按风险花 token 的 AI 代码审查流水线。 面向 AI 编码工具的「写完代码后」审查 harness：先做轻量预检，按变更风险推荐 Lite / Standard / Full，再调度对应专家。配套健康分、HTML 看板、handoff 接力、双语 Playbook、基线棘轮与 CI 集成。

Design mode — build a new self-running agent / loop / background worker. Review mode — audit an existing loop's stopping conditions, guardrails, verification, and escalation paths. It distills 12 ...

Loop Engineering 被视为继 Prompt Engineering、Context & Harness Engineering 之后的"AI 编程第三次革命"——开发者角色从"提示词工程师"彻底升级为"AI 系统架构师"。 Loop Engineering 是由谷歌工程师 Addy Osmani 提出的 AI 编程新范式。其核心理念是：围绕大模型构建自主循环运行 ...

On Friday, Claude Code creator Boris Cherny made an appearance at Meta’s @Scale conference and, surprisingly, the first question from the audience was about loops. “Are loops the next hype cycle,” the ...

Loop Engineering 是由谷歌工程师 Addy Osmani 提出的 AI 编程新范式。其核心理念是：围绕大模型构建自主循环运行系统，使 AI 从单次响应工具升级为长期自治代理。 在传统的 AI 辅助开发中，开发者与 AI 的交互模式是"一问一答"——你发一条指令，AI 回复一次，然后 ...

Anthropic Product Manager and Anthropic engineer Boris Cherny in a video introducing Claude Code on Feb 24, 2025. Anthropic.com Anthropic's Boris Cherny has stopped writing prompts. The creator and ...

为了让 AI 写出更准确的代码，我们不断优化提示词：先描述技术栈，再补充项目背景，接着规定修改范围，最后列出测试要求和输出格式。一条原本只有几十个字的需求，逐渐变成了一份几百字甚至上千字的工程任务单。 Prompt 工程还没学会，Loop Engineering 已经 ...

You're currently following this author! Want to unfollow? Unsubscribe via the link in your email. For the most powerful voices in AI, it's all about being in the loop. Claude Code creator Boris Cherny ...