Imagine your team deployed Prompt A globally two weeks ago. Tight deadlines and high confidence meant the rollout hit 100 percent of users without any A/B testing, shadow traffic, or holdout groups. W

It's tempting to treat loop engineering as something invented in a single week in June, but the mechanics behind it are closer to five years old, and knowing the lineage is what separates a real...

Most prompt engineering tutorials follow the same shape. Install the SDK, paste your API key, call generateContent, and print the response. The model says something plausible and the tutorial ends. Th

Today, Elastic announced that it has entered into an agreement to acquire Deductive AI, an AI-powered investigation platform that helps engineering teams identify and resolve production issues faster.

Public AI assistants have become so commonplace that software vendors are increasingly adding AI search, conversational experiences, and AI agents The post Is retrieval engineering becoming AI’s...

Platform engineering is evolving Platform engineering has become one of the defining disciplines of the cloud native era. As organizations embraced Kubernetes, microservices, GitOps, and...

仅仅火了两个月的“Loop Engineering（循环工程）”正面临被颠覆的命运。近期，硅谷技术圈正在被“Graph Engineering（图工程）”的新范式引爆。本文基于两篇重磅长文，深度拆解了这一转变的必然性：简单的单点循环极易陷入 Goodhart...

一句话：所谓 Loop Engineering，其实是把组织管理的老规律，用 AI 时代的新语言重新说了一遍。 又一个新词，但说的好像是件老事 AI 圈造词的速度真的快。前两年大家还在背 Prompt Engineering 的技巧，刚把思... 浅谈 Loop Engineering 与组织运作的相似性最先出现在XINDOO。

Platform engineering has won the argument. Some 90% of organizations have adopted at least one internal platform; golden paths are The post Platform engineering’s new job: serving environments at...

本文讨论了提升Agent系统稳定性与效率的方法，强调“循环工程”取代传统的“提示词工程”。Karpathy提出九条黄金法则，如角色分离、状态持久化和合同协商，旨在使Agent独立运行并交付可用产品。通过优化设计，开发者能够更有效地管理复杂性，消除不确定性，推动AI技术进步。

复利工程通过将学习成果沉淀到知识库中，提高后续工作的效率。它强调在执行前进行充分的评审和计划，以确保知识的持续积累。使用STRATEGY.md作为项目核心指导，复利工程帮助AI Agent在每次启动时自动获取上下文，避免重复错误，提升工作效率。

本文探讨了循环工程的概念，强调从手动提示代理转向设计自动提示系统。通过自动化、工作树、技能、连接器和子代理等五个要素及记忆，循环实现自主运行。Boris Cherny和Peter Steinberger的实践展示了循环如何提高代码产出和效率。循环的成功依赖于验证机制，以确保代理输出的质量。

Harness Engineering 关注安全有效地构建 AI Agent，通过设计控制系统（如编排循环、工具系统和安全护栏）确保模型在执行任务时的安全性和可控性。Claude Code 是目前最完整的 Agent 产品，具备多层次的安全机制和灵活的配置管理。不同平台（如 Codex 和 Pi）在设计上各有侧重，适应不同应用场景。