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.
41Tutorial // AgentsWe Open-Sourced an AI Agent for Coverage Citations: And Broke It Twice2026-07-30→42ComparisonsAI Agent Memory: Mem0 vs Zep vs Letta2026-07-29→43Insights // DevelopmentThe AI Coding Tools Stack: Why Teams Run Cursor, Claude Code, and Copilot Together2026-07-29→44Tutorial // Agentsagent-for-accounting: An Open-Source AI Agent for Bank-to-Ledger Reconciliation2026-07-28→45AI EngineeringAI Coding Agents in Large Codebases: Why Repository Intelligence Beats a Bigger Context Window2026-07-27→46ComparisonsClaude Opus 5 vs Grok 4.5 vs Muse Spark 1.1: Which Agentic Model to Use in 20262026-07-26→47AI EngineeringClaude Opus 5 Batch API Tutorial: AI Contract Data Extraction at Scale, with Real Costs2026-07-25→48AI EngineeringClaude Opus 5 Effort Parameter Guide: How to Reduce Claude API Costs Without Switching Models2026-07-25→49AI EngineeringHow to Build a Long-Running AI Agent with the Claude Opus 5 API: An Overnight Build Log2026-07-25→50AI EngineeringHow to Handle Claude Opus 5 Refusals in Production: stop_reason, stop_details, and the Fallbacks Parameter2026-07-25→51AI EngineeringGrok 4.5 API Review: Pricing, Performance, and When to Use It Instead of Claude2026-07-25→52AI EngineeringGrok Voice API Tutorial: How to Build a Realtime AI Voice Agent for Customer Support2026-07-25→53AI EngineeringHow to Build a Multilingual AI Voice Agent with Grok Voice: Hindi, Spanish, and 20+ Languages2026-07-25→54AI EngineeringHow to Connect an AI Voice Agent to a Real Phone Number: Grok Voice SIP Setup and Cost Breakdown2026-07-25→55AI EngineeringMeta Model API Tutorial: How to Get Started with Muse Spark 1.1 (Pricing, Setup, First Agent)2026-07-25→56AI EngineeringHow to Migrate to the Claude Opus 5 API: Breaking Changes, 400 Errors, and a Production Checklist2026-07-25→57AI EngineeringHow to Build a Computer Use Agent with Muse Spark 1.1: Cross-Application Workflows That Actually Finish2026-07-25→58AI EngineeringMulti-Agent Orchestration with Muse Spark 1.1: How Subagent Delegation Actually Works in Production2026-07-25→59AI EngineeringContext Engineering for AI Agents: Managing the Context Window in Production2026-07-24→60AI EngineeringHow to Evaluate a New LLM in 48 Hours: The Shadow-Mode Playbook2026-07-23→