Agentic AI Course
Welcome to the **Agentic AI Masterclass** – your ultimate guide to building **autonomous, intelligent AI agents** using **Large Language Models (LLMs)** and modern AI frameworks! 🚀
- 5.5K likes on YouTube
- 281.9K views
Created by Code With Aarohi Hindi on YouTube
What you'll learn
- What is agentic AI
- Generative AI • What generative models do
- Generative AI vs Agentic AI
- What is an AI agent
- Types of AI agents
- Simple reflex agents
- AI Agents • Goal-based agents
- Autonomy in AI agents
Explore related topics
Course content
01Agentic AI Explained | How AI Agents Work & Why They MatterPreview02:42
This chapter introduces agentic AI, a type of AI that can make decisions on its own. It learns from its surroundings and from real-time data, then adapts what it has learned to choose actions without needing humans to decide for it. The key point is that agentic AI does more than generate data or content; it focuses on decision making based on its experience.
- What is agentic AI
- Autonomy in AI agents
- Learning from the environment and real-time data
- Decision making in agentic AI
- Self-driving cars as AI agents
02Generative AI Explained | How AI Generates New ContentPreview02:32
This chapter introduces Generative AI, a type of AI model that can create new data in many forms, such as text, images, or video. The core idea is that a generative model is first trained on a training dataset, and during this training it learns patterns from that data. Once trained, the model can be used to generate new data that did not exist before, which is the key difference from models that only analyse or classify existing data.
- Generative AI • What generative models do
- Generative AI • Training and generating new data
- Generative AI • Text generation (ChatGPT)
- Generative AI • Image generation (DALL-E)
- Generative AI • GANs and deepfakes
- Generative AI • Limits of generative AI
03Generative AI vs Agentic AI? | How They Work TogetherPreview04:37
This chapter explains the difference between Generative AI and Agentic AI and how the two can be used together. Generative AI is built to create data such as text, images and other content. Agentic AI is focused on decision making: it looks at its surroundings and the parameters it is given, and then decides what action to take on its own.
- Generative AI vs Agentic AI
- Decision making in Agentic AI
- Content generation with Generative AI
- Combining Agentic and Generative AI
- Use case: personalized advertising
- Use case: customer support chatbots
04AI Agents Explained | How AI Agents Work & Make DecisionsPreview03:23
This chapter introduces AI agents. An agent can be a program, a robot, or any system that observes its surroundings, decides what to do, and then acts. Every agent works through three parts: perception, decision, and action. Perception is how the agent senses or observes its environment. Decision is the thinking step, where the agent uses what it perceived to choose what to do. Action is the step where the agent actually carries out that choice, such as replying to a message, switching a device on or off, or moving in its environment.
- What is an AI agent
- Perception, decision and action
- Agent examples: thermostat, chatbot and robot
055 Types of AI Agents Explained with Examples | Agentic AIPreview14:28
This chapter introduces the five main types of AI agents, ordered from simplest to most capable: simple reflex agents, model-based reflex agents, goal-based agents, utility-based agents, and learning agents. A simple reflex agent reacts only to the current situation using condition-action rules, such as an automatic door that opens when someone is near, and it has no memory or planning. A model-based reflex agent works the same way but also keeps an internal memory, called a model of the world, so it can remember past information, such as a user's name, and answer questions about it.
- Types of AI agents
- Simple reflex agents
- Model-based reflex agents
- Goal-based agents
- Utility-based agents
- Learning agents
06Simple Reflex Agent in Python | Build Your First AI AgentPreview17:29
This chapter builds a simple reflex agent in Python for a four-room cleaning task. The rooms form a 2×2 grid, and the agent moves through them one at a time. Dirty rooms are shown in red and clean rooms in green, and the agent is drawn as a blue circle. The agent's index starts at 0 in the first room and increases as it moves. The task runs for eight steps, so each room is visited twice.
- Simple reflex agents
- Condition-action rules
- Agent environment and state
- Python • Dictionaries as environment state
- Python • Matplotlib animation and interactive mode
07Goal-Based AI Agent Using LangChain & Streamlit | Build an AI AgentPreview33:51
This chapter introduces goal-based AI agents, which are systems that work step by step to achieve a defined goal and stop once that goal is met. The example used is a medical appointment scheduler whose goal is to book an appointment: it asks questions, checks doctor availability, books the slot, and then stops. A normal chatbot gives a generic reply, while a goal-based agent keeps its response purposeful and asks follow-up questions to fill in missing information.
- AI Agents • Goal-based agents
- LangChain • Custom tools and agents
- LangChain • Conversation buffer memory
- Python • Regular expressions for data extraction
- Streamlit • Building an agent chat interface
- AI Agents • Using open-source and Google LLMs
- 10Reinforcement Learning Value Function | V(s) Explained with Example & Bellman EquationPreview11:10
Description
Welcome to the **Agentic AI Masterclass** – your ultimate guide to building **autonomous, intelligent AI agents** using **Large Language Models (LLMs)** and modern AI frameworks! 🚀 This playlist is perfect for **AI enthusiasts, developers, and students** looking to master **Agentic AI concepts** and implement real-world projects. 📌 **What You’ll Learn in This Playlist:** ✅ Fundamentals of **AI & Agentic AI** ✅ Types of agents: **Reactive, Utility-based, Goal-based & LLM Agents** ✅ Prompt engineering and **tool integration** ✅ Building workflows using **LangChain, LangGraph, and CrewAI** ✅ Real-world projects: **chatbots, planners, trading bots, and more** ✅ Step-by-step hands-on tutorials with GitHub resources 💡 **Who This Playlist is For:** - Beginners exploring AI agents for the first time - Developers looking to implement **autonomous AI systems** - Students and professionals aiming to understand **LLM-driven workflows** - Anyone interested in **Agentic AI, multi-agent systems, and AI automation** 🔗 **Resources & GitHub:** Check individual video descriptions for **code examples, step-by-step guides, and tutorials**. 💬 **Engage with Us:** Ask questions and share your projects in the comments section. We love helping learners bring **Agentic AI projects to life**! 🔔 Don’t forget to **subscribe** and follow the playlist for **full tutorials on AI agents, workflows, and intelligent systems**. #AgenticAI #AIAgents #LLMAgents #LangChain #LangGraph #CrewAI #AIWorkflow #AIProjects #IntelligentAgents #AutonomousAI #AIforBeginners #AIAutomation #MultiAgentSystems
About the creator
- YouTube channel
- 31.2K subscribers
- 1 course on Studyio
The videos in this course are made by Code With Aarohi Hindi and play from YouTube, credited to them. Studyio adds the chapters, notes, quizzes and a certificate around them.
More courses like this

Barbara O'Neill Part 1. DNA and The True Cause of Disease

Claude – Full Course 2026 (How to use Claude AI for beginners)

How to Speak

Gilbert Strang lectures on Linear Algebra (MIT)

ROYAL ENFIELD HIMALYAN 450 INSTRUMENT CLUSTER FULL DETAIL ALL SETTING PHONE CONNECTION TRIPPER DASH
