A document check is only as good as its worst country.
Most document readers are excellent somewhere. The question is what happens when your customer holds an identity card from the country with the thinnest coverage of all.
Not "how many documents do you support".
Not "how many documents do you support". A catalogue count says nothing about the documents you have never seen, or what the flow does when the read is poor rather than impossible. And underneath that sits a bigger question most buyers never get asked: which route this particular applicant should take to a verified state, because reading a document is only one of three, and most vendors sell one of the three.
How it works.
Optical reading against 20,000+ document templates. Template-less reading for documents outside that set, so an unseen document still parses rather than failing.
NFC chip reading where the document supports it. The chip is signed by the issuer, which makes it the strongest evidence available short of the person standing in front of you.
Capture that adapts: autocapture, still image, burst and video stream. Random challenge and voice biometrics where assurance demands it. An operator can join as a fallback, not as the default.
Forensics on top: multiple document and biometric suppliers behind one interface, with our own checks layered over their output.
Three routes, not one.
Most vendors sell route one and call it the answer. Route one is right for most cases. Route two exists because some cases need a person in the loop. Route three should replace route one wherever the applicant already holds an identity somebody else has already verified, because asking them to prove the same thing twice is friction that buys no security.
| Route | What it is | Assurance | Friction | Where it breaks |
|---|---|---|---|---|
| Document read, optical and NFC | Scan the document, read the chip where the document carries one, match a live selfie against the photo. | High where a chip is present and read, because that data is signed by the issuer. Moderate where the read is optical only. | Low. A camera, nothing else to prepare. | On worn, damaged or badly lit documents, and on document types nobody has a template for, which is why template-less reading exists underneath it. |
| Video ident, operator assisted | A trained operator walks the applicant through capture in a live session. Also the escalation route when either of the other two does not resolve. | Highest of the three. A person is judging the document and the applicant at the same time. | High. It needs a slot, a working connection and the applicant's full attention. | On volume and on opening hours. It spends an operator's time per case, which makes it an escalation route rather than a default path for everyone. |
| eID or bank login, reused | Reuse an identity that has already been verified elsewhere, a government eID scheme or a bank login, instead of asking for a new document. | As strong as the scheme being reused and no stronger. A notified eID or a bank login is strong evidence; a thinner scheme is a thinner check. | Lowest. Nothing new is captured. | Where the applicant holds neither, which is still most applicants in most markets. It is a route to offer first, not a route to depend on. |
Which route an applicant takes is a policy decision, not a product one. It is set per market and per risk tier, and a case that does not resolve on one route steps up to another carrying what it already learned.
Coverage.
20,000+ templates, plus non-government documents where your risk model allows them. Acceptance settings are yours: which document types, which issuing countries, what quality threshold.
Reject a valid document and you lose a customer who did nothing wrong and knows it.
Reject a valid document and you lose a customer who did nothing wrong and knows it. Accept an invalid one and you have onboarded someone under a name that is not theirs. The second is worse, but the first happens more often and is invisible, which is why it goes unmanaged.
Built to be configured, not locked in.
We run several document engines and route per issuing country, to the engine built for that country's documents rather than on a single contract. When a market's document set changes, routing adjusts. Your integration does not.
Two audiences.
A document that fails to read is a customer you lose at the door, not an edge case to shrug off.
The image, the extracted data, the checks that ran, and what each returned.
Why us.
We route per issuing country to the engine built for that country's documents, so no single market's weakness is baked into your integration.