Using the app

Agents

An agent is a saved assistant with its own instructions, folders and permissions. The chat picks the right role by itself; an agent always does the same job, the way you decided, and remembers its conversations.

GalleryCreating and editingWorking with an agentToolsConfirmationsLogGranted foldersMCP servers

The Agents page: your agents at the top, the gallery below.
The Agents page: your agents at the top, the gallery below.

Four ready-made agents. Create asks for the folder they will work on and the agent is ready right away.

AgentWhat it does
File assistantFinds, reads and summarizes the documents in a folder and answers questions about their content.
Document organizerProposes an order for a messy folder and, if you agree, creates the folders and moves the files. It deletes nothing.
Coding assistantReads and changes a project's code and can run builds and tests, always asking you first.
Mail assistantFinds, reads and summarizes your emails and writes replies as drafts. It sends only when you ask, and shows you the message first every time. On creation, the editor opens so you can link the account.

Create an agent from scratch → opens an empty editor.

Creating and editing an agent

An agent's editor: name, description, instructions, granted folders and permissions.
An agent's editor: name, description, instructions, granted folders and permissions.
FieldWhat it is for
Name, DescriptionHow you recognize it in the list.
InstructionsWhat it must do and how. A few clear rules work better than a long text, especially with small models.
Granted foldersThe only folders the agent sees. The first is where it starts. At least one is required.
Can run commandsTurn it on only for agents that need it, like the coding assistant. Every command is shown to you first.
PermissionsThe actions you allowed forever for this agent, each with Revoke.
MCP serversExternal tools to connect: see MCP servers.
EmailThe email accounts the agent may use: see Email.
  • Save applies the changes; Cancel discards them.
  • Delete agent asks for a second click and also deletes its conversations (the action log stays).
  • Each agent is a readable JSON file: Open the agents folder shows them, so you can back them up or share them.

Working with an agent

The tidy-up agent has created the folders and asks for permission to move the first photo.
The tidy-up agent has created the folders and asks for permission to move the first photo.
  • Describe the task in your own words. The agent shows the steps it takes (Looks at the folder, Reads, Moves…); a click on a step shows its result.
  • For risky actions it stops on the confirmation card: Allow, Always allow for that kind of action, or Don't allow.
  • At the top, the name of the folder it works on: a click opens it in File Explorer.
  • New chat starts over; the Conversations tab on the right reopens past ones, and the agent finds the earlier questions and answers.
  • Open conversations stay alive when you switch pages: when you come back you find them where you left them.
  • Long conversations are compacted as in the chat; type /compact in the message box to summarize right away. See Long conversations.

What an agent can do

ToolWhat it does
Looks at the folderLists files and folders (up to 500 entries at a time).
ReadsOpens text files, PDFs (page by page) and Word documents (.docx). Long files are read in parts, about a quarter of the model's context at a time, continuing from where the reading stopped: a long PDF no longer fills the whole context. A PDF made only of images is reported as having no text.
Searches filesFinds files and folders by name (for example *.pdf or invoice*), subfolders included, and optionally only those containing a text, PDF and Word included.
WritesCreates a new text file or replaces its whole content.
EditsChanges just one piece of a text file, leaving the rest as it was (line endings and encoding included).
Creates a folderIncluding any missing folders in between.
MovesMoves or renames a file or a folder.
DeletesDeletes a file or an empty folder. The file doesn't vanish: it is set aside and can be restored.
Runs a commandOnly if the agent can run commands. The system command line, at most 2 minutes, not interactive: commands that wait for input stop by themselves.
Email toolsIf the agent has linked accounts: search, read, save attachments, write drafts, send. See Email.
MCP toolsThose offered by the connected MCP servers.

What asks for confirmation

ActionConfirmationCan be undone
Looking, reading, searchingNo—
Creating a file or a folderNoYes
Replacing or editing a fileYesYes (the previous version is restored)
Moving or renamingYesYes
DeletingYesYes
Running a commandYes, showing the commandNo
Using an MCP toolYes, showing the data it will receiveNo
Saving an email draftNoNo (you delete it from your email program)
Sending an emailAlways, with the full message to review and correctNo

Always allow applies to one kind of action and to that agent (for MCP tools, to the single tool); you revoke it from the editor. Sending email doesn't allow it: it asks every time.

Log and undo

The agent's log: folders created and photos moved, each with Undo.
The agent's log: folders created and photos moved, each with Undo.

The panel on the right lists everything the agent read, wrote or ran, including denied or failed attempts. Undo puts things back as they were: it deletes a created file, restores the previous content, brings a moved or deleted file back to its place.

Careful undo

If the file was changed again after the action (by you or by another program), undo stops and tells you: better not to undo than to erase later work.

Granted folders

Every path the model asks for goes through a check: it must stay inside a granted folder. For the agent, the rest of the disk doesn't exist. The check also holds against tricks: paths with .., links and junctions leading outside, hidden data streams and special Windows paths are refused, and the attempt ends up in the log. A granted folder itself cannot be moved or deleted by the agent.

MCP servers

MCP (Model Context Protocol) is an open standard for giving models external tools: memory, calendars, databases, web services. In the editor, under MCP servers, give the server a name and write:

  • a command to start, for example npx -y @modelcontextprotocol/server-memory, or
  • the address of a remote server (https://…).

At the start of the conversation the agent connects to its servers and lists their tools; if a server doesn't answer, it says so and carries on without it.

Caution

MCP servers are external programs that run with your permissions, outside the granted folders. Only add servers you trust. Each of their tools still asks for confirmation, showing you the data it is about to receive.

Models and agents

Smaller models use tools less reliably. For agents, a model marked Good for agents on the Models page is the better choice.

HotMoE is a Virsion project. This guide describes the app as it is today: what is still on the way is marked as such.