Track your progress.
Resources / AI System Design
AI System Design archive
A structured path through designing AI systems end to end. 19 modules covering requirements, data and training pipelines, serving, LLM, RAG and agent architectures, reliability, security, observability, evaluation and MLOps, with case studies and interview revision at the end.
19 modules168 sections29 diagrams
Curriculum structure
FoundationsWhat AI system design is and how to scope it
Data and modelsPipelines, training and serving
Application architecturesLLMs, RAG, agents and the components beneath them
Production qualityReliability, security, observability, evaluation and operations
In practiceCase studies and a full project
RevisionInterview prep, takeaways and trends
Topic threads
LLM applications
From a plain LLM app to RAG to agents.
Model lifecycle
Data, training, serving and the MLOps loop that ties them together.
Reliability & operations
Staying up, seeing inside the system and running it day to day.
Evaluation
Success metrics, evaluation and testing, then evaluation inside a full project.
Safety & security
Component-level access control and the wider security and privacy view.
Applied examples
Case studies, then a worked end-to-end project.