Event ·Multi-source

Hamel Husain 与 Shreya 推出进阶 evals 技能包,可让编码智能体代做大部分工作

Lenny Rachitsky 推荐 Hamel Husain 和 Shreya Shankar 发布的进阶 evals 技能包,是他们此前热门课程《Building eval systems that improve your AI product》的续作。内容基于两人与 50+ AI 公司的合作经验,讲解大多数团队跳过的关键步骤以及哪些环节该自动化、哪些不该。配套一个免费插件,能让编码智能体承担大部分搭建 evals 的工作。文中案例包括 Ramp 把自动收据收集准确率从 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、省 68% 成本,Harvey 重建 AI 合同审查器后内部质量分接近翻倍,Cursor 调优 Auto Balance 路由后成本降 41%。

Current read

做 AI 产品必看,Hamel 和 Shreya 把踩坑经验做成免费技能包,让编码智能体帮你搭 evals,Ramp 和 Cursor 都靠这招降本增效。

11 sources73° AI heatLast updated 2026/9/22 18:27:37

Evidence

11 sources
Primary sourceLenny Rachitsky
View source
Related source 2Hamel Husain
View source
Related source 3shao__meng
View source
Related source 4eric zakariasson
View source
Related source 6arXiv: OpenAI
View source
Related source 9AWS Machine Learning Blog
View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.