Field Notes, 157 Articles
Notes from the foundry
Engineering essays on generative AI, retrieval systems, and what it takes to ship intelligent software to production.
141Tutorial // WorkflowsBuild a Durable Multi-Step Workflow with Claude Opus 4.82026-06-16→142Tutorial // EvalsAdd an Eval Harness to Your LLM App2026-06-16→143Tutorial // DevToolsBuild a Code Completion Backend with Codestral2026-06-15→144Tutorial // AgentsBuild a Multi-Agent Workflow with LangGraph2026-06-15→145Tutorial // DevToolsBuild an AI Code Review Bot for Your Pull Requests2026-06-14→146AI // RetrievalRAG Is Not a Silver Bullet · It's a Retrieval Problem2026-05-29→147Insights // HiringHow to Evaluate an AI Development Partner2026-05-22→148Insights // ArchitectureVendor Lock-In with LLMs: How to Keep Providers Swappable2026-05-15→149Insights // CostCutting LLM Cost 50% Without Wrecking Quality2026-05-08→150Insights // CostWhat It Really Costs to Run an LLM Feature in Production2026-05-01→151Insights // InfrastructureShould We Self-Host an LLM? A Cost and Control Framework2026-04-24→152Insights // ArchitectureRAG vs Fine-Tuning vs Long Context: Which, and When2026-04-17→153Insights // StrategyWhen AI Is the Wrong Tool (and Cheaper Options Win)2026-04-10→154Insights // ProductionThe AI Readiness Checklist Before You Ship to Customers2026-04-03→155Insights // ProductHow to Scope an AI MVP That Won't Get Thrown Away2026-03-27→156Insights // PlanningEstimating Timeline and Budget for an AI Build2026-03-20→157Insights // EvalsMeasuring AI Quality: Evals Your Board Will Trust2026-03-13→