# Your assistant's own place

> Your assistant has a screen of its own rather than a chat, keeps every conversation, can look inside the apps you can open, lets you archive old ones, and answers a shortcut from anywhere.

Your assistant is not a chat, so asking it something does not leave a chat
behind. It has a screen of its own instead, at /omni. The chevron left of the
bolt at the top takes you back to Home, or leave it the way you leave any other
screen, by going somewhere else in the sidebar.

That screen opens by itself when you send from the question box, so you can
watch the answer arrive. To go back to an older one, open it from the list on
Home or the Omni tab in the left sidebar. See [Your sidebar, your lists and your settings](https://bolter.chat/help/your-sidebar-and-settings) for
the rest of that sidebar.

A conversation shows in bold in the sidebar when your assistant has something
for you in it: a reply that landed after you moved on, or the welcome it sends
a new account. It goes back to normal once you have read what is waiting.

## What makes it different from an agent

Four things are easy to miss. It is yours alone and acts as you, completely private and
invisible to everyone else unless you approve an individual message or
invitation it drafts; it can see across every chat, agent, workspace and file
you have access to, and nothing you could not open yourself; anything it would
send or change comes back to you as a card to approve first;
and it is on every screen, a keyboard shortcut away, whether you want data
pulled out, something set in motion, or an explanation of the screen in front
of you.

Your assistant is deliberately not presented like one of your agents. It has no
picture and no badge, only the same green bolt that marks it in the sidebar,
its name, and a line saying what it is, because it is not a teammate you set
up. It is your own reach into everything you can already get to, and it can see
exactly what you can see and nothing else.

Each conversation with it opens with the short form of that explanation. At
the top, above the first message, is the bolt and the assistant's name, a line
saying it is your assistant and private to you, a few short sentences on how it
differs from an agent (your agents are teammates you add to chats, this one
cannot join a chat but can read every chat you can, it helps with review and
analysis and drafts messages or actions, and it asks before it sends or
changes anything), the line that this is the start of a new request,
and a View profile button. It stays above the first message for the life of the
conversation and scrolls away with the history, like the introduction at the
top of a chat with one of your agents. On a long conversation the two behave
differently. An agent chat waits until you have scrolled back to the first
message before showing its introduction, because scrolling up there loads more
of the history. Your assistant's screen keeps only the most recent stretch, so
it shows the block right away, without the line about this being the start.
New request and the list of earlier requests are in the header above it, not
repeated in the block.

Conversations with your assistant have no threads. Its answers always arrive in
the conversation itself, and if you ask it to reply in a thread it will say
threads are not available there and answer in the conversation instead. Threads belong to chats, where the thread panel is;
see [Your sidebar, your lists and your settings](https://bolter.chat/help/your-sidebar-and-settings) for how those work.

## Asking about work that lives in an app

Your assistant can look inside the apps you can open, in any workspace you belong to, and it sees exactly what you would see there. Ask "what was I working on in CodePilot" or "what is on the board in the planning app" and it lists your apps, reads the one you mean, and answers from what the app holds right now. You can also paste an app's address into the conversation.

It reads only. It will not change anything in an app for you, and it tells you when an app cannot be read this way, which happens when the app does not offer a typed interface. Nothing is granted to the assistant: if you lose access to an app, so does it.

## Asking whether you have been invited

Your assistant sees the invitations waiting for you: invitations into
workspaces, with the sender, the role and the expiry date, and invitations into
conversations, with the sender and the account each is addressed to. Ask it
whether anyone has invited you to join their workspace, or what invitations are
waiting, and it answers from that list, with a link to each invitation's card
on the Requests page, where Join and Decline are. The same invitations sit
under the Invitations heading of the sidebar list, and workspace ones also
under Invitations on the Settings page. It does not accept or decline for you.

## Finding a conversation you have already had

Every conversation you have had is kept, and there are two ways in. The
Omni tab in the left sidebar lists every one of them. On Home, the clock icon
in the question box, next to the paperclip and the microphone, opens the
assistant's screen with the same list already dropped open; on a phone the
clock sits on its own row of previous requests under the question box
instead, and that row opens the list on a page of its own. Once you are on
the assistant's own screen, you switch conversations from the title at the
top, which is itself the switcher: the chevron beside it drops the list open
under the title rather than taking over the screen, so what you were reading
stays put and anything you had started typing is still there when you close
it.
Conversations are listed newest first and titled by what they were about. The
sidebar's Omni tab groups them under the same time headings as the rest of the
sidebar, Today, Yesterday, This week and Before this week, so you can see at a
glance where one day's requests end and the previous day's begin. While the
sidebar shows everything, they are also mixed in with your chats on its All
tab. Opening one picks it
straight back up: you can carry on from where it stopped. Leaving the
assistant's screen and coming back, or reloading the page, returns you to the
conversation you were last reading rather than to the newest one. Opening the
list to look through it does not count as reading one, so a glance at your
history leaves that unchanged. "New request", on the assistant's own screen,
takes you to the question box on Home with the cursor already in it. Nothing is
created until you actually ask something, so pressing it and changing your mind
leaves no empty conversation behind. Asking a new question from the question
box always starts a fresh conversation, which is what keeps the history worth
reading.

## Archiving a conversation

Conversations you are done with can be put away from the list of your
conversations on Home on a phone: open a conversation's menu and choose
Archive. It leaves the list and stops counting towards your assistant's unread
badge. It is not deleted. Archived conversations are not listed in Settings
under Archived, since that page holds chats and your assistant's conversations
are not chats.

## Asking your assistant from anywhere

You do not have to be on Home to ask. Press Cmd+Enter (Ctrl+Enter on
Windows) from anywhere and a question box opens over the middle of the screen.
It behaves like the Home box: each question starts its own new chat with your
assistant, so an ask typed from a dashboard or a settings screen never gets
appended to an unrelated conversation.

The shortcut does the same thing everywhere now, including inside a chat.

The same keys put the box away again. Press the shortcut a second time while
the question box is open and it closes, the way the × on the box does.
Anything you had typed is still there when you open it again.

If you have set Enter to start a new line rather than send, plain Cmd+Enter is
your send key, so the assistant shortcut moves to Cmd+Shift+Enter
(Ctrl+Shift+Enter on Windows). That version works whichever way the setting is
set, so it is the safe one to learn.

Pressing it while you are reading a chat brings that conversation with it: the
box shows the chat's name, and your assistant can read it while it answers.
Take the name off if the question is about something else, with the × beside
it or by pressing Escape once; a second Escape closes the box. Inside your
assistant's own screen there is nothing for it to open, so it takes you to Home
with the caret in the "What's next?" box, ready for the next request. Shift+Enter
is still the way to start a new line in that message box.

The box stays open when you send, and a small panel appears under it saying
what is happening to the question you just asked: your assistant working, and
then its reply once it lands. Click that panel to open the conversation and
read the whole answer. If the reply comes with something for you to approve,
such as a message to send or an agent to create, the panel splits into two
tabs: Actions, showing the cards waiting on you, and Message, showing what your
assistant said. It opens on Actions. Once you have approved or skipped the
cards, the tabs go away and the panel is the reply again. Close the box with
the x in its top right corner, with Escape, or by clicking away from it. The conversation is waiting in your
assistant's history either way, and it shows in bold in the left sidebar once
the reply lands, until you have read it.

The Ask Omni action on a single message opens that same box, with the message
quoted inside it. Hover a message and press the bolt, or pick Ask Omni from the
menu you get by right clicking it. The question lands the same way the shortcut
does: it starts its own new chat with your assistant and carries the chat the
message came from with it, so asking about the call you have just finished does
not turn up underneath last week's question. Selecting part of a message before
you press it quotes only that part.

So on a computer every question to your assistant goes through the one box,
whatever you were doing when you thought of it. The
message box of a chat is for that chat. On a phone there is no left sidebar, so
asking about a message switches the chat's own message box into asking your
assistant instead, and swiping a message to the left does the same.

When you ask about a quoted message, your assistant can attach a private
insight to that message for you to revisit. Only you can see that card. A reply
draft is separate and waits for your approval before it is sent to the chat.

When you ask your assistant for an agent that does a specific job, its card
shows two things: the agent's personality, which it follows on every turn, and
the first message, which your assistant writes from your request and sends as
you once you tap Create agent. The new agent's chat opens with that message,
marked as sent by your assistant, and the agent starts on it straight away, so
you do not have to explain the job a second time. An agent asked for with no job
in mind yet has no first message and introduces itself instead.

An agent your assistant creates in a team workspace is shared with everyone in
that workspace, and the card says so before you tap Create agent. Ask for one
only you can use and it is created private instead. An agent in your personal
workspace is always private. See [Agents, ownership, and visibility](https://bolter.chat/help/agents) for what each access level means.

You can ask your assistant to remember a preference for future requests, such
as how you like meeting summaries structured. Ask what it remembers when you
want to check or correct that context. See [Memory and the Wiki](https://bolter.chat/help/memory) for how saved memory
differs from your conversation history.

Source: https://bolter.chat/help/your-assistant