SaaS company embedding an AI agent into their product
Drop the widget on any page and your AI employee is available to users immediately, no separate product to build.
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.
Drop a script tag on your website and your AI employee is live, ready to chat with visitors. The widget handles the full conversation experience: streaming responses, rich media, typing indicators, and conversation history. Your employee uses the same skills, memory, and tools it uses in the workspace.
Customize the widget to match your brand. Set colors, positioning, welcome messages, and avatar. Configure which employee handles widget conversations and what skills it uses. A support employee handles your help center widget. A sales employee handles your pricing page widget. Different pages, different employees, same seamless experience.
Every widget conversation flows into the same activity feed, history, and analytics as in-app chat. Your employee remembers returning visitors across sessions. Conversations can escalate to email, Slack, or any other channel without losing context. The widget is an entry point, not a silo.
The widget is on the roadmap and is not something you can install yet. Today it appears under Settings, Technical, Channels marked as coming soon, with no embed snippet and nothing to configure. When it lands, that is where you will switch it on and copy the script tag from, and the employee you point it at will be one you already hired.
Until then the same employee is already reachable everywhere else. Give it a personal mailbox and people can write to it by email from the moment it is hired. Connect Slack or Telegram and it answers there. Call it from your own front end through the REST API if you want something custom on the page right now. None of that is a different employee, it is the same one behind a different door.
What the widget adds is the case none of those cover: a visitor who has a question while they are standing on your pricing page and will not switch to email to ask it. That is where most quiet interest leaks away, usually without leaving any trace you could have acted on. Putting the employee on the page means the answer happens in the same place and the same minute as the question.
Because the widget renders whichever employee you assign, changing what it says will never mean a deploy. Retrain that employee, adjust its tone, give it a new skill, or connect another app, and your website reflects it without anyone opening the site's code again. The embed stays the single line it was on the first day.
Embeddable Chat for Any Website in One Script Tag
The chat widget is a pre-built, embeddable UI component that puts an AI employee on any website with a single script tag. Visitors interact with the AI employee through a familiar chat interface without leaving the page. Configuration options cover appearance, initial message, employee assignment, and behavioral constraints.
Widgets are fully themeable to match your brand: colors, fonts, logo, and chat bubble position. The underlying AI employee retains its full capability stack, skills, tools, and memory, so visitors get the same quality of interaction as users in the main platform, delivered in your product's design language.
Context-Aware Conversations for Your Visitors
For SaaS products, the widget is the fastest path to embedding AI employee capabilities directly in your product. Instrument the widget initialization with your user's context (company name, plan tier, conversation history) and the AI employee can deliver personalized, context-aware assistance from the first message.
Returning visitors are recognized across sessions. Your employee remembers prior conversations, preferences, and unresolved questions. This continuity turns a simple chat widget into a relationship, not a one-off interaction that resets every time the page loads.
Full Agent Capabilities, Not a Scripted Chatbot
Unlike traditional chatbot widgets that follow decision trees or keyword matching, the Sistava widget connects to a real AI employee with full reasoning, tool access, and memory. It can search the web, look up records, create documents, and take actions on behalf of the visitor.
This means your website widget can handle complex requests that would normally require a human agent: researching product compatibility, generating custom quotes, troubleshooting technical issues, or booking appointments across time zones. A widget powered by an autonomous AI agent, not a scripted flow.
How It Works
You drop a script tag on any page and your AI employee handles inbound conversations with your branding, your knowledge, and your tone.
Paste a single script tag into your site and the chat widget appears immediately. No iframe wrangling, no backend setup. Your AI agent connects to the widget automatically, bringing everything it already knows: your products, your policies, your tone. Customize the widget's colors, logo, and greeting to match your brand without touching any code beyond the embed.
Every conversation the widget handles is a full agent conversation, not a scripted chatbot flow. The AI employee reads the page context, answers questions from your knowledge base, qualifies leads, books meetings, and escalates to humans when needed. All widget activity streams into your activity feed in real time so nothing goes unnoticed.
The widget is on the roadmap rather than installable today, and it appears in your channel settings marked as coming soon. That matters for planning, not for preparation: the employee you would put behind it is the one you hire and train now, so anything you teach it, connect to it, or set as its tone is already in place the day the embed becomes available.
Use Cases
E-commerce team adding AI-powered support to their storefront
The AI agent answers product questions, handles returns, and guides purchases, embedded directly in the store.
Marketing team adding an AI employee to the company website
Visitors get instant answers without leaving the page. The AI agent converts interest into action.
Developer team customizing a branded chat widget for a client
Embed a fully branded AI agent with a single script tag. Appearance, behavior, and routing all configured in the platform.
Comparison
| Before | After |
|---|---|
| Adding AI chat to a website requires a custom build or a separate SaaS tool. | Embed your AI employee anywhere with a single script tag. |
| Chat widgets feel generic and off-brand. | The widget matches your brand and runs your configured AI agent. |
| Changing the agent's behavior requires a code deploy. | Update the AI employee in the platform and the widget reflects it immediately. |
| Every product surface needs its own support solution. | One AI agent, embedded wherever your users are. |
FAQ
Can I use the chat widget with any AI employee?
Yes. Any active AI employee can be assigned to a widget. You configure the widget with an employee ID and an access token scoped to that employee. The widget inherits the employee's full configuration including skills, tools, and content policies.
Does the widget support multi-turn conversation history?
Yes. The widget maintains conversation history within a session and, with a user identifier passed at initialization, can persist history across sessions so returning visitors continue where they left off.
Can I put different employees on different pages?
Yes. Each widget instance is configured independently. Your help center page can use a support employee while your pricing page uses a sales employee. Each one brings its own skills, training, and persona to the conversation.
Is the chat widget open source?
The default widget is a hosted component. For teams that need deep customization, the widget source is available on enterprise plans so you can modify the UI or integrate it directly into a design system.
Can I embed an AI chat agent directly on my website?
That is what the chat widget is for. You will get a script tag that drops a fully functional chat widget onto any webpage in minutes, connected to your AI employee with all its skills, knowledge, and tools intact. It is on the roadmap and not installable yet.
Can I put the Sistava chat widget on my website today?
Not yet. The chat widget is on the roadmap and currently shows under Settings, Technical, Channels as coming soon, with no embed snippet to copy. In the meantime the same employee is reachable by email through its personal mailbox, through a connected messaging channel, or from your own front end through the REST API.
Will I need a developer to install the chat widget?
No. Installing it will mean pasting one script tag into your website, which most site builders and content platforms accept in a settings field without touching code. Appearance, greeting, and which employee answers are all set in Sistava rather than in the snippet.
Will the widget use the same AI employee I already chat with?
Yes. The widget is another door into an employee you have already hired, not a separate bot to train. It carries the same knowledge, skills, tools, and content policies, and the conversations it has land in the same history and activity feed as everything else that employee does.
We added the widget to our pricing page and the agent started qualifying leads on its own the same evening. No configuration beyond the script tag.
Where Chat Widget fits
Chat Widget 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.
- 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.
- 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.