Tag
The author criticizes the hype around autonomous AI agents, stating they are often ineffective, and recommends building practical, hardcoded AI workflows using tools like n8n and Claude Sonnet for real-world applications.
Graph engineering is a new term for coordinating multiple AI agent loops using graphs of nodes (work units) and edges (control flow). The article explains the concept, its historical context (LangGraph, AutoGen, etc.), and the real challenges of designing such graphs.
The article argues that AI coding should use specialized agents in loops with bounded retry and human approval, rather than a single super-agent, emphasizing workflow engineering over agent intelligence.