# Glean：企业AI栈中模型最可替代，统一索引才是核心

- 来源：Rohan Paul (@rohanpaul_ai)
- 发布时间：2026-08-06 02:25
- AIHOT 分数：37
- AIHOT 链接：https://aihot.virxact.com/items/cmsgfljee04aaro5qxn0n9ykw
- 原文链接：https://x.com/rohanpaul_ai/status/2085069733666472184

## AI 摘要

Rohan Paul 认为模型是企业AI栈中最可替代的部分，更难构建的是知道“有什么、谁能访问、如何连接、任务该查哪个源”的系统层。Glean 正构建跨应用统一索引层，在推理前保留权限、元数据、作者、活动信号和实体关系，并用记忆跨会话传递学习、连接器选择检索路径、工具让智能体执行操作。

## 正文

The model is probably the most replaceable part of an enterprise AI stack.

The harder asset is the system that knows what exists, who can access it, how it connects, and which source each task should query.

That is the layer @Glean has been building .

They think enterprise AI needs a unified index across applications, with permissions, metadata, authorship, activity signals, and entity relationships preserved before inference begins.

It built one cross-application layer that preserves entity relationships, permissions, authorship, activity signals, and metadata.

Memory carries learning across sessions, connectors pick the retrieval path per source, and tools let the assistant act on what it finds.

### 引用推文

> Tony Gentilcore：http://x.com/i/article/2082479542653108224