Scan your website to see how ready it is for AI agents. We check multiple emerging standards — from robots.txt and Markdown negotiation to MCP, OAuth, Agent Skills and agentic commerce.
大多数人认为网站优化主要是针对搜索引擎和人类用户，但作者认为网站需要专门为AI代理(agent)准备，这挑战了传统的网站优化观念。文章提出了一系列新兴标准，如MCP、Agent Skills等，表明未来的网站交互将不再局限于人类浏览，而是需要与AI系统进行复杂交互。
AI-generated designs break brand standards because agents can't see your design system.
这一观点揭示了当前AI设计工具的核心缺陷：生成的UI虽然技术上可行，却无法遵循品牌规范，导致设计系统的一致性被破坏。这表明AI与设计系统整合的必要性，以及当前AI设计工具与实际设计实践之间的脱节。
Each platform surfaces different vulnerabilities, making it difficult to establish a single, reliable source of truth for what is actually secure.
这一观察揭示了AI安全工具的碎片化问题，不同AI平台发现的漏洞各不相同，导致难以确定真正的安全状态。这种不确定性不仅增加了防御难度，还可能引发安全评估的混乱，需要建立新的行业标准来应对AI时代的安全挑战。
Add llms.txt metadata and root/package LICENSE files - Add website llms.txt support and move LICENSE to root - Fix llms.txt serving and restore package LICENSE
令人惊讶的是：这个项目支持llms.txt元数据格式，这是一种新兴的AI可发现性标准，使AI模型能够更好地理解项目文档和代码结构。这种关注AI可发现性的做法表明项目开发者不仅关注当前功能，还前瞻性地考虑了AI与代码库的交互方式。
What has changed, what remains the same, and what general patterns can be discerned from the past twenty years in the fast-changing field of edtech?
Join me in annotating @mweller's thoughtful exercise at thinking through the last 20 years of edtech. Given Martin's acknowledgements of the caveats of such an exercise, how can we augment this list to tell an even richer story?