Field Notes, 127 Articles
Notes from the foundry
Engineering essays on generative AI, retrieval systems, and what it takes to ship intelligent software to production.
101Tutorial // Frontend AIBuild a Streaming AI Chat UI with the Vercel AI SDK2026-06-21→102Tutorial // AgentsBuild a Multi-File Refactor Agent with GPT-5.52026-06-20→103Tutorial // Document AIBuild a PDF Data Extraction Pipeline with an LLM2026-06-20→104Tutorial // DevToolsSpin Up Sandboxed Subagents with the Antigravity CLI2026-06-19→105Tutorial // MCPBuild an MCP Server to Connect Claude to Your Database2026-06-19→106Tutorial // InfrastructureSelf-Host an Open-Weight Coding LLM with vLLM2026-06-18→107Tutorial // SearchBuild a Semantic Search Engine with Embeddings and Qdrant2026-06-18→108Engineering // LLMsShipping Generative AI Features Without Breaking Production2026-06-18→109Tutorial // Voice AIBuild an AI Voice Agent with Twilio and a Realtime Model2026-06-17→110Tutorial // MCPHow to Build an OAuth-Secured MCP Server (TypeScript Tutorial)2026-06-17→111Tutorial // WorkflowsBuild a Durable Multi-Step Workflow with Claude Opus 4.82026-06-16→112Tutorial // EvalsAdd an Eval Harness to Your LLM App2026-06-16→113Tutorial // DevToolsBuild a Code Completion Backend with Codestral2026-06-15→114Tutorial // AgentsBuild a Multi-Agent Workflow with LangGraph2026-06-15→115Tutorial // DevToolsBuild an AI Code Review Bot for Your Pull Requests2026-06-14→116AI // RetrievalRAG Is Not a Silver Bullet · It's a Retrieval Problem2026-05-29→117Insights // HiringHow to Evaluate an AI Development Partner2026-05-22→118Insights // ArchitectureVendor Lock-In with LLMs: How to Keep Providers Swappable2026-05-15→119Insights // CostCutting LLM Cost 50% Without Wrecking Quality2026-05-08→120Insights // CostWhat It Really Costs to Run an LLM Feature in Production2026-05-01→