AI classification

It reads the document
before it files it.

Findest doesn't match filenames or senders. Every attachment is read, compared against all of your rules at once, and filed under the one that actually fits — or under none, and it tells you why.

The decision

One call. Every rule. Side by side.

Your rules aren't checked one at a time. They all go to the model together, in a single request, along with the document.

1Electricity bills
2Payslips
3Signed contracts
4Supplier invoices
One request document + every rule
Answer
4Supplier invoices

The model returns one rule number — or 0, meaning none of them fit.

This is deliberate, and the reason isn't only cost — though it is that too: a Pro account with fifteen rules would otherwise mean fifteen requests per document instead of one.

The real reason is accuracy. Asked “does this document fit this rule?” in isolation, a model has nothing to compare against, so it says yes to the first rule that looks vaguely close. Shown every rule at once, it can do the thing you actually want: tell them apart.

Why it works this way

A bug filed an invoice in the wrong folder.

This isn't a hypothetical. The first version of the engine matched text, and it broke in a way that's worth showing rather than describing.

Before — substring matching
rule = "facturas electricidad"
label = "Factura"

rule.includes(label) → true

A rule for electricity bills captured every document the classifier labelled “Factura”. A Make.com invoice landed in the user's energy folder. Not an edge case — that was the algorithm working exactly as designed.

Now — read and compared
rule = "Office electricity bills
  from Endesa. Not the ones
  for my flat, not gas."

model reads the document → no match

The rule is a sentence, not a keyword, and the document is read against it. A software invoice no longer looks like an electricity bill just because both are invoices.

Keyword filters — sender, subject, filename — were removed outright rather than kept alongside the new engine. Two ways to route a document is one way too many, and the old one was the one that got it wrong.

Before the model

Most attachments never reach the AI.

Reading everything would be slow, noisy, and needlessly expensive. A pre-filter runs first, and it's plain rules, not a model.

Inline attachmentsSignatures, logos, and tracking pixels are marked inline by the mail client. Dropped.
Anything under 3 KBToo small to be a real document. Almost always a decorative image.
Anything over 25 MBAbove the size we accept, and above what's useful to classify.
Unsupported file typesOnly formats the model can actually read get through.
PDFs, images, text, CSVThese reach the model — and only these.

A newsletter with a logo in the footer costs nothing: the logo is discarded before a single token is spent.

When nothing fits

No match is an answer, not a failure.

If the model finds no rule that fits, it returns 0 and the document is kept with the status “no rule” — along with the reason the model gave.

That reason is visible in your History. You'll usually find it says something reasonable, and it's the fastest way to see that a rule needs rewording. Nothing is guessed, and nothing is silently dropped into an approximate folder.

You aren't emailed about it either. A document with no matching rule is normal operation, not a failure — alerts are reserved for things that actually broke, so they stay worth reading.

What it doesn't decide

The document type is a label, not a decision.

Findest also works out what kind of document it is — invoice, payslip, contract — and uses it for the filename and for your History.

It used to decide routing too. It doesn't any more, and that's the whole point of the change above: the type is a description, and your rule is the instruction. Two documents of the same type can go to different folders, which is exactly what you'd expect and what the old engine couldn't do.

Questions people actually ask

Which model does it use?

Gemini, configured server-side rather than hard-coded, so it can be changed without a release. It's asked for structured output, so the answer is a rule number, not prose that needs parsing.

Does my document get used to train a model?

No. The document is sent to be classified and the answer comes back; it isn't contributed to training.

What if two of my rules genuinely both fit?

The model picks one, and because it can see both, it picks the more specific one rather than whichever it happened to be asked about first. If they overlap so much that either would do, that's usually a sign they should be one rule.

Can I see why something was filed where it was?

Yes. Every document in your History carries the rule it matched, and documents that matched nothing carry the reason instead.

How long does classification take?

Seconds. The slow part of the whole journey is never the model — it's waiting for the mailbox to be polled, which is why documents arriving over IMAP take a few minutes to appear.

See it decide on your own documents.

The free plan covers 30 files a month, and it's the same engine — no trial version of the classifier.