AI Email Agent: Give One a Real Inbox It Can Send and Receive From

An agent that only sends is half an agent

The moment an AI email agent does anything real — confirms a booking, chases an invoice, answers a support thread — it has to read the reply. That is where a plain send API runs out: you end up writing an IMAP loop, an OAuth refresh, a MIME parser and your own threading, none of which belongs in an agent runtime.

Give the agent an identity instead. It gets a sending address and a receiving address, and inbound arrives as an event shaped like every other event your code already consumes:

import { createClient } from "@mailsai/sdk";
const mails = createClient();

// Sending: no agent to pre-create, no domain to verify, no DNS.
await mails.send({
  from: "hello",
  to: "customer@example.com",
  subject: "Your invoice #221 is ready",
  body: "Invoice #221 for March is attached, due the 30th.",
});

// Receiving: replies arrive as typed events, already threaded and scanned.
mails.agent("hello").onReply((event) => {
  // Hold for a person: quarantined, not scanned (no score), or 0.5 and up
  if (event.quarantined || typeof event.injection_score !== "number" || event.injection_score >= 0.5) {
    return flagForReview(event);
  }
  if (event.source_message_id) {
    mails.messages.reply(event.source_message_id, { body: answer(event) });
  }
});

Two boundaries, both enforced by the API

An agent with email is exposed in both directions, and a prompt is not a control. Inbound, anything it reads is untrusted input that may be trying to redirect it — so every message carries an injection_score and its flagged categories, and scores of 0.95 or above arrive flagged quarantined. Outbound, an agent that is talked into prospecting would spend a sending reputation it did not build — so cold and bulk mail is refused in the send call, with a reason the agent can read and a second review if the verdict looks wrong.

Reputation is scored per agent, not per account. One misbehaving agent auto-suspends at a 0.3% complaint rate, before the upstream provider’s 0.5% threshold ever sees it, and your other agents keep sending unless the workspace’s mail as a whole crosses the line too.

What it costs to run one

Free covers 3,000 emails and 3,000 inbound replies a month with one agent and no card. Beyond that, Pro is $20 a month for 50,000 emails and 50,000 inbound replies across five agents, and Scale is $99 for 250,000 emails and 500,000 inbound replies with unlimited agents. Parsing and the injection scan come with every inbound, and intent/entity classification of first-contact mail is opt-in on paid plans at no extra charge when you want routing decided before the model runs. For the operational layer above individual agents — routing, classification, reputation monitoring — see AI email management.