Inside a call
How a Nebula call is laid out — the stage, agent postures, the work board, the chat and recap rail, and the transcript waiting for you afterwards.
Inside a call you talk, show things, and watch work land — all in the same room. The stage reflows around whatever matters most at that moment, so you rarely have to arrange anything yourself.
The stage
Everyone on the call sits on an orbit ring. The call's agent rides its owner's tile as a small companion avatar rather than standing there as a stranger of its own — and if its owner isn't on the call, it takes a tile by itself. The ring fills the room when nothing else is competing for it, shifts to the top while dispatched work is running below it, and compacts to a strip when a screenshare or camera takes the floor.
Along the bottom, the controls bar holds your mic, speaker, camera, and share — each a split pill, where the icon toggles and the caret opens its options. Leave sits at the far end of the same bar.
The speaker pill's two halves do different jobs. The caret picks which device call audio plays through. The toggle mutes the agent, and only in your ear — everyone else on the call stays audible, and they keep hearing the agent normally. Mute your mic and the agent both and the bar reads chat mode: you type, the agent answers in text, and the room carries on around you.
Chat mode isn't a switch you flip — it's what the call calls you once your mic and the agent are both muted.
Active and background agents
An agent on a call sits in one of two postures, and you can flip it between them at any point without interrupting the conversation.
| Active | Background | |
|---|---|---|
| One-on-one with you | Answers every turn of the conversation | Never speaks — replies in text when you address it |
| Group call | Stays out of the room's back-and-forth and speaks when addressed | Never speaks — replies in text when you address it |
| Listening & working | Yes | Yes |
| Best when | You want it in the conversation | You want it on the work but out of the audio entirely |
Active reads the room instead of making you manage it. On your own with an agent it answers every turn, which is what you want when you're thinking out loud. Add other people and the same posture holds back on its own — it stays out while you and your teammates work something through, and speaks up when the conversation turns to it. You don't have to summon it formally: its name or a wake word always works, but simply talking to it is usually enough. When it can't tell whether a question was meant for it or for the person next to you, it stays quiet rather than talking over anyone. Nothing to switch when the group grows, and nothing to switch back when it shrinks.
Background is a hard mute. The agent keeps listening and keeps doing the work you hand it, but it won't say a word out loud — not even when you call it by name. Anything it has to tell you lands as text in the chat rail instead. Reach for it when you want an agent on the job without a voice in the room.
To change a posture, click the agent's avatar to toggle between the two, or open the Voice mode menu on its tile.
You rarely need to touch this in a group call — an active agent already stays out of the way until someone addresses it. Switch to background when you want it working with no voice at all.
There are two ways to quiet an agent, and they differ in who they apply to.
| Mute the agent | Background posture | |
|---|---|---|
| Where | The speaker toggle in the controls bar | The agent's avatar, or its Voice mode menu |
| Who stops hearing it | Just you | Everyone on the call |
| Does it still speak | Yes — to everyone else | No — not to anyone |
| Best when | You want quiet without changing the call for others | The room wants the agent working, not talking |
What the tile is telling you
Beyond the posture, a tile shows what its agent is doing right now.
| State | Meaning |
|---|---|
| Listening | It's here and attending the room, waiting for something to do |
| Thinking | It's working out its reply |
| Writing | Its answer is arriving right now |
| Searching | It's looking something up in your workspace |
| Working | It's running a tool for you |
| Dispatching | It's handing work to a specialist; watch for a card on the board |
Speaking isn't in that list because it doesn't need to be — when the agent talks, its ring moves with its voice, so you can see who's speaking without reading a label.
If a call loses its connection, the agent's state freezes where it was rather than flipping to something new. A stalled label is the signal that the room dropped, not that the agent changed its mind.
Asking about your workspace
Not everything you say needs to become work. Ask about something that already exists in your workspace and your agent just answers, out loud, in the same breath — no thread, no hand-off, no waiting.
What does the research agent actually do? And is the nightly sync job still running?
The research agent handles competitive briefs and market summaries. The nightly sync ran at 2am and finished clean.
It can look across threads, agents, jobs, and miniapps this way. The dividing line is knowing versus doing: questions get answered on the call, and only genuinely new work gets dispatched to a specialist. When it does dispatch something you asked for, it says so — a quick "on it" — rather than going silent while you wonder whether it heard you.
Your teammates' and agents' names are fed to the transcriber before the call starts, so unusual names come out spelled right instead of turning into something phonetically close.
Bringing someone else in
If you realise mid-call that you need someone, just say so — your agent can pull a teammate in by name without you leaving the room.
We need Priya for the billing part — can you get her on here?
Invited Priya Raman — she'll get a join notification now.
Your agent matches the name against your workspace directory, so a first name is usually enough. If two people could match, it asks which one you meant before inviting anyone. Because inviting reaches outside the room, your agent says out loud what it did rather than doing it silently.
The invite arrives as a notification that opens the live call when clicked — it doesn't ring anyone. Someone already on the call won't be pinged again. You can also invite from the call's own invite dialog if you'd rather pick people from a list.
Showing your agent something
Two ways to put something in front of your agent mid-call, each with a page of its own.
Sharing your screen
Show what's on your computer — a dashboard, an error, a document — and ask what it says.
Live camera
Turn on your webcam and hold something up. Good for labels, hardware, and whiteboards.
Either one takes the stage, compacting the people into a strip beside it. In both cases your agent looks when you ask rather than watching continuously, and answers in the same turn.
Putting a thread on screen
It works the other way too. Ask your agent to pull up a thread and it puts that thread on the stage for everyone — no screen sharing, no hunting for a link.
Pull up the Q3 pricing thread so everyone can see it.
Got it — putting the Q3 pricing thread on screen now.
The thread appears as a shared screen with a chip saying who's sharing it, showing the conversation and any files in it — stripped of the activity chrome so it reads cleanly from across a room. One thread at a time: pull up another and it takes the place of the first.
Pulling a thread up shows it to everyone on the call, and closing it puts it away for everyone too — it isn't a private view. Anyone without access to that thread sees a note that it's been pulled up rather than its contents, so permissions still hold.
Say put that away to clear the stage, or use the X on the shared screen. A live screenshare or camera outranks a pulled-up thread, so starting one takes the stage back.
The work board
When you and your agent agree on something to do, it dispatches the work to a specialist and a card appears on the board — right there in the room, below the people.
The cards are the same ones from your Home feed, with the same statuses: live while it's working, unread once a result is waiting, then read. You can cancel, mark read, or archive without leaving the call.
The board sits under the people whenever work is live, and disappears when there's none.
Chat and recap
The right rail keeps a Work section at the top — the threads dispatched from this call, with a badge for results you haven't read — and two tabs below it.
The conversation as a feed — everything spoken plus anything typed, with your agent's activity folded inline. There's a composer at the bottom, so someone who can't talk can still take part.
The call's shape as it builds — the topics you've covered, the decisions you've reached, and the questions still open. It updates while you talk, so you can glance at it to see where you've got to.
On a narrow screen the rail steps out of the way and the header's Call / Chat tabs swap between the two.
Live captions
Speech turns into captions as people talk, attributed by name. Captions correct themselves in place — a line may re-attribute to the right speaker once there's enough audio to be sure, so don't be surprised to see one shift as it settles.
After the call
Hang up and the room doesn't disappear — it settles. You get the same layout at rest: the tiles go static, and the recap takes the floor where the people were.
The recap reads like a good meeting note — what you covered, what you decided, and the work that came out of it — about half a page for a short call and a page for a long one. Nebula resolves every speaker to their real name first, so it reads like minutes rather than a machine dump.
The rail carries the call's numbers — duration, messages, threads, and people — over two tabs.
The recap in detail, the threads the call kicked off, and who was there.
Every turn, attributed by speaker. Download saves it as a plain text file you can keep or paste elsewhere.
Nebula also saves the transcript and recap as files on the call's thread, so they're reachable from the channel's Sessions section later. And Start again opens a fresh call seeded from the same thread, so a recurring conversation doesn't need setting up twice.
The recap takes a moment to appear after you hang up — it shows up once Nebula finishes writing it.
Related
Live
Start a live voice session with Nebula and your teammates from Home, a thread, or a channel — talk it through while agents work in the background.
Sharing your screen
Share your screen on a Nebula call and ask your agent what it sees — read an error, pull text off a stack trace, or talk through a dashboard together.