Field Notes, 152 Articles
Notes from the foundry
Engineering essays on generative AI, retrieval systems, and what it takes to ship intelligent software to production.
141AI // RetrievalRAG Is Not a Silver Bullet · It's a Retrieval Problem2026-05-29→142Insights // HiringHow to Evaluate an AI Development Partner2026-05-22→143Insights // ArchitectureVendor Lock-In with LLMs: How to Keep Providers Swappable2026-05-15→144Insights // CostCutting LLM Cost 50% Without Wrecking Quality2026-05-08→145Insights // CostWhat It Really Costs to Run an LLM Feature in Production2026-05-01→146Insights // InfrastructureShould We Self-Host an LLM? A Cost and Control Framework2026-04-24→147Insights // ArchitectureRAG vs Fine-Tuning vs Long Context: Which, and When2026-04-17→148Insights // StrategyWhen AI Is the Wrong Tool (and Cheaper Options Win)2026-04-10→149Insights // ProductionThe AI Readiness Checklist Before You Ship to Customers2026-04-03→150Insights // ProductHow to Scope an AI MVP That Won't Get Thrown Away2026-03-27→151Insights // PlanningEstimating Timeline and Budget for an AI Build2026-03-20→152Insights // EvalsMeasuring AI Quality: Evals Your Board Will Trust2026-03-13→