Skip to content
W
GoBD-compliant §203 StGB-compliant Q1-Q2

Reconciliation Agent

Reconcile subledgers against general ledger - continuously instead of at period-end.

Matches subledgers against the general ledger, assigns open items, flags unexplainable differences and creates reconciliation reports - running throughout the month instead of only at month-end.

Score Dashboard

Agent Readiness 81-88%
Governance Complexity 21-28%
Economic Impact 74-81%
Lighthouse Effect 31-38%
Implementation Complexity 28-35%
Transaction Volume Monthly

What This Agent Does

Account reconciliation is the most time-intensive step in the month-end close. In a typical group, hundreds of accounts must be matched between subledger and general ledger. If a single balance does not match, the manual search begins - often under time pressure on the third working day after month-end.

The Decision Layer breaks every reconciliation into individual decision steps. Exact amounts are automatically assigned. Partial amounts and deviating references are recognised by AI via pattern matching. Only material differences that genuinely require human judgement are escalated.

The result: reconciliation runs continuously instead of as a period-end marathon. By month-end, 80-90% of accounts are already reconciled. The remaining clarification cases are documented and prioritised. The month-end close shortens by days, not hours.

Micro-Decision Table

Human
Rules Engine
AI Agent
Each row is a decision. Expand to see the decision record and whether it can be challenged.
Load account list Which accounts must be reconciled? Rules Engine

Configured account list

Decision Record

Rule ID and version number
Input data that triggered the rule
Calculation result and applied formula

Challengeable: Yes - rule application verifiable. Objection possible for incorrect data or wrong rule version.

Subledger/GL matching Does the subledger balance match the general ledger? Rules Engine

Numerical comparison

Decision Record

Rule ID and version number
Input data that triggered the rule
Calculation result and applied formula

Challengeable: Yes - rule application verifiable. Objection possible for incorrect data or wrong rule version.

Assign open items Can open items be uniquely assigned? Rules Engine

Exact amounts = R, partial match = A

Decision Record

Rule ID and version number
Input data that triggered the rule
Calculation result and applied formula

Challengeable: Yes - rule application verifiable. Objection possible for incorrect data or wrong rule version.

Flag differences Are the remaining differences explainable? AI Agent Auditor

Pattern matching against known difference causes

Decision Record

Model version and confidence score
Input data and classification result
Decision rationale (explainability)
Audit trail with full traceability

Challengeable: Yes - fully documented, reviewable by humans, objection via formal process.

Challengeable by: Auditor

Materiality assessment Is the difference material and requires clarification? Human Auditor

Judgement in the materiality assessment

Decision Record

Decider ID and role
Decision rationale
Timestamp and context

Challengeable: Yes - via manager, works council, or formal objection process.

Challengeable by: Auditor

Reconciliation report Is the report created and archived? Rules Engine

Formatted report per template

Decision Record

Rule ID and version number
Input data that triggered the rule
Calculation result and applied formula

Challengeable: Yes - rule application verifiable. Objection possible for incorrect data or wrong rule version.

Approval tracking Who has approved which account? Rules Engine

Workflow status tracking

Decision Record

Rule ID and version number
Input data that triggered the rule
Calculation result and applied formula

Challengeable: Yes - rule application verifiable. Objection possible for incorrect data or wrong rule version.

Continuous reconciliation Is reconciliation continued throughout the month? Rules Engine

Automatic repetition per configuration

Decision Record

Rule ID and version number
Input data that triggered the rule
Calculation result and applied formula

Challengeable: Yes - rule application verifiable. Objection possible for incorrect data or wrong rule version.

Decision Record and Right to Challenge

Every decision this agent makes or prepares is documented in a complete decision record. Affected parties (employees, suppliers, auditors) can review, understand, and challenge every individual decision.

Which rule in which version was applied?
What data was the decision based on?
Who (human, rules engine, or AI) decided - and why?
How can the affected person file an objection?
How the Decision Layer enforces this architecturally →

Prerequisites

  • ERP system with API access to general ledger (SAP FI, DATEV, Microsoft Dynamics or equivalent)
  • Configured account list with reconciliation obligation
  • Access to subledgers (receivables, payables, assets, bank)
  • Defined materiality thresholds per account group

Governance Notes

GoBD-compliant §203 StGB-compliant

GoBD-relevant: reconciliation reports are part of the procedural documentation and must be archived immutably. Traceability of every assignment decision is mandatory per AO Paragraph 147 (retention obligation). The statutory auditor reviews reconciliation as part of the financial audit - complete reports significantly shorten the audit.

Every assignment decision is documented in the decision log with rule, version and confidence. During a tax audit, it is traceable not only that reconciliation was performed but how every individual assignment was made.

§203 StGB-relevant data is encrypted end-to-end and never passed to AI models in plain text.

Process Documentation Contribution

The Reconciliation Agent documents for the GoBD procedural documentation: which accounts were reconciled when, which assignment rules were applied, which differences were identified and how they were resolved. The reconciliation reports form a central component of the procedural documentation for tax audits.

Infrastructure Contribution

The Reconciliation Agent builds the reconciliation pattern reused across domains: bank reconciliation, intercompany reconciliation and consolidation use the same matching engine. The continuous reconciliation logic (running throughout the month instead of at period-end) becomes the standard for all close agents.

Builds Decision Logging and Audit Trail used by the Decision Layer for traceability and challengeability of every decision.

Does this agent fit your process?

We analyse your specific finance process and show how this agent fits into your system landscape. 30 minutes, no preparation needed.

Analyse your process

Frequently Asked Questions

Does the agent fully replace manual account reconciliation?

No. The agent handles routine assignments and identifies differences. Material discrepancies requiring human judgement are escalated with context and a suggested resolution. The final sign-off remains with the clerk.

What does continuous reconciliation mean in practice?

Instead of reconciling all accounts in a marathon session at month-end, matching runs throughout the month. New postings are continuously assigned. By period-end, 80-90% of accounts are already complete - the month-end close shortens by days.

How does the agent handle partial payments and split amounts?

Exact amounts are assigned rule-based. For partial amounts and deviating references, the agent uses pattern matching with a confidence score. Assignments below the configured threshold are escalated for manual review.

What Happens Next?

1

30 minutes

Initial call

We analyse your process and identify the optimal starting point.

2

1 week

Discover

Mapping your decision logic. Rule sets documented, Decision Layer designed.

3

3-4 weeks

Build

Production agent in your infrastructure. Governance, audit trail, cert-ready from day 1.

4

12-18 months

Self-sufficient

Full access to source code, prompts and rule versions. No vendor lock-in.

Implement This Agent?

We assess your finance process landscape and show how this agent fits your infrastructure.