Government and migration · Specified

The decision: Grant or refuse

The letterhead was genuine. It had just been used before.

A visa application with qualifications, employment references, bank letters and relationship evidence, assembled across three jurisdictions and two languages. The statutory test is specific. The evidence has to meet it, and be what it claims to be.

This is not a customer case study

There is no production tenant and no paying customer. Every document, finding and verdict on this page is synthetic, written to show what the forensic core examines and what a cited verdict looks like. No accuracy or detection figure appears here, because no pilot has produced one under a methodology we would publish beside it. The rule set for this sector is specified, not encoded. The forensic findings below run on any document bundle today; the sector rules do not exist yet.

What arrives

The bundle as it lands, before anybody has read it.

Qualification certificates3 documents, 2 languages
Employment references4 letters, on letterhead
Bank letters2 documents, PDF
Identity documents4 documents, images
Relationship evidence22 items, mixed
Translations5 documents, certified

What gets examined

The forensic core runs on every document in the bundle regardless of sector. None of these questions changes when the industry changes.

Document lineage Fabrication detection Template comparison Image forensics Sender authentication Registry resolution Cross-file reuse Entity resolution Cross-document reconciliation

What comes back

Every finding carries at least two anchors drawn from at least two separate documents, and the benign explanation that would account for it. A pattern appearing once in one place is not reported at all.

A qualification certificate does not match the institution’s issued format Template comparison

Seal placement, crest resolution and the award wording differ from the format the named institution has used for the year printed on the document. The differences are small and consistent with a reconstruction from a photograph.

Anchored to
  • Qualification certificate 2, seal and crest region
  • Certified translation, page 1, award wording

The benign explanation: Institutions change certificate design without announcement, replacement certificates are issued in later formats, and a genuine reprint can look nothing like the original.

An employment reference reuses letterhead seen on an unrelated application Cross-file reuse

The letterhead raster, including a compression artefact in the logo, is byte-identical to that on a reference letter filed with an unrelated application from a different applicant and a different stated employer.

Anchored to
  • Employment reference 3, letterhead raster fingerprint
  • Application 2026-0088, employment reference, same fingerprint

The benign explanation: A shared preparation service producing letters for multiple applicants would explain this entirely, and using an agent is not misconduct.

The statutory test is not met on the evidence present Sufficiency

The encoded criterion requires continuous evidence across a defined period. The bundle covers the period with a gap of five months for which nothing is supplied.

Anchored to
  • Relationship evidence, complete item inventory with dates
  • Encoded eligibility criterion, with citation to the instrument

The benign explanation: Evidence of an ordinary life is rarely continuous, and a gap is not an absence. This is a request for more, not an adverse conclusion.

The verdict

REVIEW

Two integrity findings and one sufficiency gap, each anchored twice. The application is not refused and the applicant is not scored. It returns to a case officer with the specific documents to test and the specific period to ask about.

This sector is the closest match to the rule structure already encoded: eligibility assessed against statutory criteria, with a review and appeal path on every decision, which means every decision has to be defensible on the record it was made on.

What it did not do

The same four constraints apply in every sector, and they are enforced in code rather than in policy.

No adverse decision

Nothing was declined, refused, held or approved by the platform. A person decides, on the record, with the reasoning in front of them.

Every sector

No score

No risk number, no ranking, no composite figure. The only number attached to a person is how many independent documents corroborate a fact about them.

Nowhere in the product

No single-source assertion

Two anchors from two documents, or the finding is not reported. This is the largest source of false positives in the category and the platform refuses to generate them.

Enforced at registration

No protected attributes

A detector referencing a protected attribute fails registration and the platform will not start. It is a structural guarantee rather than a policy.

Throws on load

How this gets tested on your own files

Hand us two hundred closed files. Settled claims, funded loans, granted applications, paid invoices, onboarded accounts. We examine them and show you the documents that lied, against outcomes you already know. It is the only honest way to evaluate this category, and it is the same motion in every sector on this page.

The other sectors

Only insurance is built. Every other sector is specified rather than shipped: the forensic core runs on any bundle today, and no rule set outside insurance has been encoded. [email protected]