> ## Documentation Index
> Fetch the complete documentation index at: https://docs.vorel.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Email

> Give the agent a mailbox: triage rules, draft versus send, loop protection, and the spam gate.

Connect a mailbox and the agent reads what arrives, decides whether it should answer, and either
replies or leaves a draft for a human.

## Connecting

Connect your mailbox under **Settings, then Email**, by granting access to the mailbox you want the
agent to work. Nothing is routed until you nominate the receiving address, so connecting the mailbox
and turning the agent loose on it are two deliberate steps.

## Draft or send

The most important setting on this channel is the mode:

| Mode      | Behaviour                                                                                                                                      |
| --------- | ---------------------------------------------------------------------------------------------------------------------------------------------- |
| **Draft** | The agent composes a reply and leaves it in the conversation for a human to review, edit and send. Nothing reaches the customer automatically. |
| **Send**  | The agent replies directly.                                                                                                                    |

Most teams start in draft, watch for a week, then move the intents they trust to send.

You can also allow automatic sending for specific intents only, so straightforward questions get
answered immediately while anything else waits for a person.

## Triage

Not every message in a mailbox deserves an answer from an AI agent. Triage runs before the agent and
can suppress:

* **Spam and junk**
* **Out-of-scope messages** that have nothing to do with your business
* **Messages requesting a human**, which go straight to escalation
* **Complaints**, which go straight to escalation

Suppressed messages still land in the inbox. They are visible, they are just not answered by the
agent.

## Loop protection

Auto-responders are the classic way an email bot embarrasses a business. Messages are checked for
the signals that mark them as machine-generated (auto-submitted headers, bulk precedence, mailing
list headers, empty return paths, bounce shapes, and our own stamp on outbound mail) and are never
answered.

## The spam gate

Email is the one channel where an applied `spam` or `irrelevant`
[category](/inbox/categories) stops the agent entirely. The message is stored and categorized, the
agent is not dispatched, and no fallback reply is sent. A spam message gets silence, which is the
only correct response.

This gate is deliberately limited to email. On WhatsApp, voice and web chat, a wrong spam call would
mean ignoring a real customer, so those channels categorize without gating.

## Threading

Replies thread correctly against the original message, so the customer sees a conversation rather
than a series of disconnected emails. Inbound replies attach to the same Vorel conversation.

## What the agent can do

The full chat tool surface: answer from knowledge, qualify, check availability, book, write to your
CRM, escalate.

## SLA and CSAT

Email is tracked for [SLA](/inbox/sla) like any other channel, which matters more here than
elsewhere because email is where response times quietly slip. CSAT surveys on email conversations
are delivered as a link in a follow-up message.