# Ways you talk to them Every channel. One conversation. 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. Communication with your AI employees works the way you already communicate with your human team. Chat in the app with live streaming and visible reasoning. Call with voice for hands-free interaction. Send an email, a Slack message, or a WhatsApp text. The real power is that channels are interchangeable. Start a conversation over email in the morning, continue it in chat during the afternoon, and check results on Slack from your phone at night. Embed a chat widget on your website and visitors talk directly to your employees. Same skills, same memory, same capabilities. What you can switch on today already covers the ground most small teams need first. In-app chat is always on, so a new employee is reachable the moment you hire it. Every employee also gets its own working email address, which means you can write to it, copy it into a client thread, or forward something messy and ask for a summary. Slack and Telegram put that same employee inside the places your team already talks, and you can connect your own Gmail or Outlook when a reply needs to go out from your real address. Meetings and calendars are covered too. Invite an employee's email address to a Google, Outlook or Apple calendar event and it turns up when the meeting starts, follows what is being said, and speaks when someone addresses it. Nothing has to be installed on the call itself. When the meeting ends you get a written wrap-up from that same employee, so the hour becomes notes and next steps instead of a recording nobody replays. There is a programmatic side as well, for when the thing that needs to reach your employee is another system rather than a person. A REST endpoint lets your own software send it a message. An inbound webhook drops a payload straight into a conversation. An MCP endpoint lets other AI clients use your employee as a tool, and A2A support lets outside agents work with it directly. All of it runs on the same employee, with the same memory, alongside the human channels. Channels still being built are visible in the workspace before they arrive and are clearly labeled, so you always know what is real today. WhatsApp, SMS, Discord, Microsoft Teams, in-app voice and video, phone calls, an embeddable website widget and language SDKs are all on the way. When one of them goes live it appears in the same list, ready to switch on for the employees you already have, with nothing to rehire and nothing to rebuild. ## At a Glance - **5+** Communication channels - **1** Unified conversation - **0** Context lost between channels ## Benefits ### Live reasoning Every response streams word by word with visible reasoning. You see which tools the agent calls, what decisions it makes, and why. Stop or redirect mid-sentence if it heads the wrong direction. ### Any device, any channel Start a conversation in chat, continue it over email, and check results on Slack from your phone. Every channel connects to the same agent with the same memory. Context never resets. ### Agent delegation Leaders delegate to specialists through team chat. When a complex task crosses functions, agents hand off work to each other automatically. Every agent-to-agent conversation is visible in your activity feed. ## How It Works **Your AI employees meet customers and teammates wherever they are: in-app chat, voice calls, Slack, WhatsApp, email, phone, and embedded directly on your website.** The in-app chat shows your AI agent's live reasoning as it works, so you can follow along and understand exactly how it reached a decision. For real-time conversations, agents handle voice calls natively with low latency. You can also connect Slack and WhatsApp so your AI employee participates in the channels your team and customers already use daily. Embed a chat widget on any page of your website and your AI agent handles inbound inquiries instantly, with full knowledge of your products and policies. For phone support, AI agents take calls directly. Every channel uses the same agent brain, the same memory, and the same behavioral rules, so customers get a consistent experience regardless of how they reach you. Turning a channel on is a switch, not a setup project. Open the communications list, flip the one you want, and follow the short connect step if that channel needs one, such as authorizing a Slack workspace or pasting in the token for your own Telegram bot. You can also simply ask an employee in chat to turn a channel on, and it will do it and tell you what is still missing. A few surfaces stay permanently on, including in-app chat, because switching those off would lock you out of your own workspace. The same list reports how much each channel is actually being used, day by day and in total. ## Use Cases ### Chat with your employee directly in the workspace Open a conversation and start working. Assign tasks, ask questions, review drafts, and give feedback in a familiar chat interface built for getting things done. ### Deploy to Slack so your team can use them too Connect your AI employee to Slack. Your whole team can reach them in channels or DMs without leaving the tools they already use. ### Handle customer inquiries over WhatsApp or email Route inbound WhatsApp messages and emails to your AI employee. They respond with context, triage issues, and escalate when needed, all without human intervention. ### Embed a widget on your website Add a chat or voice widget to any page. Visitors get instant, accurate answers from your AI employee rather than waiting for a human or searching through FAQs. ## FAQ ### Which channels can I actually use today? Today an AI employee works over in-app chat, its own email address, your connected Gmail or Outlook, Slack, Telegram, calendar invitations and live meetings, plus programmatic routes like a REST endpoint, inbound webhooks, MCP and A2A. WhatsApp, SMS, Discord, Microsoft Teams, in-app voice and video, phone calls, a website widget and language SDKs are on the roadmap and are labeled as coming inside the workspace. Anything not carrying that label is live and can be switched on right now. ### Do I have to set up channels again for every AI employee I hire? No. A channel is switched on once for your workspace, not once per employee, so the connect step happens a single time. Most people only ever turn on the two or three channels they genuinely use, and in-app chat needs no setup at all because it is on from the moment you hire. The one thing that binds to a particular employee is a Telegram bot, since each bot points at one employee. ### Does an AI employee get its own email address, or does it use mine? Both, and they do different jobs. Every employee is given its own working email address the moment you hire it, so you can write to it directly, copy it into a thread, or forward something and ask for a summary. Separately you can connect your own Gmail or Outlook, and then the employee drafts and sends from your real address. Use its own address for delegating work to it, and your connected account for anything a customer should see coming from you. ### Can I switch a channel off once I have turned it on? Yes, and it applies immediately. Any channel you enabled can be turned back off from the same communications list, or by asking your employee to do it in chat. Core surfaces such as in-app chat stay on by design, because disabling those would lock you out of your own workspace. Turning a channel off changes nothing about the history, so past conversations stay exactly where they are. ### Do I need a developer to put an AI employee into Slack or Telegram? No developer is needed for either one. Slack is a normal workspace authorization: you click connect, approve it the way you would approve any Slack app, and afterwards people mention the employee in a channel or send it a direct message. Telegram is simpler still, because you create a bot inside Telegram itself and paste its token into Sistava. Neither route needs code, a server, or anything hosted by you. ### Can an AI employee join a meeting and take part, or does it only listen? It takes part. Invite the employee's email address to a Google, Outlook or Apple calendar event and it joins the call when the meeting starts, follows the discussion, and speaks when someone addresses it directly. It works on the usual meeting platforms and needs nothing installed by the other participants. After the call ends, the same employee writes up what happened so you get notes and next steps rather than a recording. ### How do I tell whether a channel is actually being used? The communications page reports usage per channel: how many requests came in, the all time total, and daily activity. That is usually enough to spot a channel you switched on that nobody touches, or to notice that the employee's email address is quietly carrying most of the load. Nothing extra has to be installed or connected to get those numbers. ### Can people outside my company reach my AI employee? Yes, through a few doors that are live today. The employee's own email address works for anyone who can send email, so a client or supplier can write to it without an account. An inbound webhook lets a system you already run hand an outside message into a conversation, and Slack works for anyone in a workspace you have connected. The public website widget and WhatsApp are on the roadmap, so for direct outside contact today, email is the route. ## One Agent, Every Channel Running separate tools for chat, email, and phone means your context is scattered and your AI agent starts every interaction cold. With Sistava, one agent operates across all channels with a unified memory. It knows what the customer said in Slack, what they asked via the widget, and what you discussed in email, all at once. Adding a new channel takes minutes, not a separate integration project. Your AI employee carries its skills, duties, and knowledge into every new channel you activate. You expand your coverage without expanding your workload. ## How It Works 1. **Activate Your Channels**: Turn on the channels you need: in-app chat, voice, Slack, WhatsApp, email, phone, or the embeddable widget. 2. **Same Agent Everywhere**: Your AI employee uses the same memory and behavioral rules across every channel, delivering consistent responses every time. 3. **Embed Without Dev Work**: Drop the chat widget onto any page with a single script tag and your agent starts handling inbound traffic immediately. > We embedded the widget on our pricing page and it started booking demos on its own. We didn't change anything on the backend. > > Sofia R., VP Marketing ยท B2B startup ## Features in Channels - [Communicate Over Every Channel](/en/features/channels/external_channels_group): Talk to your AI employees wherever you already work: the web app, Slack, or email, with more channels rolling out. Every channel routes into the same conversation history, so an employee never loses context switching between them. Turn a channel on or off from Settings, and a plan-gated channel unlocks the moment you're on the right plan. - [Web Chat](/en/features/channels/channel_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. A focused Watch-sized view keeps a direct employee conversation readable when you only need to catch up or send a short reply. - [Voice Calls](/en/features/channels/voice_channel): 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](/en/features/channels/channel_email): 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](/en/features/channels/channel_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](/en/features/channels/connected_mailbox): 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. - [Talk to Your Employee on Video](/en/features/channels/channel_in_app_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. - [Chat Widget](/en/features/channels/channel_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](/en/features/channels/channel_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](/en/features/channels/channel_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](/en/features/channels/channel_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](/en/features/channels/channel_calendar): 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](/en/features/channels/channel_slack): 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](/en/features/channels/channel_telegram): 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. - [Microsoft Teams Channel](/en/features/channels/channel_microsoft_teams): Bring an AI employee into Microsoft Teams so it can answer direct messages and reply when mentioned in a channel, the same way it already works in Slack. This channel is planned and not available yet; today you can reach your employees through the web app, Slack, Telegram, or their personal mailbox. Sitting in a Microsoft Teams video call already works through the Meeting channel, so Teams chat is the piece still being built. - [Meeting Channel](/en/features/channels/channel_meeting): Paste a Google Meet, Zoom, or Microsoft Teams link and your AI employee joins the call as a real participant. It listens the whole time, speaks up when you address it by name, and writes a summary to memory and Drive once the call ends. - [Phone Call Channel](/en/features/channels/channel_phone_call): Call a real phone number and talk to your AI employee out loud, the way you would call a colleague. It is planned as a full telephony channel: your employee answers inbound calls, can place outbound calls, and carries the same memory, tools, and approval controls it uses everywhere else. This channel is not available yet; it shows as coming soon in Settings. - [Form Channel](/en/features/channels/channel_form): Embed a form on your website and route every submission straight to an AI employee, no inbox in between. The employee reads the fields, replies, files a lead, or kicks off a task the moment someone hits submit. This channel is on the roadmap and is not available yet. - [RSS Feed Channel](/en/features/channels/channel_rss): The RSS Feed Channel is on our roadmap. Once it ships, you will point an AI employee at any RSS or Atom feed, blog, changelog, or news source, and it will wake the moment a new item is published. No polling by hand, no inbox full of alerts you have to triage yourself. - [Spreadsheet Channel](/en/features/channels/channel_table): Connect a Google Sheet or Airtable base as a trigger for an AI employee. When a row is added or updated, your employee picks up the change and acts on it, no separate automation tool required. This channel is on the roadmap and not available to hire against yet. - [Slack Notifications](/en/features/channels/slack_notifications): Connect Slack and your platform notifications move there automatically: an Employee finishing work, reporting in, or waiting on your decision shows up as a Slack DM instead of email. Approval requests arrive as an interactive card with Approve and Reject buttons, so you can resolve them without leaving Slack. - [Channel Enable/Disable Toggle](/en/features/channels/channel_enable_disable): Not every employer wants every channel open. Turn Slack, WhatsApp, SMS, or any other non-core channel on or off for your workspace, either in the settings screen or by simply telling your employee to switch it. Core channels like chat stay on because every employer needs them; everything else is yours to control. - [Channel Usage Analytics](/en/features/channels/channel_usage_analytics): Every channel tile on your Communications page shows exactly how much it is being used: requests in the last 30 days, the all-time total, when it was last active, and a daily sparkline so you can see the pattern at a glance. No separate report to pull, no counter to trust: it is read straight from your message history every time the page loads. ## Explore - [Every feature](/en/features) - [Browse AI employees](/en/agents) - [Pricing](/en/pricing)