As agents are generating more and more documents, they need a better agent-native document format ...
TL;DR · AI 摘要
当前主流文档格式如Markdown和HTML各有缺陷，亟需一种更适合AI代理协作的新型文档格式。
核心要点
- Markdown易于人类阅读但缺乏丰富的视觉输出和交互性。
- HTML提供更丰富的视觉输出，但对人类编辑不友好且占用大量token。
- 理想的AI代理文档格式应支持人类与AI的协作、版本控制和权限管理。
结构提纲
按章节快速跳转。
- §引言
当前AI代理生成文档的需求日益增长，但缺乏合适的文档格式。
Markdown易于人类阅读和编辑，但缺乏丰富的视觉输出和交互性。
HTML提供丰富的视觉输出，但对人类编辑不友好且占用大量token。
理想的文档格式应支持人类与AI的协作、版本控制和权限管理。
思维导图
用一张图看清主题之间的关系。
查看大纲文本（无障碍 / 无 JS 友好）
- AI代理文档格式需求
- 当前文档格式问题
- Markdown的缺点
- HTML的缺点
- 理想文档格式特征
- 支持人类与AI协作
- 版本控制
- 权限管理
金句 / Highlights
值得收藏与分享的关键句。
Markdown: Easily readable/reviewable by humans, but lacks rich visual output/interactivity
HTML: Providers richer visual output, but on its own is hard to edit by humans, and is token intensive.
An ideal agent-native document format is a surface area like Microsoft Word/Google Docs that both humans and agents can easily collaborate on.
Jerry Liu on X: "As agents are generating more and more documents, they need a better agent-native document format 🤖📄 So far the two main containers are markdown and HTML: 1️⃣ Markdown: Easily readable/reviewable by humans, but lacks rich visual output/interactivity 2️⃣ HTML: Providers richer https://t.co/FRQlCFNzUg" / X
Jerry Liu
@jerryjliu0
As agents are generating more and more documents, they need a better agent-native document format 🤖📄 So far the two main containers are markdown and HTML: 1️⃣ Markdown: Easily readable/reviewable by humans, but lacks rich visual output/interactivity 2️⃣ HTML: Providers richer visual output, but on its own is hard to edit by humans, and is token intensive. An ideal agent-native document format is a surface area like Microsoft Word/Google Docs that both humans and agents can easily collaborate on: ✅ Good for human-review/human-editing ✅ Good for agent-review/agent-editing ✅ Supports needed features like versioning and permissioning I touched on this during my Databricks talk this past week. There’s still a massive amount of human knowledge stored in PDFs, Powerpoints, Word that we are handling via LlamaParse, but at the same time we need to innovate on the way that agents are creating and collaborating on information.
7:11 PM · Jun 20, 2026
14K
Views
2
3
23
1
6
16
8
128
113
Read 23 replies