Document Verification Agent AI

Invoked when: document set is assembled by the Loan Origination Agent AI

• –Extracts all structured data fields from each document type — salary slips (employer name, employer UEN, gross salary, deductions, net salary, pay period, employee name), bank statements (account holder name, account number, bank name, bank code / SWIFT BIC, statement period, opening and closing balances), IRAS Notice of Assessment (NOA) (filed income, tax paid, assessment year, NRIC / tax ID), and business documents (GST registration number, turnover from IRAS GST filing, ACRA UEN) — using OCR with confidence scoring per extracted field.
• –Flags fields where OCR confidence is below the configured threshold — poor scan quality, low-contrast print, handwritten fields — and marks these as requiring human verification rather than using the low-confidence extracted value in downstream calculations. A field the agent cannot reliably read is better flagged as unread than passed forward as a wrong value.

Invoked on each document as part of the verification pass

• –Cross-checks document data against authoritative external sources: employer UEN on salary slips against ACRA records; employer GST registration against IRAS for the stated employer name; bank SWIFT BIC against the MAS bank code / SWIFT BIC directory. Where the document's stated details do not match the authoritative record, the discrepancy is flagged as a potential fabrication signal — specific field, expected value from the authoritative source, value stated on the document.
• –Checks the document against the forgery pattern library — known templates used in prior fraud cases: salary slip formats with specific watermark placements or font combinations associated with previously identified forgeries, income certificate formats from institutions that the fraud team has flagged, or document structures that match known synthetic income document patterns.
• –Does not authenticate physical document features — ink, paper, embossing, watermark UV response. Pattern detection is data-driven, not forensic.

Invoked after OCR extraction is complete

• –Checks every extracted document against the document policy requirements: salary slips must be from the last 3 months (or as configured per product), bank statements must cover the required period, IRAS Notice of Assessment must be for the assessment year specified in the product policy, and business registration documents must not have a lapsed validity date. Policy misses are documented with the specific requirement and the actual document date/status.
• –Cross-checks field consistency across documents: name on the salary slip vs name on the national ID / tax identification number vs name on the bank statement; income declared on the salary slip vs income shown in the bank credits; stated employer on the application form vs employer named on the salary slip. Each discrepancy is flagged with the conflicting fields and values from each document.
• –Produces a structured exception log — every exception with the document it was found in, the specific field, the policy requirement or expected value, the observed value, and a severity classification (Minor / Material / Fraud flag). The exception log is the handoff document to the credit officer who must resolve each exception before the underwriting agent is invoked.