docs.json, search across your entire repository, and manage dashboard settings.
The editor agent makes changes directly in your current branch.
Open the agent
Click Ask agent in the editor toolbar, or press Cmd + I (macOS) or Ctrl + I (Windows). To close the panel, click the X button in the panel header or press Cmd + I again.Send a message
Type your request in the chat box at the bottom of the panel and press Enter or click the send button. Type @ to mention a specific page. The agent focuses on that page when processing your request. If you don’t mention a page, the agent uses the page you currently have open. Example prompts:simplify the introduction pagefix all grammar errors across my contentadd a new page that explains authenticationrename every mention of "Acme Pro" to "Acme Team" across all pagesupdate docs.json to add a new group called "Guides"
Attach files
Click the paperclip icon in the chat box, or drag and drop files onto the panel. The agent reads attached files as context for your request. Supported file types:- Images: JPG, PNG, GIF, WebP, SVG
- Documents: PDF
- Code and text:
.js,.ts,.jsx,.tsx,.mdx,.md,.json,.yaml,.html,.css, Python, Go, Rust, Ruby, Java, Swift, C, C++, SQL, shell scripts, and more
Add a selection to the agent
In visual mode, select text on a page. A floating toolbar appears over the selection. Click Add to agent to send the selected text to the agent as context.Review what the agent changed
As the agent edits your pages, a Changed files panel appears in the chat. Expand it to see a list of every file modified in the session. Click any file to open it in diff view and compare the agent’s changes against the original.What the agent can do
Edit pages
The agent can write, rewrite, expand, and reorganize content on any page. It reads your existing content to match your style and structure.Search and navigate your content
The agent can search across your entire repository, not just the page you have open. Use it to find information, check for inconsistencies, or verify that content exists before adding it.Update navigation and docs.json
The agent can add, rename, reorder, and delete navigation elements, the same changes you’d make manually in the navigation panel. It can also updatedocs.json configuration directly, including adding new groups, adjusting settings, and configuring redirects.
Example: add a "Quickstart" group under the Getting Started tab and move the quickstart page into it
Run bash commands
The agent can rungrep, rg, and other bash commands against your repository. Use this for bulk operations that span many files.
Example: find every page that mentions the deprecated /v1/auth endpoint
Work with private pages
If you have access to private pages, the agent can read and edit them from the private pages root. Use this when you need to review or update content that should not appear in your public navigation. Private pages are available in the editor without an additional feature flag. Your role and page grants still determine what you can access and change. You can open the agent from the private page editor. The agent button is hidden for users with the viewer role. Private navigation refreshes when the agent or another editor changes the private page tree. You can also right-click the Private section header in the sidebar to create a private page or folder if you have permission to create them. When the agent works with a private page, its tool activity labels show the page title instead of the UUID-based filename. When you open a private page, the editor toolbar shows an Edited label with how long ago the page was last edited. The label updates after you edit the page. Private pages use UUID-based filenames. Start by listing the private pages, then read or edit the file you need:@ in the composer to search for private pages by title. Private pages appear in the mention picker with the label Private page. After you select one, its chip does not link to the private page. The agent resolves the mention to its UUID path and includes only pages you can access.
To create a private folder, use a human-readable title as the final path segment. The folder appears under a new private-folder-<uuid> path after you list the directory again:
/home/daytona/private, use mv to reparent a private page or folder into another private folder. The item keeps its UUID-based name. Manager access is required. You cannot rename pages or move a folder into itself:
/home/daytona/private is not supported.
To duplicate a private page, use cp with a human-readable title as the final path segment. The copy appears under a new private-page-<uuid>.mdx path after you list the directory again:
/home/daytona/private and /home/daytona/workspace are not supported.
You can also delete a private page if your role allows it. Manager access is required for deletion. To make a private page public, move it into the workspace:
Configure your site (code mode)
For requests that go beyond editing pages (setting up authentication, managing workflows, or changing deployment settings), the agent switches into code mode. It writes and runs a script against your Mintlify dashboard on your behalf. Code mode respects your dashboard permissions. If you don’t have access to a setting in the dashboard, the agent can’t change it either. Example prompts that use code mode:enable JWT authentication for my sitecreate a workflow that updates my site when I merge a PRadd a custom domain
Continue an automation run
When you open the editor from a completed automation run by clicking View changes, the agent panel opens automatically with context on what the automation did. A Changed pages card at the top of the chat lists every page the automation modified. Click any page to open a diff view. The agent has context on the automation’s prompt, a summary of the changes it made, and which pages it modified. You can ask it to refine or extend the automation’s work without re-explaining the background. For example:The new section on rate limits is too long. Trim it to three sentences.