Guided education
Learn
Guided reading paths through AI systems foundations, model internals, local inference, agent performance, evaluation, and production infrastructure.
Build a working understanding of AI systems, from the model execution loop to the infrastructure around it. Choose a path for the question you are trying to answer, then connect the concepts to a worked example or experiment.
How to use these paths
Start with AI Systems Foundations if you are new to the system architecture. For a specific engineering problem, go directly to the relevant path. Each path describes its audience, goals, prerequisites, and a suggested reading sequence.
Existing articles are linked as starting points. New guided lessons will appear in the published lesson lists as they are released. For all articles in publication order, visit Writing; for experiments and research analysis, explore Labs and Research.
Choose a path
Learning paths
Learning path
Agent Performance
Understand tool-call execution, cache behaviour, retries, and trajectory evaluation in stateful AI agents.
View curriculumLearning path
AI Systems Foundations
Understand the components of an AI application and the boundaries between models, retrieval, tools, and production services.
View curriculumLearning path
Evaluation & Benchmarking
Design measurements that distinguish speed, quality, retrieval effectiveness, and reliable agent execution.
View curriculumLearning path
Local LLM Inference
Run and measure open-weight models locally, connecting quantization, hardware limits, latency, throughput, and output quality.
View curriculumLearning path
Model Internals
Connect model execution, token generation, context, and KV-cache behaviour to memory use and serving performance.
View curriculumLearning path
Production AI Infrastructure
Build reliable AI services through explicit system boundaries, policy, validated outputs, durable execution, evaluation, and workload admission.
View curriculum