Ramp Glass 用共享知识层统一数据、人员与智能体
Every company I’m aware of is either building or seeking to buy something that places their data, people, and agents on the same page.
Ramp 的 Glass 在任意模型前加一层共享可编辑的公司知识层，包含定义、已保存的 Skills 以及 Linear、Notion、Google、Slack、Gong 的连接，使每个员工的会话都读取同一份修正后的定义。Glass 按设计可换模型，同时支持开源与闭源模型，Ramp 的立场是更好模型一发布就切换。
查看原帖https://t.co/SGu5SRww1P
正文
当前显示原文，中文全文译文尚未就绪。
Every company I’m aware of is either building or seeking to buy something that places their data, people, and agents on the same page.
Ask a model how many U.K. customers your company has added, and it will probably count U.S. companies that have U.K. offices.
Ramp’s Glass got that question right because Finance had corrected the definition months earlier. The correction sits in a shared knowledge layer that every employee’s session reads from.
It puts a shared, editable layer of company knowledge in front of whichever model you run: definitions, saved Skills, and connections to Linear, Notion, Google, Slack and Gong.
The model is swappable by design. Glass runs open or closed models, and Ramp’s position is that you switch the day a better one ships.