AI systems, illustrated.
Learn how production AI really works — tokens, attention, RAG, agents, inference, evals — by stepping through animated diagrams. Every idea is a picture that moves, breaks and gets fixed in front of you.
- 25
- modules
- 2409
- animated steps
- free
- no login
Every lesson tells the same five-part story.
Use ← → to step. Metrics update as the system changes, so you see what each decision buys you.
- Problem01
Something breaks or doesn't scale.
- Key idea02
The one insight that fixes it.
- How it works03
Watch the mechanism move.
- Trade-off04
What it costs, when it fails.
- Recap05
The decision table to keep.
Pick a module
AI Foundations
Machine learning, deep learning, NLP, computer vision, reinforcement learning and the techniques underneath modern AI.
How LLMs Work
Tokens, attention, transformers, embeddings and the inference pipeline — from text in to text out.
Choosing Models
The model landscape, capability assessment, pricing, and how to pick the right model for the job.
Training & Adaptation
Pretraining, fine-tuning, LoRA, RLHF/DPO, distillation, synthetic data, quantization and reasoning models.
Inference & Serving
KV cache, batching, speculative decoding, paged attention, serving stacks and the cost playbook.
Prompting & Context
Prompt fundamentals, few-shot, chain/tree of thought, context engineering, structured output and injection defense.
Read, map, or follow a path.
Guide library
All 141 chapters of the open-source AI System Design Guide — interview prep, case studies, glossary — each linked to its animated lesson.
Browse chapters →Mind maps
Zoom and pan around interactive maps of whole fields. Click any node for notes and resources.
All mind maps →Roadmaps
Structured learning paths with progress tracking — from AI foundations to MLOps and agents.
See roadmaps →