MeetingsA few seconds
Meeting commitment finderWhat did you just agree to in that meeting?
Paste a meeting transcript. Get every promise made in the room, yours and theirs, with the ones most likely to be forgotten flagged first.
Which emails in this list actually need you?
Paste up to 40 subject lines from your inbox and each one is sorted into needs you, can wait, or sent by a machine, with the reason shown beside it. The first sort is pattern matching in your browser; only lines it cannot place get a second look from a small model. It is a free sample from Mailient.
- Free
- No account
- First sort runs in your browser
- Up to 40 lines
What you paste
Three steps, no sign-up
Copy your subject lines
Open your inbox, select the subjects on screen and copy them. Just the subjects, no senders or bodies. Up to 40 lines.
Paste and press Sort them
The first sort is pattern matching that runs in your browser, so the answer is on screen straight away.
Read the three piles
Every line lands in one pile with the reason it was put there. A second look at the unclear ones can move lines while you read.
What you get
How a line gets sorted
The first sort is patterns over the text itself. Each one is written to fire on something a person would not write to another person.
| Part | Where it comes from | What it tells you |
|---|---|---|
| A machine sent it | Counted in code | No-reply senders, receipts and account notices, newsletters and promotions, app notifications. Markers no one writes by hand. |
| Needs you | Counted in code | Someone asking you directly (“can you”, “quick question”, “following up”), or money or a deal involved (a proposal, a contract, a renewal). |
| A date attached | Counted in code | Words like “today”, “by Friday” or “urgent”. On its own this keeps a line in Can wait rather than promoting it. |
| Automated, but something failed | Counted in code | A machine sent it but a person has to act, such as an overdue invoice or a declined card. These are held for the second look, not binned. |
| The second look | Model judgement | Only for lines the patterns could not place. A small model can move them between piles, and any line it moves is marked. |
Reading it
How to read the result
Start with Needs you. Those lines matched a direct ask (“can you”, “quick question”, “following up”) or money and deals (a proposal, a contract, a renewal). If that pile is short, most of what is in your inbox is not waiting on you, which is the usual finding.
Can wait holds the lines the patterns could not call either way. It is deliberately generous: a vague subject can hide an urgent email, so an unclear line lands here rather than being called noise. Any line the second look moved is marked, so you can see which calls came from the model.
Sent by a machine is about who sent the email, not whether it matters. Receipts, notifications and newsletters go here; an automated notice that needs a person, such as an overdue invoice, is held back for the second look instead of being binned.
Background
Why it works this way
How do you tell how much of your inbox needs you?
Sort a real sample rather than estimating. Take the subject lines currently sitting in your inbox and put each one in a pile: a person is waiting on you, it can wait, or a machine sent it. The point of the test is to see that split on your own inbox instead of guessing at it.
This tool does the sorting from the text of the lines, shows which pattern put each line where it went, and holds back anything it is unsure about instead of confidently binning it.
Limits
What it cannot tell you
Every tool here is a first pass with edges. These are this one's.
- Subject lines carry little context. A vague subject can hide an urgent email, so anything unclear stays in Can wait rather than being called noise.
- “A machine sent it” is about who sent it, not how much it matters. That is why an overdue invoice is held back instead of binned.
- The patterns are written for English. Subject lines in other languages will mostly land in Can wait.
- Forty lines at most, each cut at 200 characters. That is enough to show the shape of an inbox without turning the page into a slog.
- The second look is limited. Ten an hour from one connection, and it only counts when there is something unclear to judge. The first sort is always complete without it.
Beyond the sample
When this is not enough
Subject lines are a thin slice of an email. When the answer depends on what the thread says, who the sender is to you, or what you last agreed with them, a sort on subjects alone runs out.
That is where Mailient on Gmail starts. Its Today view reads the messages themselves and shows the emails that need a decision today, today's meetings, and the threads you sent 3 to 14 days ago that got no reply. It drafts a reply in your writing voice when you ask, and by default sends nothing until you approve it.
Your data
What we keep
Read off the code that does it, not written from memory.
- In your browser
- The first sort, by pattern. It is on screen before anything is sent.
- Sent to our server
- Your subject lines (up to 40, each cut to 200 characters), so the sort can be re-checked and the unclear lines picked out.
- Sent on to a model
- Only the lines the patterns could not place, and only if there are any. A small open model (Gemma) through OpenRouter.
- What we keep
- Nothing you paste. A request counter tied to your IP address (10 model calls an hour) holds no content.
Read from app/api/triage-demo/route.ts and lib/rate-limit.ts.
Questions
Questions people ask, answered plainly
6 answers, grouped. Each one is written against what the tool actually does.
Using it
Which lines should I paste?
The subject lines of whatever is sitting in your inbox right now: open it, select the subjects on screen and copy. No senders or bodies are needed. Forty lines is the most it will read.
How it decides
How does it decide what needs me?
Two passes. The first is pattern matching over the text: no-reply senders, receipts, security codes, digests and app notifications on one side, and 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 get a second look from a model.
What does “A machine sent it” mean?
It is a statement about who sent the email, not about how much it matters. A receipt is automated and safe to ignore. An overdue-invoice notice is also automated, but a person has to act on it, so it is held back for the second look instead of being binned.
How accurate is it?
We have not scored it against a labelled set of real inboxes, so there is no accuracy percentage to quote. What we can say is how it errs: toward Can wait, and away from calling a real email noise. The reason for each line is shown, so you can check any call yourself.
Your data
Do you store the subject lines I paste?
No. Nothing you paste is written to a database and there is no account. The sort runs in your browser first. Then the lines (up to 40) are sent to our server, which repeats the same sort so the numbers cannot be faked, and picks out the unclear ones. Only those unclear lines, if there are any, go on to a small AI model through OpenRouter. We keep a request counter tied to your IP address, limited to ten model calls an hour, which holds no content.
Mailient
Is this what Mailient does?
It is the same idea on a smaller input. This page sorts subject lines you paste. Mailient works on your Gmail: its Today view shows the emails that need a decision today, today's meetings, and threads you sent that got no reply; it drafts a reply in your writing voice when you ask; and by default it sends nothing until you approve it.
More free tools
Try another one
WritingInstant, then a few seconds
Writing voice analyserWhat does your writing voice actually look like?
Paste two emails you have sent. Get your writing fingerprint, measured from the text rather than guessed, and one new email in your voice.
SecurityAbout two seconds
Email spoofing checkerCan someone send email as this domain?
Type your domain. See whether a stranger can email your customers from your address, what that email would look like, and the exact records that stop it.
This is the sample. Mailient does this on Gmail.
This tool runs on text you paste. Mailient does the same kind of reading on your Gmail: it shows what needs a decision today, drafts in your voice when you ask, and by default sends nothing until you approve it.