Your inbox,
maintained.

Every day comes back
as one page.

Every message that arrives is read and given a verdict. Most are ordinary and get set aside as ordinary. What is left is a short numbered list — sender, subject, the reason it is on the list, and what it wants from you. The same list is the daily digest: one computation, one set of numbers, no second opinion.

Sample data · Delivered as the daily digest on Pro · 14:00 UTC

You see the before and
the after in one sitting.

Connect, and SiftMail scores your fifty most recent messages. That is the free audit, and it finishes in about the time it takes to read this paragraph. Then, when you ask it to, it goes wider: one sweep across the whole mailbox that counts the promotions, the bulk mail, and the no-reply threads older than ninety days.

The sweep runs as a preview. It shows you the count and a sample of the messages behind it, and it changes nothing until you apply. Applying archives. There is no delete path in this product — not in the API, not in the worker, not anywhere.

Sample preview · Not your mail

The deep clean is free, once. You see a preview first; nothing moves until you confirm. Confirming archives the matching mail — it leaves the inbox, it is not deleted, and Undo puts it back. Shadow stays on: the recurring sort, the daily digest, and auto-quarantine wait for Pro, off until you turn them on, and still only a label when you do.

Then it holds.

The same sort runs on new mail. Bulk is set aside. A message that wants a reply stays in front of you for up to seven days, whether or not you were at your desk the day it landed. Once a day, one digest — not four — says what happened.

If SiftMail acted, it says acted. If it only flagged, it says flagged. It never claims the other one, because a run only counts the operations Gmail confirmed. And every maintenance run records the inverse of each label it wrote, so one control puts the mailbox back the way it was.

The recurring sort, the daily digest and auto-quarantine are Pro · $15/mo · Gmail

Every flag shows its work.

A risk score on its own is a number you are asked to trust. SiftMail prints the signals instead, in the same words the product uses everywhere else. Each one is checkable in the message headers, by you, which is the entire point of printing them.

The gate runs the other way too. A message only reaches the digest's most trusted slot — the service alert — on a curated infrastructure sender, an alert-shaped subject, and a DMARC pass. And a DMARC-aligned sender you have real history with does not get called a threat on a hunch: the guard stands the flag down, and the digest stands it down with it. One inbox, one story.

Promotion to a critical alert requires a DMARC pass. Never without.

We mark it.
We don't take it.

In Gmail, quarantine adds one label — Sift/Quarantine — and stops. The message stays in your inbox, in its thread, in the place you last saw it. Release takes the label back off. Which means the worst thing a false positive can do to you is disagree with you in writing.

Archiving is the one action that takes mail out of the inbox, and it runs only on the noise tier you approved: promotions, bulk, dead no-reply threads. Most tools in this category ask you to trust that they took the right thing. There is nothing here to trust, because nothing was taken.

SiftMail for Gmail — in-inbox risk badges · Built at 3.4.0, not yet listed on the Chrome Web Store

Half museum.
Half liability.

The same reader, pointed backwards. Your mailbox comes back as strata — what year, what is in it, and what a stranger holding your password would find first. A passport scan from 2016. A tax form. A temporary password somebody typed into an email and never thought about again. Sitting in the same result set: the oldest photograph anyone ever sent you.

Red is reserved for identity-level exposure; if everything were critical, nothing would be. Old phishing that already failed is trash, not a siren — it is muted and shredded in a batch, never presented as an emergency a decade late. No model runs on this path at all, and the build fails if anything on it so much as imports one.

No model runs on this path · Findings stored per-user, visible only to you · Deletion happens in Gmail, by you

Here is exactly what
leaves your mailbox.

Headers and a snippet go to Anthropic when our own scoring cannot settle a message. Up to 4,000 characters of the body go on ingest, once per message — one pass that sorts it, spots sensitive content, and decides whether it wants a reply. If you connect Slack, the sender and subject of a flagged message go to the webhook you supply.

We are not going to tell you this runs on your device, because it does not. We are not going to tell you we never read your mail, because reading it is the job. It is read by automated systems rather than by staff — with the narrow exceptions our privacy policy sets out, which is also the only complete list. Tokens are encrypted at rest with AES-256-GCM.

Four scopes. Nothing else is requested.