Agentic AI is a branch of artificial intelligence focused on building autonomous, intelligent agents capable of making decisions, interacting with other agents and completing complex tasks with minimal human intervention. It combines LLMs, multi-agent systems and workflow orchestration to build advanced AI applications.
Basics
This section introduces Agentic AI, where intelligent systems act autonomously, interact with their environment and collaborate with other agents to complete tasks.
- Introduction
- Agent vs Traditional AI
- Types of Agents
- Building AI Agents
- AI Agent Frameworks
- Multi-Agent Systems
- Agent-to-Agent Communication (A2A)
Python for Agentic AI
Python is used in Agentic AI for building intelligent agents, automating decision-making workflows and integrating AI models with external tools and APIs.
- Introduction
- Download and Install Python 3
- Python Variables
- Python Data Types
- Python Operators
- Conditional Statements in Python
- Loops in Python
- Python Functions
- Python String
- Python Lists
- Python Dictionary
Frameworks & Libraries for Agentic AI
This section introduces the key frameworks and libraries used to build agentic AI systems and autonomous agents. These tools help in developing AI agents, managing workflows and integrating language models with external data sources.
- Hugging Face Transformers
- LangChain
- LangGraph
- Langflow
- LlamaIndex
- Integration of Langchain with Llama-Index
Generative AI
It helps agents to produce text, code and actions autonomously.
- Large Language Model
- Popular LLMs: GPT, Claude, LLaMA, Gemini
- LLM APIs: OpenAI, Hugging Face, Gemini
- Hugging Face Models
Prompt Engineering
Focuses on designing effective inputs to improve LLM outputs
- Introduction
- Zero-Shot, One-Shot & Few-Shot Prompting
- Chain of Thought Prompting
- Role & Contextual Prompting
- ReAct (Reasoning + Acting) Prompting
- Retrieval-Augmented Prompting
- Self-Consistency Prompting
- Tree of Thought (ToT) prompting
- Guardrails in AI
Knowledge, Memory & Embeddings
explains how agents use embeddings, memory and retrieval techniques to store, recall and process knowledge in context-aware systems.
- Embeddings
- Vector Databases: FAISS, ChromaDB, Qdrant, Pinecone
- Agent Architectures & Memory
- Model Context Protocol (MCP)
- Context-aware agent workflows
- Context Sharing System using MCP
- RAG in AI
- RAG Architecture
- Multimodal RAG
CrewAI
Supports collaboration between multiple agents on shared tasks
- Introduction
- CrewAI Tools
- Creating Custom Tools for CrewAI
- Memory in CrewAI
- CrewAI Embeddings
- CrewAI Collaboration
- CrewAI Knowledge
- CrewAI Planning and Reasoning
- CrewAI CLI
- CrewAI Flow
- Fraud Detection Using CrewAI Project
Automation & Workflow Integration
Agentic AI can be combined with automation tools to execute complex workflows and business processes.
- Agentic RAG
- Agentic RAG with LlamaIndex
- Introduction to n8n
- Automated Email Classifier with n8n
- AI Deployment with Gradio, Streamlit, FastAPI
Responsible & Ethical AI
This section discusses the ethical, legal and security challenges of autonomous agents and outlines responsible practices for safe deployment.
Projects
This section provides practical, hands-on project ideas to help apply these concepts and build a strong portfolio.
- Building an AI application with LlamaIndex
- PDF Summarizer using RAG
- RAG(Retrieval-Augmented Generation) using LLama3
- Simple Retrieval Augmented Generation using Java
- Building AI Agents with Phidata
- RAG System with Langchain and Langraph
Careers in Agentic AI
One of the fastest-growing fields in AI, offering strong career opportunities