Open your inbox, select the subject lines on screen, paste them here. You get them sorted into what genuinely needs you, what can wait, and what a machine sent — with the reason for each. Most founders find the first pile is smaller than they expected.
Nothing is stored and there is no account. The sorting runs in your browser; only lines it cannot place are sent anywhere.
No. Nothing is written to a database and there is no account. The sorting itself is computed in your browser from the text you paste. Only the handful of lines the patterns cannot place are sent on for a second opinion, and they are not retained after the answer comes back.
Two passes. The first is pattern matching over the text itself: no-reply senders, receipts, security codes, digests and app notifications on one side; someone asking you a direct question, or anything involving money or a deal, on the other. That pass runs in your browser and is what you see first. Only the lines it cannot place confidently go to a model for a judgement call.
Because nobody knows their own numbers. A tool that asks how many emails you get a day and multiplies by a slider is arithmetic on a guess, and the answer is just your input wearing a percentage sign. Subject lines take ten seconds to copy and cannot be fudged.
Probably, on the ambiguous ones. The rule it follows is that calling a real email noise is far worse than the reverse, so anything it is unsure about stays in 'can wait' rather than being binned. The automated calls are the confident ones, because those fire on markers a person writing to a person would never use.
It is the first thing Mailient does, run on subject lines alone. The real product reads the whole thread, plus who the sender is to you and what you have already agreed with them, then drafts the replies for the ones that matter. This page is that idea shrunk to something you can test in a minute without connecting anything.