The problem, in one line
You chase an unpaid invoice. The customer writes back. Now somebody has to read that reply and work out what it actually means. Are they paying? Arguing? Confused? Was it even the right person? That reading is the part that still lands on a human.
Tools that send the reminders are everywhere. QuickBooks bundles one at $85/mo and Chaser lists $180/mo, and the better ones already do something with what comes back. Chaser files replies from your Gmail or Outlook against the right customer, and its AI can read a message, work out the intent, and write you a polite response to send.
That polite response is exactly what this does not produce. What comes out here is not a message. It is a decision: the chasing pauses or stops, a payment query is opened, a part payment is recorded, a promised date is worked out. It writes nothing and it sends nothing. There is no email in it at all.
Using it, in three steps
- Pick a reply from the list. These stand in for what arrives in your finance inbox after the reminders go out. There are 72, written to look like a real inbox: mostly junk, with the awkward ones mixed in.
- Look at the seven scores under the message. Each one answers a separate question, because a single reply can genuinely be two things at once.
- Move the dial. Left, and it checks nearly everything with you. Right, and it handles more alone. It sets two lines as it moves: the score a reading needs before it acts, and the lower score it needs before it will even mention the possibility. Under that second line, nothing is said.
Try the ones marked 2 things. Those pay part of the bill and argue about the rest. A tool that has to pick one answer would have recorded the part payment and lost the argument, or spotted the argument and lost the money.
How to read the seven scores
Each score is that question answered on its own, from 0 to 1. They are not shares of a total and they do not add up to anything: a reply can score high on two at once, which is the whole point.
The small mark on each bar is your line. So:
- Bar past the mark, it is sure enough, and it acts.
- Bar close to the mark but short of it, it is unsure, so it does nothing and flags the reply for you with the score attached.
- Bar nowhere near, it does not apply and you never hear about it.
Two of the seven sit at a higher line than the rest: a reply that argues about the bill, and one that claims it was already paid. Those are the two where acting wrongly costs the most, so they carry a line 0.15 above the other five, wherever the dial sits, and never past 0.99. It shipped with the acting line at 0.65, which puts those two at 0.80.
Drag the dial and watch the row of numbers at the top move. Left, and almost everything comes to you. Right, and more is handled without you, with more chance of something being handled wrongly. There is no correct setting. It is your call, and the point of showing it is that it is a dial rather than someone else's decision.
When a reply is two things at once, which one leads
Both still happen: nothing is discarded. But one of them has to lead, and five rules decide which, written while the replies were being labelled rather than afterwards.
- money now beats money later. part of the balance is being paid now, so that is what leads even when the rest is promised.
- a promise to reply is not a promise to pay. coming back to you is not sending money.
- an actionable redirect outranks an auto-reply. an out-of-office naming a live alternate contact is something to act on.
- acknowledging the email is not acknowledging the debt. 'received, thank you' says nothing about whether the invoice was paid.
- disputing the terms is still a dispute. 'our contract says net 60' argues with the bill even though it asks nothing.
Is this just a canned demo?
Fair question, and the reason for the Write your own tab. Type any reply you like against any invoice and it goes to the same model, through the same seven questions, into the same rules, and comes out in the same layout as everything on the other tab. Nothing is matched against a script.
The 72 sample replies work differently on purpose. They were written and labelled before this was built, and their answers are fixed, so the accuracy figures below are measured against something that cannot be quietly adjusted after the fact. Your own text is read fresh each time and is kept out of those figures.
What it will not do
- It never sends anything. There is no email path in the system.
- It never marks an invoice paid. If someone claims they paid, that opens a query for a person to check. There is no action in the system that can close an invoice.
- It never invents a date. If a promise has no date in it, the promise is recorded without one and a person sets it.
- It does what the text says, not what the text asks. A reply telling it to ignore its rules is read as data, like any other reply.
- It never keeps chasing someone who asked it to stop.
remove me, unsubscribe, stop emailing: those are caught by a plain rule in the code, not by the model, so it does not depend on a score being high enough.
What it actually got right
Every one of the 72 replies was read at the settings this shipped with, and the answer compared to the label written beforehand. It is reported one class at a time, with the count beside it: the mix here is lopsided on purpose, so a single overall figure would say more about the mix than about the system. Moving the dial changes what happens on this page. It does not change these.
The ordinary replies, 51 of them
| reply type | how many | how many it found | when it said so, right |
|---|
| argues with the bill | 5 | 100% | 100% |
| says it is already paid | 6 | 100% | 100% |
| promises to pay | 10 | 100% | 100% |
| pays part of it | 2 | 100% | 100% |
| asks for something | 10 | 100% | 100% |
| is the wrong person | 5 | 80% | 100% |
| carries nothing actionable | 13 | 100% | 93% |
The deliberately awkward ones, 21 of them
| reply type | how many | how many it found | when it said so, right |
|---|
| argues with the bill | 1 | 100% | 50% |
| says it is already paid | 4 | 50% | 100% |
| promises to pay | 2 | 50% | 100% |
| pays part of it | 4 | 100% | 100% |
| asks for something | 2 | 50% | 100% |
| is the wrong person | 3 | 67% | 100% |
| carries nothing actionable | 5 | 80% | 100% |
The reading time at the top is your own estimate, which is why you can change it. It is an estimate, not a measurement, and it is never mixed in with the figures above.