Everyone talks about AI agents. This is what one looks from the inside

大多数人工智能工具都位于您的知识库之外，等待您复制和粘贴。

Vault Operator lives inside it.它会读取您的笔记，遵循将它们联系在一起的图表，了解您的习惯，并代表您采取行动。

This page is the short tour.每个部分都链接到深入的指南。喜欢观看吗？

This 7-minute animated explainer walks through the agent from the inside: the loop, the harness with its five gates, tools, skills, and MCP, then one real job crossing every layer.您可以直接在正在阅读的笔记上进行聊天。

Select text, press Cmd+Shift+I (Ctrl+Shift+I on Windows and Linux) or right-click and pick "Inline AI chat", and a floating panel opens over the editor.

From there you ask a question about the selection, look something up, rewrite, translate, summarize, or extract action items without leaving the note.当专家组建议对文件进行更改时，首先打开 änderungen prüfen 模式。

You review each edit, apply only the ones you want, and the agent writes a checkpoint marker into the chat so you can undo the change later through the same checkpoint system used elsewhere in Vault Operator.将 PDF、Web 剪辑或 Office 文件放入聊天中。

Vault Operator runs a fast triage against your vault's ontology and, if you choose to ingest, walks you through a short dialog before it writes anything.由此产生的有意义的注释在每个声明的末尾都有一个 ↗ 链接。该链接跳转回源中的确切块。不再有“我在某处有关于此的注释”而没有返回声明来源的路径。

You drive this from chat in plain language: "Ingest this PDF" runs the quick single-pass capture, "Do a deep ingest of this paper" starts the deep path (triage, topic pick, source markup, sense-making note, backlinks).五步深度流程在每个问题处停止并等待着您。提示示例：“深入理解这篇研究论文。重点关注方法论部分。” Ask the agent to clip an article and it archives the page the way the Obsidian Web Clipper does: the full text converted to Markdown, the images downloaded into your vault with the links rewritten to local embeds, and a header the agent writes on top (frontmatter plus its own summary).这比 web_fetch 更进一步，后者将页面读取到对话中，将图像保留为远程 URL，并截断长文本。