Assigned reviewers
Decisions go to named owners or authorized teams, with reminders, and every email links back to the case.
SAP AI Agent · FI · Intercompany Configurable
Design scenario · how the agent is configured to work
Why it matters
Each company code posts its side at a different time, in a different currency, sometimes to the wrong partner. The differences are found when consolidation won't balance, and controllers trade spreadsheets to explain them.
How it works
The same four steps as every Artificio agent. The agent does the research and the paperwork; your teams make the decisions.
Compares intercompany balances for every company pair.
Matches documents across the pair.
Classifies every difference by cause.
Proposes the correcting entry for both controllers.
Worked example
Company codes 1000 and 2000 are $48,600 apart. Here is what the agent finds.
The invoice reached company code 2000's AP mailbox on 29 Oct but was never posted. The receiving PO and goods receipt exist in 2000.
| Cause | Amount | Proposed fix |
|---|---|---|
| Not posted in 2000 | $48,600.00 | Post the payable in 2000 |
| Timing, posted 1 Nov | $2,140.00 | None: matches in November |
| FX rate difference | $312.40 | Post to FX difference per policy |
| Wrong trading partner | $0.00 net | Reclass in 2000 from partner 3000 to 1000 |
| Matched | 312 documents | No action |
Corrections post only after both controllers approve. Timing differences are left to match in the next period.
Design scenario · names and values are fictional and depend on your SAP configuration
Inside the platform
The case shows who it is waiting for, what happens next, what the agent checked and exactly what each person is approving.
Waiting for K. Schmidt (Controller, 2000) to approve posting the $48,600 payable, asked Mon 2 Nov at 05:40. A. Romero (Controller, 1000) has approved.
Once both have approved, the entry posts in 2000 and the pair is re-matched before consolidation.
| Step | Owner | Status |
|---|---|---|
| Match 318 documents | Agent | Done |
| Approve · company 1000 | A. Romero | Approved |
| Approve · company 2000 | K. Schmidt | Waiting |
| Post and re-match | Agent | On hold |
Invoice 90051877 from company code 1000 for $48,600.00 was never posted in 2000. The PO and goods receipt exist. Post the payable in October?
Illustration of how this agent's cases appear on the Artificio platform · names and values are fictional
Capabilities
Every company pair reconciled the same way, every period.
Ownership
You map company codes to controllers. Corrections need both sides, and anything unassigned goes to group accounting.
Owners, rules and tolerances are configured to your organization and agreed for each deployment.
Controlled autonomy
The agent proves itself on your real work before it writes anything to SAP. The platform measures how often your people agree with it, so you decide when to give it more room, case type by case type.
The agent proposes every action but writes nothing to SAP. Your people decide, and each answer counts toward the agreement rate.
The required owners approve. The agent acts in SAP only when the last approval lands.
For case types you explicitly configure and approve, such as posting FX differences under your threshold to the agreed account, the agent acts on its own and reports back.
Governed agent runtime
What makes this agent different is its configuration: its instructions, the tools it may use and the policies it works under. Reviewers, approvals, versions and audit work the same way for every agent you add.
Decisions go to named owners or authorized teams, with reminders, and every email links back to the case.
Gathering data is kept separate from changing SAP. Action tools are controlled and can require human approval before they run.
Versions can't be edited, and each case keeps the version it started with, so a change never alters work in progress.
Recreations of Artificio platform screens
What we measure
Every pilot tracks the same four measures from day one, so the business case comes from your data, not ours.
For SAP teams
The agent reads and writes data through supported SAP interfaces, without modifying standard SAP objects and without replacing your existing governance.
| Balances | Intercompany accounts by trading partner |
|---|---|
| FI documents | Postings in both company codes |
| Billing and POs | Source documents behind each posting |
| Exchange rates | Rates used by each company code |
| Corrections | Posted after both controllers approve |
|---|---|
| Reclassifications | Trading partner corrections |
| Reports | Agreed balances by company pair |
| Responses | Every SAP response recorded on the case |
ScopeWorks on the trading partner and intercompany accounts in your SAP system. On SAP S/4HANA the agent can work alongside Intercompany Matching and Reconciliation where you use it.
Pilot approach
A focused pilot in your QA or sandbox system proves the agent on your own data before anything reaches production.
Review SAP edition, interfaces, authorizations and representative data.
Agree the company pairs, tolerances, controllers and approval rules.
Reconcile one period in shadow mode: the agent explains, controllers correct.
Review the four measures, then add pairs and approved automatic corrections.
Frequently asked questions
Security & compliance
ISO 27001:2013 certified, SOC 2 Type 2 compliant, GDPR and HIPAA ready. Every agent action is logged and auditable, and SAP credentials stay in the platform's integration accounts.
See it working
Talk through your intercompany close and company pairs with our team, and see how a similar agent works on the Artificio platform.
Request DemoScope a pilot on your highest-volume company pairs in your SAP QA or sandbox system, with the four measures agreed up front.
Discuss an SAP pilot