ExplainLLM
LLM FundamentalsAI AgentsContext EngineeringClaude CodePlayground

Understand How LLMs Actually Work

Interactive visualizations and hands-on exercises to demystify Large Language Models and AI Agents

Interactive Visualizations

See tokenization, attention, and embeddings come alive with real-time animations

Hands-on Challenges

Test your knowledge with interactive exercises and real-world scenarios

Real-world Examples

Learn from actual use cases in code generation, chatbots, and more

Learning Modules

LLM Fundamentals
12 lessons
Tokenization, embeddings, attention, transformers, inference, decoding, and prompt engineering
Prompting Techniques
19 lessons
CoT, Few-shot, RAG, Tree of Thoughts, Reflexion, and 14 more techniques
AI Agents
9 lessons
ReAct pattern, function calling, planning, memory, and multi-agent systems
Context Engineering
5 lessons
System prompts, context windows, prompt structure, RAG, and security
LLM Production
8 lessons
Model selection, benchmarks, vector databases, observability, and deployment
Multimodal AI
4 lessons
Vision models, image analysis, voice agents, and video understanding
LLM Security
4 lessons
Prompt injection, jailbreaking, biases, and factuality issues
Applications
6 lessons
Code generation, classification, summarization, Q&A, and more
Claude Code Deep Dive
22 lessons
Complete guide: tools, agents, MCP, memory, hooks, and SDK

Subscribe to updates

Get notified about new lessons and materials.

Legal

Terms of ServicePrivacy Policy

© 2024-2026 ExplainLLM. All rights reserved.