Evals 进阶指南：Hamel Husain 与 Shreya Shankar 联手发布续篇
做了 50+ 家 AI 公司评测的两位作者出了续篇，Ramp、Shopify、Cursor 怎么靠 evals 降本增效都写了，还送个插件。
Lenny Rachitsky 邀请 Hamel Husain 和 Shreya Shankar 撰写评测（evals）体系的进阶续作，两人此前服务过 50+ 家 AI 公司。文中引用多个实际收益案例：Ramp 把自动收据识别准确率从 35% 提到 83%，Shopify 的 AI 工作流构建器比原前沿模型方案快 2.2 倍且便宜 68%。Harvey 重构 AI 合同审查器后内部质量分接近翻倍，Cursor 调优 Auto Balance 路由，在成本降低 41% 的同时用户满意度更高。文章覆盖多数团队跳过的关键步骤、哪些环节该自动化，并附一个让编码 Agent 干重活免费插件。Lenny 还提到上周分享的 25 个 PM 职位中近半要求有写 evals 的经验。
Evals have been coming up more and more in my conversations with podcast guests and PM friends. Nearly half of the 25 awesome PM job openings I shared last week ask for experience writing evals. And leading companies keep sharing what investing in evals bought them: — @tryramp took its automatic receipt collection from 35% to 83% accuracy. — @Shopify shipped an AI workflow builder that's 2.2x faster and 68% cheaper than the frontier-model setup it replaced. — @harvey__ai rebuilt its AI contract reviewer, nearly doubling its internal quality score. — @cursor_ai tuned its Auto Balance routing, with much higher user satisfaction at 41% lower cost. So I asked the 🐐s of evals, @HamelHusain and @sh_reya , to write an advanced sequel to their very popular "Building eval systems that improve your AI product." Drawing on their work with 50+ AI companies, they share the key step most teams skip, what you should (and shouldn't) automate, and a free plugin that lets a coding agent do most of the heavy lifting. Read it here: lennysnewsletter.com/p/advanced-eva… F 💬 23 🔄 12 ❤️ 148 👀 17456 📊 65 ⚡
