Prompt Engineering Is Dead. Loop Engineering Is Here.

Prompt engineering is being replaced by loop engineering, a practice where AI systems generate, evaluate, and improve their own work until meeting a goal. Engineers at Anthropic and OpenAI are now designing loops that prompt AI agents autonomously, marking a shift in how AI workflows are built.

Member-only story Prompt Engineering Is Dead. Loop Engineering Is Here. Learn what Loop Engineering is, why it matters, and how AI engineers are building autonomous agent workflows. A clip went viral in June 2026 and stopped a lot of engineers cold. Boris Cherny https://thenewstack.io/loop-engineering/ — creator and head of Claude Code at Anthropic — told interviewers that his job had changed: “I don’t prompt Claude anymore. I have loops running that prompt Claude and figuring out what to do. My job is to write loops.” The same week, OpenAI engineer Peter Steinberger https://letsdatascience.com/news/engineers-embrace-loop-engineering-for-ai-agents-cb1a1d6a posted: “You shouldn’t be prompting coding agents anymore. You should be designing loops that prompt your agents.” Then Google engineer Addy Osmani https://cobusgreyling.substack.com/p/loop-engineering gave the pattern a name: loop engineering. “ Prompt engineering is dead ” started trending. This article explains what loop engineering actually is, what changed, and why it matters for the future of building with AI. Loop engineering is the practice of designing AI systems that generate, evaluate, and improve their own work until they meet a predefined goal.In one sentence: