Xiaohongshu and Rokid have partnered on "Xiaohongshu Sweet Potato," which changes the starting point of the Personal Agent problem rather than offering a different solution to it, according to the article. The piece states that after Lingguang's recent publicity blitz, many people almost believed a local Chinese Muse had arrived that would outperform products from Alibaba and ByteDance, but real-world tests show its actual performance is far below expectations. Lingguang 2.0 can connect to systems and third-party services including calendar, alarm clock, Baidu Netdisk and QQ Mail, but authorization interfaces for high-frequency daily scenarios such as WeChat, Douyin, Xiaohongshu and Meituan are basically not open; even among Alibaba's own apps, only Alipay and DingTalk are interconnected. The article says the product direction is correct, but insufficient permissions make its experience far from satisfactory, and China's internet app ecosystem is dominated by closed "walled gardens." It notes Doubao mobile assistant once faced widespread resistance from a large number of applications, and the number of national-level applications Lingguang can deeply integrate with is also very limited. Lingguang takes "application generation" as its entry point but eventually hits existing boundaries of application distribution and digital service transactions; the article says these shortcomings cannot be eliminated by a single product iteration and represent the shared ceiling of building a smarter Agent inside a mobile phone dialog box, since permissions,