Walk through a draft together
Planned: talk an employee through what is wrong with a document while it sits on the screen in front of you, instead of writing out where each problem is.
Talk to Your Employee on Video
In-App Video is a planned channel for live, face to face video calls with an AI employee, camera and microphone, directly inside the workspace. It has no working implementation today: it appears in Settings > Technical > Channels as a Coming soon placeholder only. Once it ships, it is meant to run on the same execution pipeline as every other channel, so the employee keeps its skills, tools, training, and conversation memory on a video call. If you need an employee in a live call today, it can already join a Google Meet, Zoom, or Microsoft Teams meeting as a participant, which is a different capability and available now.
In-App Video is the planned way to sit down with an AI employee face to face, camera and microphone, without leaving the workspace. It is on the roadmap and has no working implementation today: open Settings, then Technical, then Channels, and In-App Video appears under In-App as a Coming soon card with no camera, no microphone, and nothing to configure. This page describes the intended shape so you can judge whether it matters to you, not something you can switch on this afternoon.
The reason to build it is presence. Typing is efficient for a clear request and slow for a messy one, and some work is easier to talk through than to write out: walking a draft, arguing about a plan, explaining what you actually meant. A live conversation surface inside the workspace keeps that exchange next to the work being discussed.
What will not change is who you are talking to. Video is planned as another way in, running the same execution path as every other channel, so the employee brings the skills you attached, the duties it always follows, the tools it can reach, the training you uploaded, and the memory of every earlier conversation. Nothing about a call makes it a thinner employee, and the exchange lands in the same history as your typed conversations.
One thing is worth being clear about, because the names sit close together. In-App Video is you meeting an employee inside Sistava. Joining a Google Meet, Zoom, or Microsoft Teams call is a separate capability, and that one already works: your employee can sit in a real meeting with real people, listen the whole way through, speak when you address it by name, and write a summary afterwards. If what you need is an employee in a meeting today, that is the answer.
Nothing is lost by waiting. Employees, skills, duties, training, and memory belong to the employee rather than to a channel, so the day video ships the employee you already built is ready to appear on it with everything it has learned intact. Until then, web chat carries the same employee and the meeting capability covers live calls.
A Conversation Surface, Not A Second Product
The plan is for video to reuse the same real time pipeline the in-app voice channel is built on, which is why it is described as a channel rather than a feature of its own. Sound and picture are a way of carrying a message, and everything behind the message stays where it already is.
That is also why the roadmap position can be stated plainly. The parts a video call needs, the employee, its memory, its tools, its approvals, are already built and already used by every other channel. What is missing is the live surface on top of them.
What It Will Not Change
Guardrails do not relax because a conversation is spoken. Anything an employee must check with you before doing still stops and asks, and anything it is not allowed to touch stays out of reach, on video exactly as in text.
The record does not thin out either. Work that comes out of a call belongs in the same place as work that comes out of chat, so a decision made out loud can still be found later by someone who was not there.
What You Can Do Today
Web chat is the live surface and every employee answers on it. For anything that genuinely needs a live call, paste a Google Meet, Zoom, or Microsoft Teams link and the employee joins as a participant, or add its email address as a guest on a calendar event so it turns up when the meeting starts.
That covers most of the reasons people ask for video: an employee present in a real conversation, hearing what was said, and writing it up afterwards. In-App Video is the other direction, a call with your employee rather than a call it attends alongside you.
How It Works
Planned: camera and microphone into the same employee, nothing else changes
When it ships, In-App Video is expected to be managed from Settings, then Technical, then Channels, the same page every other channel lives on, and switched on for the employees you want to reach that way.
A call would carry your camera and microphone to the same employee that answers your typed messages. Speech becomes text on the way in and the reply comes back as speech, which is how the planned voice channel is meant to work as well.
Everything after that is unchanged. The employee uses its skills, tools, and memory, pauses for approval where it must, and the conversation is written into its history so the call never becomes a hole in the record.
Use Cases
Think out loud about a decision
Planned: argue a plan through with an employee the way you would with a colleague, then let the conclusion land in its memory and on the board.
Explain something messy quickly
Planned: some requests are faster said than typed, and a live call is the shortest route from a half formed idea to work that has actually started.
Get an employee into a real meeting today
Available now, and the closest thing to video: paste a Meet, Zoom, or Teams link and the employee joins the call, listens throughout, speaks when addressed, and writes a summary afterwards.
Comparison
| Before | After |
|---|---|
| Explaining what is wrong with a draft means typing out where each problem sits. | Planned: talk it through on a call while the employee holds the document and its memory. |
| A live discussion happens in a meeting tool and the notes never make it back. | Planned: the conversation runs inside the workspace and lands in the employee's history. |
| Getting an employee into a real meeting sounds like it needs video first. | Available now: paste a Meet, Zoom, or Teams link and it joins the call as a participant. |
| A new channel usually means configuring the assistant all over again. | Skills, training, tools, and memory belong to the employee, so video changes nothing you built. |
FAQ
Can I have a video call with my AI employee today?
No. In-App Video is on the Sistava roadmap and has no working implementation yet: it shows in Settings, then Technical, then Channels as a Coming soon card with no camera or microphone connection. Web chat is the live conversation surface today, and an employee can already join a Google Meet, Zoom, or Microsoft Teams call as a participant.
Where do I find In-App Video in the app?
Settings, then Technical, then Channels, in the In-App group, listed as In-App Video with a Coming soon badge. There is no Manage drawer, no toggle, and no activity on the card while the channel is unbuilt.
Is this the same as my employee joining a Zoom or Google Meet call?
No, and the difference matters. Joining a meeting is a separate capability that works today: paste a Meet, Zoom, or Teams link, or invite the employee's own email address to a calendar event, and it attends, listens, speaks when addressed by name, and writes a summary afterwards. In-App Video is the planned reverse, a call with your employee inside the workspace.
Will a video call share memory with my chat conversations?
Yes, that is the intended design. Memory belongs to the employee rather than to a channel, so anything said on a call would be available in web chat afterwards, and anything discussed in chat would already be known on the call.
Will I need to install anything for video when it launches?
No install is planned. The channel is designed to run inside the workspace in your browser, using the camera and microphone you grant that page, which is why it is grouped with the other In-App surfaces rather than with external apps.
What should I use for live conversation while video is unavailable?
Web chat is available now for every employee, and the meeting capability covers real calls: an employee can join a Google Meet, Zoom, or Microsoft Teams meeting as a participant. The in-app voice channel is also still on the roadmap, so it is not an alternative today.
Will I have to set anything up again when video ships?
No. Skills, duties, training, tools, and memory belong to the employee rather than to a channel, so switching video on will not mean rebuilding anything. The employee you use in chat today is the one that would appear on a call.
Where Talk to Your Employee on Video fits
Talk to Your Employee on Video is part of Ways you talk to them.
Chat in the app with live reasoning, speak to your AI voice agent over a call, message on Slack or WhatsApp, send an email, or embed a widget on your website. Every channel connects to the same AI agent with the same memory and capabilities. Switch channels mid-conversation and your employee picks up right where you left off.
- Ways you talk to them: Every channel. One conversation.
Read the guide
More in Channels
- Web Chat: Chat with any AI employee directly in the workspace, with a streaming reply, a live execution timeline showing what it is reading, thinking, and doing, and inline approve/reject buttons when it needs a sensitive action confirmed. It is the default channel: nothing to configure, works on desktop or mobile, and every conversation persists so you can pick it back up later.
- Voice Calls: Voice Calls is a planned channel for speaking to an AI employee out loud and hearing it reply in real time, instead of typing. It is not available yet: there is no voice button in the workspace today, and the feature is paused while the underlying voice flow is redesigned. When it ships, a voice call will run through the same skills, tools, and memory as a typed conversation.
- Connect an Email Provider: Point your own SendGrid, Mailgun, or Postmark inbound-parse webhook at a tenant-scoped endpoint and every email that lands there gets turned into work for an employee. Forward support requests, sales inquiries, or internal approval emails and the employee reads the sender, subject, and body, then acts on it in the background. You get a 202 response immediately; there's no waiting on the request.
- Personal Mailbox: Every employee gets its own email address on the shared Sistava domain the moment you hire it, no setup. Email it directly, CC it on a thread with other people, or forward something over, and it reads and replies within seconds. Free to send from, with a monthly cap by plan. Control the shared employee signature in Company Profile, or connect your own Gmail or Outlook when you want it sending as you, with no cap.
- Send from Gmail or Outlook: The built-in employee address is free and always on, but it sends as the employee, not as you. Connect your own Gmail or Outlook instead and an employee sends and replies from your real address, in your name, with no monthly sending cap on any plan.
- Chat Widget: The Chat Widget will let you embed an AI employee directly on your public website so visitors can ask questions and get answers without leaving the page. It is on the roadmap and is not available to configure yet: today it appears in Settings > Technical > Channels as a Coming soon placeholder with no setup, embed snippet, or Manage action.
- SMS: SMS is a planned channel for reaching an AI employee by ordinary text message, with no app to install. It is on the roadmap and not available today: there is no SMS number, no inbound texting, and no way to turn it on yet. Until it ships, use web chat or Telegram for mobile access from any phone.
- WhatsApp: WhatsApp is a planned messaging channel for talking with an AI employee from your phone. It is not connected yet: the card shows as coming soon and cannot be set up today. When it ships, it will carry the same employee memory, skills, and guardrails as web chat, Telegram, Slack, and the mailbox. Telegram and Slack are live now and give you the same access from a phone, so nothing you set up today has to be rebuilt when WhatsApp arrives.
- Discord: Discord is a planned channel for bringing an AI employee into the servers and direct messages your community already uses. It will connect the same way Slack does today: authorize a bot through OAuth, then map it to one employee. It is not available to connect yet, so no Discord traffic reaches an employee until it ships. Slack, Telegram, each employee's own email address, and web chat cover the same job in the meantime.
- Calendar Invites: Add your employee's personal address as a guest on any Google, Outlook, or Apple calendar event and they show up for the meeting automatically, no RSVP or extra app on your side. Once the meeting starts, the employee joins the Meet, Zoom, or Teams call, listens, speaks when addressed, and writes a summary afterward. There is nothing to switch on for the invite itself, just turn on the Meeting Attender tool for that employee once.
- Slack Channel: Bring your AI employee into Slack as a real bot user your team can mention, DM, or trigger with a slash command. Every reply lands in the same thread, and memory, tasks, skills, and tools stay shared with web chat, so a conversation started on Slack continues anywhere else. You approve or reject requests right from Slack, and the bot only speaks when mentioned, DM'd, or already in a thread.
- Telegram Channel: Connect an AI employee to its own Telegram bot so you can message it from your phone the same way you message a person. It answers direct messages instantly, and joins group chats where it replies only when mentioned or replied to. Memory, tasks, and tools are shared with the web app, so a conversation started on Telegram picks up right where it left off on the desktop, and back again.