Written by AI
When the words give it away.

OpenEmail reads the sender’s own words as mail arrives, and marks the message when they look generated rather than written.

In short

What makes an email look AI-written?

Language models have habits, like stock greetings and sentences of near-identical length. People leave typos and shorthand. A detector weighs one against the other, but no detector can prove who wrote a message.

60

out of 100 earns the label

20

tells count towards the score

7

count against it, like typos and emoji

How it works

Read from the words they wrote

Quoted history and the signature are cut first. Stock phrasing adds to the score, and a typo or a quick btw takes points off.

A second reading that leans human

From 30, the assistant reads the words too, unless the mail came from a template. It can take off 45 points but add only 35.

Declined rather than guessed at

Bulk mail and anything under 40 words are not scored, and Details says which. Template mail never gets the label.

Tells it looks for

Weighted and summed from the sender’s own words.

as an AI language modelenough on its own##markdown headings[Your Name]an unfilled placeholdernot just X, but Ythe stock contrastbtwshorthand, counts againstSent from my iPhonephone signature, counts against

What you get

In the product today

Labels, never filters

Nothing is moved or hidden on the strength of a guess.

Maybes stay in Details

Between 35 and 60, the verdict stays in the Details tab.

Encrypted mail is skipped

An encrypted message is declined, not scored, and Details says so.

Good practice

Getting the most out of it

  1. 01

    Open the Details tab

    It lists the tells that fired and the score behind the label.

  2. 02

    Judge what it says

    A label describes the writing, not whether the message matters.

  3. 03

    Read the score plainly

    It measures how much stood out, not the odds of being right.

Where it stands

Good to know

Silence is not proof
No label means nothing stood out, or the check declined to judge.
The second reading on older mail
Mail that predates the check is scored as it opens, with no second reading and a weaker bulk check.

Questions

Asked often

Keep going

Works well with

Verified sender

A mark beside the sender when the sending domain’s published records line up.

Phishing & spam filtering

Mail the sending domain itself disowns lands in Spam rather than the inbox.

Sender research & look-alike domains

Who is this, in fifty words, and is the domain a look-alike?

Start

Your domain,
your mail.

Point a domain at OpenEmail and read it in a mailbox built around it. The free plan covers one domain.

Your inbox,
on your own terms.

Email infrastructure for businesses, AI, agents and personal email. Built for scale, privacy and control. Everything email should have had from day one.

OpenEmail

Email infrastructure for businesses, AI, agents and personal email. Built for scale, privacy and control. Everything email should have had from day one.

© 2026 OpenEmail. All rights reserved.