<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>AI Agent on RekCore</title><link>https://rekcore.com/tags/ai-agent/</link><description>Recent content in AI Agent on RekCore</description><generator>Hugo -- gohugo.io</generator><language>zh-cn</language><copyright>© 2026 RekCore</copyright><lastBuildDate>Wed, 06 May 2026 16:00:00 +0800</lastBuildDate><atom:link href="https://rekcore.com/tags/ai-agent/index.xml" rel="self" type="application/rss+xml"/><item><title>别把 Skill 写成 Prompt：工业级 AI Agent Skill 的七个设计原则</title><link>https://rekcore.com/tutorials/2026-05-06-industrial-skill-design/</link><pubDate>Wed, 06 May 2026 16:00:00 +0800</pubDate><guid>https://rekcore.com/tutorials/2026-05-06-industrial-skill-design/</guid><description>AI Agent Skill 不是 Prompt 的加长版。本文从按需加载、工具边界、模型选择、渐进式披露、验证迭代五个维度，拆解如何写出真正能在生产环境稳定运行的工业级 Skill。</description></item><item><title>Feynman 实战：用 AI Agent 半小时搞定一篇文献综述</title><link>https://rekcore.com/tutorials/2026-05-06-feynman-tutorial/</link><pubDate>Wed, 06 May 2026 14:30:00 +0800</pubDate><guid>https://rekcore.com/tutorials/2026-05-06-feynman-tutorial/</guid><description>Feynman 实战教程：一行命令安装，三步完成配置，分别演示深度研究（deepresearch）、文献综述（lit）和论文审计（audit）三个核心工作流，附带本地模型和云 GPU 的配置方法。</description></item><item><title>Feynman：把学术研究搬进终端的 AI Agent</title><link>https://rekcore.com/projects/2026-05-06-feynman-research-agent/</link><pubDate>Wed, 06 May 2026 14:00:00 +0800</pubDate><guid>https://rekcore.com/projects/2026-05-06-feynman-research-agent/</guid><description>发现一个叫 Feynman 的开源 AI 研究助手，6.5k Star。不是普通的搜索增强，而是能做文献综述、论文审计、实验复现的终端 Agent。四个内置 Agent 分工协作，搜索论文用 alphaXiv，GPU 实验跑 Modal/RunPod，所有结论都带来源链接。</description></item><item><title>OPC 实战：如何用 Hermes 搭建多 Agent 协作团队</title><link>https://rekcore.com/tutorials/2026-05-06-opc-multi-agent-collaboration/</link><pubDate>Wed, 06 May 2026 14:00:00 +0800</pubDate><guid>https://rekcore.com/tutorials/2026-05-06-opc-multi-agent-collaboration/</guid><description>详解 Hermes 多 Profile 协作架构：为什么一个 Agent 不够、Profile/Subagent/Project/Wiki 四个概念怎么区分、Coordinator/Researcher/Writer/Builder 四角色模型如何搭建。</description></item><item><title>AI Agent 动不动就翻车？六层 Harness 架构让你告别玄学调参</title><link>https://rekcore.com/tutorials/2026-05-06-harness-engineering-six-layers/</link><pubDate>Wed, 06 May 2026 12:00:00 +0800</pubDate><guid>https://rekcore.com/tutorials/2026-05-06-harness-engineering-six-layers/</guid><description>AI Agent 频繁跑偏、死循环、成功率卡在 70%？北大博士后卢菁和一线团队的经验表明，真正的瓶颈是 Harness——模型外面的运行系统。本文详解六层架构设计。</description></item><item><title>别再死磕 Prompt 了：2026 年 AI 工程化的真正战场在哪？</title><link>https://rekcore.com/tutorials/2026-05-06-beyond-prompt-engineering/</link><pubDate>Wed, 06 May 2026 11:00:00 +0800</pubDate><guid>https://rekcore.com/tutorials/2026-05-06-beyond-prompt-engineering/</guid><description>很多团队做 AI Agent 效果不好就疯狂改 Prompt，但问题往往出在上下文和框架层。本文拆解 AI 工程化的三个阶段，帮你定位 Agent 拉胯的真正原因。</description></item></channel></rss>