HomeAutomationAccounting Automation

Specialty · Automation / 10

Automate pre-accounting
document by document

Document intake, data capture and payment matching run automatically — without GL account coding. That stays with your tax advisor. We clear away the prep work, not the advisor.

Request document-flow check

Automatisierte Belegverarbeitung in der vorbereitenden Buchhaltung

Our approach

Deterministic where possible, AI only for edge cases.

A permanent agent pushing every document through a language model is expensive and hard to audit. We invert it: amount and invoice-number matching runs on plain rules — no model, no token cost, reproducible results. AI is used only where something genuinely needs to be read and interpreted. Anything the system is unsure about lands in a human review queue. Control stays with you.

Alexander OhlFounder · Pragma-Code

Before / After

What changes at month-end.

The document takes the same route — a human just no longer walks it by hand.

Document flow compared

Pre-accounting

Before · manual

Document intakeScattered across several inboxes

Data captureTyped in field by field

Payment statusTracked by hand

Payment matchingBank statement against a stack of invoices

Missing documentsOnly noticed by the tax advisor

TraceabilityIn one person’s head

After · automated

Document intakeOne channel, straight into the ERP

Data captureAI extracts, humans review edge cases

Payment statusPaid / outstanding with due date detected

Payment matchingRule-based, incl. batch payments

Missing documentsFlagged automatically for follow-up

TraceabilityAudit log for every action

Building blocks · 06

What we automate.

Six building blocks that carry pre-accounting together — each introducible on its own.

Consolidated intake

Invoices from a mailbox, scan or direct upload land in your ERP automatically — instead of scattered across inboxes.

AI data capture

Supplier, document number, date, amount and payment terms are extracted and matched against your master data.

Paid or outstanding?

Card, PayPal and subscriptions are debited automatically anyway. The system tells already-paid from outstanding-with-due-date.

Confidence routing

Confident cases pass through, uncertain ones go to the review queue. The threshold rises as trust in the system grows.

Payment matching

Bank movement meets open item — rule-based via amount and invoice number. Batch payments are resolved by subset search.

Spot missing documents

A debit without a matching document is flagged for follow-up — before your advisor has to ask.

Framework · 04

What we work with.

No exclusive tool lock-in — we dock onto whatever you already run.

Your ERP

Connected via your system’s API — Billomat, lexoffice and sevDesk are examples, not a requirement.

Your tax advisor

GL account assignment stays where it belongs: in your advisor’s DATEV module.

GDPR & DPA

Data-processing agreement, least-privilege access, processing in an EU region.

Audit log

Every automated action logged with time, trigger and result — traceability in the spirit of GoBD.

Fixed-price packages · 03

Three fixed-price packages — from check to operations.

Clearly defined scope, fixed price, defined outcome. Every package starts with a free intro call.

"Der Beleg-Check"

Analysis

890€

approx. 1 week

Know what can be automated: your document flow mapped and assessed — before you invest.

What's included

Your document flow mapped in a video call

ERP and mailbox integration feasibility check

Rated by automation potential and effort

Implementation recommendation as a document

Fully credited if you book the pilot

Request

Recommended

"Der Beleg-Pilot"

Implementation

4.900€

3–4 weeks

Intake and capture in production — starting in shadow mode so you can compare.

What's included

Intake consolidated and connected to your ERP

AI capture incl. supplier matching

Review queue for edge cases set up

Shadow mode: nothing is written without your approval

Documentation + handover video, 30 days of adjustments

Request pilot

"Beleg-Automation Scale"

Programme

from9.900€

6–10 weeks

The full chain through to payment matching — including step-by-step partial autonomy.

What's included

Payment matching: bank ↔ open item

Batch payments resolved via subset search

Missing documents detected for follow-up

Audit log and monitoring in operations

Confidence thresholds raised step by step

Request

Process · 05 Steps

From a stack of documents to a checked data set.

Introduced step by step — the system watches first, then takes over.

Map the document flow

Which document types, what volumes, which special cases? And who does what by hand today?

Integration

Connect mailbox, scan folder and ERP — e.g. Billomat, lexoffice or sevDesk.

Shadow mode

The system proposes but writes nothing. You compare against how you work today.

Partial autonomy

Confident cases go through, the rest to the review queue. We tune the threshold together.

Operations & audit log

Every automated action is logged and traceable — for you and for your tax advisor.

FAQ · Frequently Asked

Questions on document automation.

The points that come up in almost every intro call.

Does this replace my tax advisor?

No — by design. We automate pre-accounting only: collecting documents, capturing data, matching payments. The bookkeeping itself, GL account assignment and the annual accounts stay with your tax advisor. The difference is that they receive a clean, complete data set instead of a stack of documents.

Why don’t you assign GL accounts (e.g. SKR03)?

Because in many SMBs it is already solved: the tax firm handles coding inside its DATEV module, often with learned per-supplier rules. Automating that assignment a second time in parallel creates two versions of the truth and an extra source of error — with no real time saved. The effort sits upstream of coding, not in it.

What happens when the AI is unsure?

Then nothing happens automatically. Every document gets a confidence score; below the agreed threshold the case goes to a review queue and a human decides. The threshold starts deliberately strict, so a lot gets reviewed. Only once you see the decisions holding up is it raised step by step.

How are batch and partial payments handled?

A batch payment — one transfer settling several invoices — is resolved by subset search: the system looks for the combination of open items whose sum exactly matches the payment. Partial payments do not need to be solved by the automation at all; the ERP handles them itself via the remaining open balance.

What about GoBD, GDPR and data location?

Every automated action is logged with time, trigger and result — that provides the traceability GoBD requires; the audit-proof recording itself is done by your ERP or your tax firm. On data protection we work with a data-processing agreement, least-privilege access and processing in an EU region.

What does ongoing operation cost?

Considerably less than many expect — because the core is not AI. Payment matching runs purely on rules over amount and invoice number and incurs no model cost. A language model is called only for extraction and edge cases. Actual running cost depends on document volume and is quantified concretely in the document-flow check.

Related Insights

Done with the document stack?

We look at your document flow and tell you which steps can be automated today — and which are better left to humans.

Request document-flow check

Automate pre-accounting
document by document

Deterministic where possible, AI only for edge cases.

What changes at month-end.