Industries/Shared service centres/Reconciliation Agent

Standardized cash recon factoryshared service centres.

Entity-specific tolerances run in one hub — Polish złoty files and US BAI2 files share a rules catalog with local thresholds. Playbooks in PDF; execution quality varies by team member.

Scenarios in shared service centres

  • Inconsistent bank file formats by country

    Each entity's banks send different field layouts. Agent encodes playbooks as rules with per-entity tolerances.

  • KYC document review capacity

    Entity controller approves exceptions locally.

  • Standardized cash recon factory

    September operating account activity includes outgoing wire WIRE-88213 to Halvorsen Trade Partners GmbH.

What the agent checks

  • Exact amount match within penny tolerance
  • Reference token match (wire ID, lockbox, check number)
  • Transposition heuristic when |bank − ledger| is divisible by 9
  • Deposit in transit when ledger precedes bank within N days
  • Duplicate payment detection on reference + amount
  • Corporate card aggregation vs individual bank debits

How it works

  1. 1

    Ingest bank and ledger

    Parse BAI2, MT940, CAMT.053, or CSV bank files alongside GL cash detail. Normalize signs, dates, and references to a common matching key.

  2. 2

    Auto-match within policy

    Pair lines by exact amount, by reference token, and by fuzzy description within date windows you configure. One-to-many and many-to-one sets are scored and ranked.

  3. 3

    Classify exceptions

    Flag transpositions when differences divide by nine, deposits in transit when bank date follows ledger date, outstanding checks when only GL shows the payment, and duplicate payments when the same reference hits twice.

  4. 4

    Propose journals

    Draft adjusting entries with memo text that quotes bank and ledger amounts. Route to approvers by threshold and account sensitivity.

  5. 5

    Close the period

    Publish a reconciliation summary with matched balance, open items, and approved adjustments — ready for controller sign-off.

Questions

Language support?

Document extraction works on common Latin scripts; pilot scoping covers languages you need.

Entity policy differences?

Rules are parameterized per entity — thresholds, approvers, and account mappings.

Does FinanceAI need live API access on day one?

No. Many pilots start with scheduled BAI2/MT940/CAMT.053 files and GL exports over SFTP. Read-only APIs come next once security review passes. The live demo uses the shared Aster Bank synthetic ledger.

What if Stellitron Intelligence is unavailable?

Every decision still runs through deterministic rules: amount matching, transposition checks, UBO percentage math, screening score thresholds, and flux materiality gates. Optional intelligence only improves extraction and narrative.

More agents for Shared service centres

Reconciliation Agent in other industries

Run it on your own document

Upload a dummy bank statement, KYC pack, or trial balance. Agents read it, apply policy checks, and show each step before a human would approve.