHAIN FOR LLM APPLICATIONS & AI AGENTS

Topics Covered

LangChain Fundamentals

Introduction to LangChain
LangChain architecture
Models
Prompts
Runnables
Chains
Output Parsers

LangChain & RAG

Document loaders
Text splitters
Embeddings
Retrievers
Vector stores
Retrieval chains

LangChain Agents

Agent architecture
Tools
Tool calling
Agent execution
Agent workflows
Memory concepts

AI Application Development

Building chat applications
Building RAG applications
Building tool-using Agents
Building AI assistants

Hands-on

LangChain-based RAG application
Tool-using Agent
AI Research Assistant
Business Automation Assistant

Tools & Technologies Covered

LangChain | Python | LLM APIs | RAG | Vector Databases

Expected Outcomes

Students will be able to:

Build LLM applications using LangChain
Develop RAG pipelines
Integrate tools into Agents
Build reusable AI application components

MODULE 6 – 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
Planning and execution
Agent orchestration
State persistence

Advanced Workflows

Human-in-the-loop
Checkpoints
Error handling
Retry mechanisms
Agent validation
Multi-step workflows

Agentic Design Patterns

Router Pattern
Planner-Executor Pattern
Supervisor Pattern
Reflection Pattern
Human-in-the-loop Pattern

Hands-on

Project – Intelligent Workflow Agent

Students build an Agentic workflow that can:

Analyze a task
Create an execution plan
Route tasks
Select tools
Execute actions
Validate results
Request human approval
Generate final output

Tools & Technologies Covered

LangGraph | LangChain | Python | LLM APIs

Expected Outcomes

Students will be able to:

Build stateful AI workflows
Implement conditional Agent workflows
Orchestrate AI tasks
Implement human-in-the-loop workflows
Build advanced Agentic applications

MODULE 7 – 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
Agent coordination
Result sharing
Parallel execution

Multi-Agent Architectures

Supervisor Agent
Planner Agent
Research Agent
Data Analysis Agent
Content Agent
Report Agent
Worker Agents

Multi-Agent Orchestration

Task distribution
Agent routing
Result aggregation
Agent validation
Conflict handling
Workflow coordination

Hands-on

Project – Multi-Agent Business Assistant

Supervisor Agent

↓

Research Agent
Data Analysis Agent
Content Agent

↓

Report Agent

Students develop a complete multi-agent workflow with task delegation, 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
Build specialized AI Agents
Implement Agent collaboration
Develop supervisor-worker systems
Create multi-agent business workflows

MODULE 8 – MODEL CONTEXT PROTOCOL (MCP)

Topics Covered

MCP Fundamentals

Introduction to Model Context Protocol
Why MCP matters for AI Agents
MCP architecture
MCP Clients
MCP Servers
MCP Tools
MCP Resources

MCP & AI Agents

Connecting Agents to external tools
Tool discovery
Tool execution
External system integration
API integration
Database integration

MCP Development

MCP server concepts
Creating MCP tools with Python
Connecting 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
Extend Agent capabilities using MCP
Connect AI Agents with external systems

MODULE 9 – ADVANCED AGENTIC AI

Topics Covered

Agent Memory

Short-Term Memory
Long-Term Memory
Conversation Memory
Persistent State
Memory management

Planning & Reasoning

Task decomposition
Planning strategies
Goal-based execution
Dynamic planning
Reasoning workflows

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
Evaluation strategies

Guardrails & Reliability

Input validation
Output validation
Guardrails
Safety controls
Hallucination 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 error recovery
Evaluate Agent responses
Optimize Agent performance and cost

Tools & Technologies Covered

Python | LangGraph | RAG | Agent Evaluation | Guardrails

Expected Outcomes

Students will be able to:

Build reliable AI Agents
Implement Agent memory
Add validation and recovery mechanisms
Evaluate Agent performance
Optimize AI Agent applications

MODULE 10 – PRODUCTION-ORIENTED AI AGENT DEVELOPMENT

Topics Covered

AI Application Architecture

Designing AI application architecture
Separating application and AI logic
Configuration management
Environment management
Secure API key management

API & Service Integration

Exposing AI applications through APIs
FastAPI fundamentals for AI applications
Connecting AI Agents to external services
Database integration concepts

Application Reliability

Logging
Error handling
Retry mechanisms
Monitoring concepts
Response validation

AI-Assisted Development

Using AI coding assistants
Claude Code / Cursor concepts
AI-assisted coding
AI-assisted debugging
AI-assisted refactoring
Code review with AI

Version Control

Git workflow
GitHub repository management
Managing AI application code
Project documentation

Hands-on

Convert an Agent into an API service
Implement logging and error handling
Create a GitHub project
Use AI-assisted development to improve the project

Tools & Technologies Covered

Expected Outcomes

Students will be able to:

Structure AI applications professionally
Expose Agents through APIs
Implement basic reliability practices
Use Git/GitHub for AI projects
Use AI coding assistants effectively

MODULE 11 – REAL-WORLD AI AGENT PROJECTS

PROJECT 1 – ENTERPRISE KNOWLEDGE ASSISTANT

Technologies: Python + LLM + RAG + Vector Database

Document ingestion
Document processing
Embeddings
Vector search
Retrieval
Context generation
Conversational interface

PROJECT 2 – AI RESEARCH AGENT

Technologies: Python + LLM + Tools + Agent Workflow

User objective understanding
Research planning
Information gathering
Tool/API usage
Analysis
Information synthesis
Report generation

PROJECT 3 – MULTI-AGENT BUSINESS AUTOMATION SYSTEM

Technologies: Python + LangGraph + Multi-Agent Architecture

Supervisor Agent
Research Agent
Analysis Agent
Content 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

PRACTICAL APPROACH

Hands-on LLM application development
LLM API integration
Prompt engineering exercises
RAG implementation
Vector database implementation
AI Agent development
Function and Tool Calling
LangChain development
LangGraph Agentic workflows
Multi-Agent system development
MCP integration
Agent memory implementation
Agent evaluation
Guardrails and reliability
AI-assisted software development
Git/GitHub project development
Multiple real-world projects

EXPECTED OUTCOMES

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

Build LLM-powered applications using Python
Integrate commercial LLM APIs
Design effective prompts
Build structured LLM applications
Develop RAG-based applications
Work with embeddings and vector databases
Build intelligent AI Agents
Implement Function Calling and Tool Calling
Create stateful Agentic workflows
Use LangChain and LangGraph
Build Multi-Agent systems
Integrate external tools using MCP
Implement Agent memory
Build human-in-the-loop workflows
Evaluate Agent performance
Implement basic guardrails and reliability mechanisms
Expose AI applications through APIs
Use AI coding assistants for development
Build end-to-end Agentic AI applications
Develop a portfolio of real-world AI projects

CAREER OPPORTUNITIES

Learners completing this program 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
AI Agent Developer
Generative AI Application Engineer

TECHNOLOGY LEARNING PATH

Python Development Knowledge
↓
Generative AI & LLMs
↓
Prompt Engineering
↓
LLM Applications
↓
RAG
↓
AI Agents & Tool Calling
↓
LangChain
↓
LangGraph
↓
Multi-Agent Systems
↓
MCP
↓
Advanced Agentic AI
↓
Production-Oriented Development
↓
Real-World AI Agent Projects