# 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.

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.

The endpoint takes an employee ID and a body (both required), plus an optional sender address and subject line. Whatever your provider sends gets rebuilt into a single prompt: "[Email from jane@example.com] Subject: Q3 Report" followed by the body, so the employee knows the message arrived by email and who it came from, not just raw text. It runs through the same dispatch pipeline as web chat, the REST API, and webhooks, so execution and Credit billing work the same way regardless of the channel a message came in on.

This is not the same thing as a Personal Mailbox. A Personal Mailbox gives every employee a free address on the shared Sistava domain the moment it's hired, no setup required. This channel is the opposite: it only works after you connect a provider account you already own, on a domain you control, and only on Starter plan or above. Use the Personal Mailbox when you want an employee reachable by email today with zero configuration; use this channel when you need mail from your own support or sales inbox to become employee work automatically.

What arrives is a message like any other, which means everything the employee already knows how to do is available the moment it lands. It can read the message, pull the relevant record from a connected app, draft a reply for you to look at, open a task on its board, write a note to Drive, or hand the whole thing to a teammate. Arriving by email narrows nothing about what happens next.

Duplicates are handled rather than hoped about. Send an Idempotency-Key header with each delivery, and your provider's own Message-ID makes a good one, and a repeat inside a five minute window is recognised and refused instead of starting a second run of the same work. Mail providers retry more often than people expect, and this is the difference between one draft reply and three.

Afterwards it looks like any other conversation. The message sits in a thread you can open, the work appears in the activity log, credits are recorded exactly as they are everywhere else, and the employee's journal keeps a record of what it did. There is no separate email console to learn, and nothing about this channel lives outside the workspace you already watch.

## Enabling And Authenticating It

The Email Webhook channel is off for every tenant by default, same as the rest of the Programmatic group. Turn it on under Settings, Technical, Channels, find Email Webhook, and toggle it. It also needs a plan at Starter rank or above; it is not available on the Free plan.

Requests authenticate with a Bearer API key, created from the same Channels page and shared across every programmatic channel (REST API, MCP, webhook, email), so one key works for all of them. A request from a tenant whose account email is not yet verified is rejected with EMAIL_NOT_VERIFIED instead of being dispatched.

## Limits And What Happens At The Edges

The email body is capped at 32 KB and the whole request payload at 64 KB; anything past that comes back as a 400 or 413 rather than being silently truncated. Send an `Idempotency-Key` header (the provider's Message-ID works well) and a duplicate delivery within 5 minutes is rejected as a duplicate instead of dispatched twice.

Dispatch is rate-limited to 60 messages per 60 seconds per tenant, and that limit is shared across API, MCP, webhook, and email combined, not 60 for email alone. If the employee cannot be reached, the caller gets a 502; if the channel is off, a 403. There is no reply thread on this channel: the employee cannot answer back through it, only through a connected Gmail tool if one is attached to that employee.

## Choosing Which Employee Gets The Mail

Every delivery names the employee it is for, so the routing decision lives at your mail provider rather than in a rules engine here. Point support mail at a support employee and sales mail at a sales employee, and each message arrives with the sender address and subject line attached so the employee opens it already knowing who wrote and about what.

That also means one endpoint serves your whole workforce. Adding a second inbox is another forwarding rule on your side, not another setup here, and moving an inbox from one employee to another is a single change to the employee ID your provider sends. Nothing has to be rebuilt when your team grows or your inboxes get reorganised.

## How It Works

**Your email provider posts parsed inbound mail to a tenant-scoped endpoint, and an employee works it.**

Enable inbound parse in SendGrid, Mailgun, or Postmark and point it at the webhook URL in your channel settings. Every email that arrives is parsed into sender, subject, and body, then posted to your tenant-scoped endpoint along with the ID of the employee it belongs to.

From there it becomes work for an AI employee, processed under the same guardrails as every other channel. The employee classifies it, extracts what matters, drafts, opens tasks, or escalates, all without anyone opening the inbox. The channel itself runs one way on purpose: it hands work in and acknowledges the delivery, and if you want the employee to write back it does that through a connected mail tool as part of its own work.

Because the delivery is acknowledged immediately, your provider is never left waiting while an employee thinks. A ten second job and a ten minute one look identical from the provider's side, so nothing times out and nothing gets retried by accident. The API key and the volume limit are shared with the other programmatic channels, which means a burst of inbound mail counts against the same budget as your API calls and you plan for one number rather than four.

## Use Cases

### Support inbox routing

Forward incoming support@ mail to a support employee so every ticket becomes a task the moment it lands, without anyone re-typing it.

### Sales inquiry capture

Route inbound sales@ email to a sales employee so leads get read, contextualized, and acted on within seconds of arriving.

### Internal approval requests

Forward expense reports, PTO requests, or internal approval chains to an employee that reads the request and moves it forward in the background.

### RFP response drafting

Send incoming RFP emails to an employee that reads the requirements and drafts a first response while you're doing something else.

## Comparison

| Before | After |
|---|---|
| Inbound inboxes pile up until someone has time. | An employee works every message as it arrives. |
| Email parsing means brittle custom scripts. | Mail arrives pre-parsed and ready to act on. |
| Connecting email automation means a migration. | Point your provider at a URL and you are live. |
| Volume email needs a human triage team. | The workforce handles routine mail end to end. |

## FAQ

### Do I need my own domain and email provider?

Yes. This channel does not host inbound DNS for you. You need an account with a provider that supports inbound parsing over HTTP, such as SendGrid, Mailgun, Postmark, AWS SES, or Cloudflare Email Workers, configured to POST to the tenant-scoped endpoint.

### Can the employee reply to the email it received?

Not through this channel. It is fire-and-forget: no response content comes back on the request. If the employee has Gmail connected as a tool, it can compose and send a reply as part of its own work, but that is a separate step, not something this channel does for it.

### What's the difference between this and Personal Mailbox?

Personal Mailbox gives every employee a free, always-on address on the shared Sistava domain the moment it's hired, no setup, capped monthly sending by plan. This channel is the reverse: it requires your own provider account and domain, and a Starter plan or above, but lets mail from an inbox you already run become employee work.

### What happens if I forget to enable the channel?

Every request gets rejected with a 403 (channel not enabled) until you turn it on in Settings, Technical, Channels. The API key still authenticates; the channel gate is checked separately.

### Can different email addresses go to different AI employees?

Yes. Each delivery names the employee it is for, so you point support mail at a support employee and sales mail at a sales employee using ordinary forwarding rules at your provider. One endpoint serves your whole workforce, and reassigning an inbox is a single change on your side.

### What happens if my email provider delivers the same message twice?

Send an Idempotency-Key header with the delivery, using your provider's own Message-ID if you have one, and a repeat inside a five minute window is recognised as a duplicate and refused rather than run again. Without that header a resend is treated as a new message, so it is worth setting.

### Does an email that comes in this way cost the same as a chat message?

Yes. Inbound email runs through the same dispatch path as web chat, the REST API, and webhooks, so the credits an employee spends depend on the work it does, not on the door the message came through. Volume limits are shared across those channels rather than counted separately per channel.

## Where Connect an Email Provider fits

Connect an Email Provider 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](/en/features/channels): Every channel. One conversation.

## Read the guide

- [Guide: Connect an Email Provider](/en/guide/channels/email)

## More in Channels

- [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.
- [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.
- [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.

## Explore

- [Every feature](/en/features)
- [Hire an AI employee](/en/market)
- [Pricing](/en/pricing)