<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>DogXAI</title><description>记录思考，分享实践，探索 AI、Agent 与软件工程。</description><link>https://dogxai.pages.dev/</link><language>zh-CN</language><item><title>从 ChatGPT 到 Agent：下一代人机协作范式</title><link>https://dogxai.pages.dev/blog/from-chatgpt-to-agent/</link><guid isPermaLink="true">https://dogxai.pages.dev/blog/from-chatgpt-to-agent/</guid><description>从问答模型走向能够规划、调用工具和验证结果的 Agent，拆解真正可落地的人机协作系统。</description><pubDate>Mon, 14 Sep 2026 00:00:00 GMT</pubDate><category>AI</category><category>Agent</category><category>Engineering</category></item><item><title>我如何用 Claude + Astro 重构个人知识库</title><link>https://dogxai.pages.dev/blog/claude-astro-knowledge-base/</link><guid isPermaLink="true">https://dogxai.pages.dev/blog/claude-astro-knowledge-base/</guid><description>把散落的 Markdown、项目笔记和研究材料变成可搜索、可版本化、可持续演进的知识系统。</description><pubDate>Thu, 10 Sep 2026 00:00:00 GMT</pubDate><category>Engineering</category><category>Astro</category><category>Knowledge</category></item><item><title>RAG 实战：构建企业级知识问答系统</title><link>https://dogxai.pages.dev/blog/rag-enterprise-qa/</link><guid isPermaLink="true">https://dogxai.pages.dev/blog/rag-enterprise-qa/</guid><description>从检索、切分、重排到评估，梳理一个 RAG 系统从 demo 走向生产环境必须补齐的工程环节。</description><pubDate>Sun, 06 Sep 2026 00:00:00 GMT</pubDate><category>LLM</category><category>RAG</category><category>Engineering</category></item></channel></rss>