Original post · AI translation
他们的官方公告博客。
网站开始看起来像一组可调用的操作，而这正是智能体希望看到的网站形式。
AgentWeb 刚刚发布，它让 AI 智能体无需浏览器就能完成网站任务：智能体不用读取截图和点击按钮，而是调用一个预先做好的操作。
这些数据确实扎实：在 15 个政府门户网站、7 家保险公司的网站，以及亚马逊和 LinkedIn 等 25 个需要登录的网站上，47/47 项实时任务全部完成；中位耗时 1.9 秒，整轮运行花费 3 美元。
AgentWeb 将每项已映射的任务作为工具开放，附带输入模式、前置条件、权限边界和完成证明，任何助手都可以调用。
Original
A website is starting to look like a set of callable operations, which is exactly how an agent wants to see it. AgentWeb just launched and it lets AI agents do website tasks without a browser: instead of reading screenshots and clicking buttons, the agent calls a ready-made action. The numbers are actually solid. 47/47 live tasks across 15 government portals, 7 insurers and 25 signed-in sites like Amazon and LinkedIn, 1.9s median, $3 for the whole run. AgentWeb exposes each mapped task as a tool with an input schema, preconditions, an authority boundary and a completion proof, callable from any assistant.
推出 AgentWeb：面向通用智能体的可靠网络基础设施。
在真实网站上完成 47/47 项真实世界任务。中位耗时 1.9 秒。总花费 3 美元。
申请使用权限：https://t.co/KsgVebkvLT https://t.co/tscylNwiZQ
Original
Introducing AgentWeb: reliable web infrastructure for generalized agents. 47/47 real world tasks on live sites. 1.9s median. $3 total. Request access: https://t.co/KsgVebkvLT https://t.co/tscylNwiZQ