Vercel 推出面向 Agent 用户的 Evals 工具
Vercel 发了个给 agent 时代用的评测工具,能看 agent 怎么调你的产品、上线前跑回归测试、新模型出了还能横向对比。做 API 或 MCP 工具给 agent 用的开发者会需要,比纯人工验收省事。
Vercel 在 X 上发布了一条简短公告,主题是"你的下一批用户是 agent",并推出配套的 Evals 工作流。该工具提供三项能力:观察 agent 如何实际使用你的产品、在上线前测试改动、在新模型发布时进行对比评测。公告未公布定价、基准名称或具体参数数据。
其核心逻辑是把评测(evals)从模型侧转移到产品侧:当调用你 API 或使用你工具的不再是人类而是自动化 agent 时,回归测试的对象变成模型版本和 agent 行为。Vercel 建议开发者在每次发布前跑评测,并在 OpenAI、Anthropic、Google 等新模型上线时横向比较。
这条内容本质是功能预告而非技术报告,具体实现细节需参考其链接页面。对给 agent 提供 MCP/工具接口的开发者来说,这是值得关注的工作流方向;但对纯业务方信息量有限。
Your next users are agents. Evals are how you build for them.
▪︎ See how agents use your product ▪︎ Test changes before you ship ▪︎ Compare models as they launch
https://t.co/gommDmzUvE
This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Vercel, Evals, MCP and tools, agents.
Source attribution: curated from Vercel AI (@vercel). Cross-source corroboration: 11 independent sources have covered this development (including Aravind Srinivas, 掘金本周最热, shao__meng), confirming industry-wide signal strength.