Resources
Short on purpose: the resources the school itself produces and stands behind. Reading paths per workshop, the public code library, and the channels where new work appears first.
Reading paths
RAG SystemsFreshness, chunking, reranking, retrieval quality. The failure modes nobody demos and every production system has.Agent EngineeringTool loops, budgets, circuit breakers, confirmation gates, memory you can inspect. Agents you can bound are agents you can trust.Evals & ReliabilityCanary evals, LLM-as-judge failure modes, and the monitoring that tells you the system broke first.AI System DesignThe design interviews test and production demands: latency budgets, cost routing, failure design, scale.Data Engineering for AIPipelines, embeddings at scale, data quality. AI systems are data systems with a model attached.
The library
ai-school-369-projectsEvery project from every edition, MIT licensed. Start with rag-freshness and agent-tool-loop; both run offline in minutes.The interview pack100 questions with model answers, free with the newsletter. The fastest interview preparation the school makes.
Stuck on a production problem that is not covered yet? Reader problems become future builds. Tell us here.