<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>DeepEval on AI 实战派 · 从技术到赚钱</title><link>https://guijiagi.com/tags/deepeval/</link><description>Recent content in DeepEval on AI 实战派 · 从技术到赚钱</description><generator>Hugo</generator><language>zh-cn</language><copyright>本站内容采用 CC BY-NC-SA 4.0 国际许可协议授权</copyright><lastBuildDate>Fri, 09 Oct 2026 12:18:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/deepeval/index.xml" rel="self" type="application/rss+xml"/><item><title>把 LLM 评测写进 pytest：DeepEval 让每次改提示词都有据可查</title><link>https://guijiagi.com/posts/2026-10-09-14-deepeval-pytest-ci/</link><pubDate>Fri, 09 Oct 2026 12:18:00 +0800</pubDate><guid>https://guijiagi.com/posts/2026-10-09-14-deepeval-pytest-ci/</guid><description>提示词一改就翻车，是因为没有回归集。本文用 DeepEval 把评测做成 pytest 用例，接进 CI，每次改动自动跑黄金集。</description></item></channel></rss>