loop-engineering

This article discusses the concept of agentic loops for automating work with AI, providing eight tips for writing quality loops, and introduces loop engineering as a method to reduce developer bottlenecks by designing systems that prompt agents automatically.

Claude Code head Boris Cherny proposes that AI programming is shifting from prompt engineering to Loop Engineering. In the future, developers' core task will be designing automated loops rather than writing prompts—a trend that could level the development playing field.

An explanation of loop engineering for AI agents, emphasizing the separation of maker and checker agents, state persistence on disk, and exit conditions to avoid runaway costs.

Claude Code v2.1.172 adds sub-agent nesting capability, supporting up to 5 layers of nesting. It allows lower-level agents to automatically generate sub-agents to handle complex sub-tasks, and introduces usage scenarios, configuration methods, and common pitfalls.

Loop Engineering will completely replace Harness Engineering in the coming months, becoming the hottest paradigm in AI.

This article introduces the concept of Loop Engineering, which involves designing automated systems that allow AI agents to work in autonomous loops, including elements such as automated tasks, work trees, skills, plugins, and sub-agents, thereby replacing manual prompting and improving development efficiency.

A 14-step roadmap on loop engineering, guiding developers from manually prompting AI coding agents to designing automated systems that handle the prompting, verification, and iteration themselves.

The post discusses loop engineering for AI agents and introduces Opik, an open-source tool from Comet ML that provides debugging, evaluation, and optimization for generative AI applications, with a focus on automating failure handling and building regression tests from real failures.

This article explores the view that in the Agent era, Loop Engineering is more important than Prompt Engineering. The author believes that the core capability of an AI Agent lies not in the model itself, but in the feedback loop system built around the model, which determines whether the Agent can continuously improve and approach the correct answer.

Loop Engineering is replacing the direct way of writing prompts for agents, focusing on designing a system to write prompts for the agent.

This article introduces the concept of Loop Engineering — instead of directly writing prompts for AI agents, it designs a system (loop) that recursively lets the agent iterate on tasks until completion. The article provides a detailed comparison of how Claude Code and Codex implement five building blocks: automations, worktrees, skills, sub-agents, etc. It suggests this could be the future trend of collaborating with coding agents, but also warns about token costs and AI slop issues.

Explains the shift from prompt engineering to loop engineering, where AI agents are given goals and iterate through recursive loops (research, draft, evaluate, test, improve) until meeting standards, with open, closed, and orchestrated looping approaches.

LoopX is an open-source, agent-agnostic local control plane for managing long-running AI agent work, providing durable state for objectives, gates, todos, evidence, quota, and handoffs across tools like Codex, Claude Code, and Cursor.

Loop engineering is a new approach to working with AI coding agents where you design automated loops that prompt and manage agents instead of prompting them directly. The concept involves five building blocks—automations, worktrees, skills, plugins, and sub-agents—plus external memory, and is already implemented in tools like Claude Code and Codex.