AI tutorials you can see and play with
Every concept explained in simple English, with animated diagrams you can control, real code with output and a quick quiz. From neural networks to RAG and AI agents — free.
Understand how an RNN reads a sentence word by word, with an interactive unrolled RNN. Hidden state, the RNN equation, types of RNN, backpropagation through time, vanishing and exploding gradients, NumPy and PyTorch code.
Learn how an LSTM works with an interactive, animated LSTM cell. Forget, input and output gates, the cell state, the math, a worked example, NumPy and PyTorch code, LSTM vs GRU and interview questions.
See self-attention in action. Click any word to see where it looks, then step through Q·Kᵀ, scaling, softmax and the weighted sum with real numbers. Multi-head attention, masking, positional encoding, NumPy and PyTorch code.
Learn RAG step by step with interactive visuals. Watch the RAG pipeline animate, play with chunk size and overlap, run a similarity search in your browser and see the exact prompt the LLM receives. Embeddings, vector databases, evaluation and LangChain code.
Watch an AI agent think, call tools and observe results in an animated ReAct loop. Learn what makes an agent different from a chatbot, how tool calling works, agent patterns, MCP, frameworks like LangGraph and CrewAI, and how to keep agents safe.
Step through binary search on a live array, see why O(log n) is so fast, then learn the iterative and recursive code, lower bound, first and last occurrence, binary search on the answer, common bugs and interview questions.
AI Foundations
- The AI Landscape
- How an LLM Answers a Question
- Careers, Roadmap & Your First GenAI App
- Environment Setup
Deep Learning & NLP
- Recurrent Neural Networks (RNN)NEW
- LSTM (Long Short-Term Memory)NEW
- Tokenization
- Text Preprocessing
- Regular Expressions
- Count-Based Feature Representation
- Word Embeddings
- Artificial Neural Networks
- Loss Functions & Gradient Descent
- Backpropagation
- Activation Functions & Gradient Problems
- Optimizers & Training in Practice
- Recurrent Neural Networks
- LSTM & GRU
- Encoder–Decoder (Seq2Seq)
Transformers & LLMs
- Self-Attention (Q, K, V)NEW
- Motivation & Self-Attention
- Scaled Dot-Product & Multi-Head Attention
- Advanced Attention
- Architecture & Positional Encoding
- Inside the Encoder and Decoder Blocks
- Transformer Variants
- BERT Explained: How It Works and Its Variants
- Generative Modeling & Hugging Face
- How an LLM Is Trained
- Decoding Strategies & the LLM Landscape
- Adaptation, Quantization & Evaluation
- Prompt Fundamentals
- Reasoning Techniques
- Structured Output & Reliability
- Dynamic Prompting with LangChain
- Conversational Chains & Tracing
- LoRA and Fine-Tuning
- The Fine-Tuning Decision
- PEFT Hands-On
RAG & LangChain
- RAG (Retrieval-Augmented Generation)NEW
- RAG From Scratch
- RAG Foundations
- Document Extraction
- Chunking Strategies
- Embeddings & Vector Databases
- Retrievers & Re-Ranking
- RAG Evaluation
- LangGraph & Agentic RAG
- Production Challenges
- LLMs & Chat Models
- Prompt Templates
- Output Parsers & Structured Output
- Chains with LCEL & Runnables
- Memory & Chat History
- Document Loaders
- Text Splitters (Chunking)
- Embeddings
- Vector Stores
- Retrievers
- RAG: Chat with your PDF
- Tools & Tool Calling
- Agents with create_agent
- Middleware & Guardrails
- Callbacks, Caching, Rate Limits & LangSmith
- LangChain Classic: Reading Old Code
- LangGraph Basics: the Engine behind Agents
Agentic AI
- AI Agents & the ReAct LoopNEW
- What Is an AI Agent?
- Tool Calling Explained
- MCP in 5 Minutes
- Multi-Agent Patterns
- LangChain: Complete Interactive Notes
- LangGraph: Complete Interactive Notes
- LlamaIndex: Interactive Notes
- Which AI Framework Should You Use?
AI System Design & Security
- Design a RAG Chatbot
- Serving LLMs at Scale
- Caching, Rate Limits and Cost Control
- OWASP Top 10 for LLM Applications
- OWASP Top 10 for Agentic Applications
- Red-Teaming an LLM App
Data Structures & Algorithms
- Binary SearchNEW
- Big-O & Complexity
- Arrays, Hashing & Prefix Sums
- Two Pointers
- Sliding Window
- Binary Search
- Sorting Algorithms
- Stacks, Queues & Monotonic Stacks
- Linked Lists
- Heaps & Priority Queues
- Trees & Graphs, Visually
- Binary Trees & BSTs
- Graphs: BFS & DFS
- Topological Sort, Dijkstra & Union-Find
- Recursion & Backtracking
- Dynamic Programming (1-D)
- Dynamic Programming (2-D)
- Greedy & Intervals
- Bit Manipulation
Cloud AI: Azure & AWS
- Session 1: The AI Landscape & Setup
- Session 2: Responsible AI & How Generative Models Work
- Lab 1: Your First Model in Microsoft Foundry
- Session 3: Generative, Agentic, Text & Speech Workloads
- Session 4: Vision & Information Extraction Workloads
- Lab 2: AI Workload Explorer
- Session 5: Prompts & Model Deployment
- Session 6: Chat App with the Foundry SDK
- Session 7: Building Your First Agent
- Lab 3: Chat Assistant & Customer Support Agent
- Session 8: Language & Speech in Foundry Tools
- Lab 4: Voice Feedback Analyzer (BFSI)
- Session 9: Vision & Image Generation
- Lab 5: Image Describer & Generator
- Session 10: Azure Content Understanding
- Lab 6: Invoice Data Extractor
- Session 11: Mock Exam 1 & Gap Review
- Session 12: Mock Exam 2 & Exam Strategy
- Lab 7: Mock Exam Analysis
- Session 13: Topic-wise Practice Questions
- Session 14: Mock Exam 3 & Exam-Day Readiness
- Lab 8: Final Readiness Drill
- Introduction to Cloud Computing & AWS
- Cloud Service & Deployment Models
- AWS Deep Dive & Global Infrastructure
- Virtualization & Creating Your AWS Account
- Introduction to Networking
- IPv4 Addressing
- IP Classes, Public vs Private & DHCP
- Amazon EC2 and Its Features
- Operating Systems & a Windows EC2 Instance
- Launch & Access a Linux EC2 Instance
- Linux Introduction & Navigation Commands
- Linux File Commands & Web Servers on EC2
AI in Finance
- AI in Banking & Finance: The Big Picture
- Fraud Detection Fundamentals
- Imbalanced Learning & Cost-Sensitive Evaluation
- Feature Engineering for Transactions & Graph Fraud
- Credit Risk Modelling & Scorecards
- AML & Transaction Monitoring with ML
- Explainability, Fairness & Model Risk Management
- GenAI in Banking: Use Cases, Architecture & Guardrails
GenAI Course
A complete 40-session course from AI basics and NLP to transformers, LLMs, prompting, RAG and fine-tuning, plus animated visual lessons.
Start courseLangChain Hands-on
17 hands-on labs from Ajeetkumar’s Colab notebooks: chat models, prompts, parsers, LCEL, memory, RAG, tools, agents, middleware, production and LangGraph, with a free Groq key.
Start courseAzure AI Fundamentals (AI-901)
The complete AI-901 course by Ajeetkumar, from AI basics to building chat apps, agents, speech, vision and document-extraction apps in Microsoft Foundry: 14 sessions, 8 hands-on labs, 5 portfolio projects and 3 timed mock exams, mapped to Microsoft’s official skills outline.
Start courseAWS Solutions Architect
Learn AWS from zero for the Solutions Architect Associate exam: cloud basics, networking, EC2, Linux and web servers, with labs and live tools.
Start courseDSA
Data structures & algorithms for coding interviews: 17 visual lessons with 37 step-by-step animations, and 90 practice problems with an online editor, solutions in Python, Java, C++ and JavaScript, hints and approaches.
Start course10 Job-ready AI Projects
10 job-ready AI projects with architecture, step-by-step build, starter code, free deployment, resume bullets and the interview questions each project triggers.
See projectsStudents and freshers with basic Python
- Python & ML basics
- NLP foundations
- Neural networks
- Sequence models → attention
- Transformers & LLMs
- Prompting
- +6 more
Working data scientists / ML engineers switching to GenAI
- Transformers refresh
- Prompting & structured output
- RAG properly
- Evaluation project
- Agents & MCP
- Fine-tuning
- +2 more
Engineers in IT services targeting product companies / big tech
- DSA foundations
- DSA patterns
- ML depth
- ML system design
- Strong project
- DP & harder DSA
- +2 more
Anyone preparing for product-company coding rounds (about 1 hour a day)
- Big-O, arrays & hashing
- Two pointers & sliding window
- Binary search & sorting
- Stacks, linked lists & heaps
- Trees
- Graphs
- +2 more
Beginners to Azure and AI; follows the live weekend batch (2 sessions per weekend + labs)
- AI concepts & responsible AI
- AI workloads on Azure
- Prompts, deployment & the Foundry SDK
- Agents, plus language & speech
- Vision, image generation & Content Understanding
- Revision & mock exams 1–2
- +1 more
Anyone targeting banks, fintech, payments or insurance
- Domain basics
- Modelling rare events
- Credit & AML
- Governance
- Build the project
- Interview sprint