SAP AI Agent · MM-IM · Goods receipt Configurable
Design scenario · how the agent is configured to work
Why it matters
Trucks arrive faster than receivers can key packing slips. Receipts post a day late, stock looks short in MRP, invoices block for missing receipts and wrong deliveries are found after the supplier is paid.
How it works
The same four steps as every Artificio agent. The agent does the research and the paperwork; your teams make the decisions.
Reads packing slips and delivery notes from a photo, scan or email.
Matches every line to the right PO line.
Flags over-, under- and wrong deliveries at the dock.
Posts the goods receipt once the receiver confirms.
Worked example
A delivery of fasteners arrives with six lines. One line is over-delivered. Here is what the agent finds.
Line 40 is 200 EA over the open quantity, beyond the 5% delivery tolerance. The other five lines match quantity and batch.
| Line | Receive | Why |
|---|---|---|
| 10–30 | As shipped | Quantity and batch match the PO |
| 40 | 1,000 of 1,200 | Over tolerance; 200 to return or confirm with buyer |
| 50 | As shipped | Matches |
| 60 | As shipped | Goes to quality inspection per material setting |
| Duplicate check | None found | No receipt yet for delivery note 66120 |
The receipt posts only after the receiver confirms the counts. The extra 200 are held for the buyer to decide.
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 J. Ortiz (Receiver) to confirm counts, asked Mon 2 Nov at 07:50.
Once confirmed, the receipt posts for 1,000 EA on line 40 and the buyer decides on the extra 200.
| Step | Owner | Status |
|---|---|---|
| Read and match 6 lines | Agent | Done |
| Confirm counts | J. Ortiz · Receiving | Waiting |
| Post goods receipt | Agent | On hold |
| Decide on 200 extra | Buyer | Scheduled |
Delivery note 66120 matches PO 4500091544. Line 40 shows 1,200 EA against 1,000 open. Confirm the counts and receive 1,000, holding 200 for the buyer?
Illustration of how this agent's cases appear on the Artificio platform · names and values are fictional
Capabilities
Every delivery checked against the PO before it enters stock.
Ownership
You map plants and purchasing groups to owners. Whoever answers first decides, and anything unassigned goes to the receiving lead.
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 receipts where every line matches the PO within tolerance, 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.
| Packing slips | Photos, scans and emails |
|---|---|
| Purchase orders | Open lines, tolerances and dates |
| Inbound deliveries | ASNs where suppliers send them |
| Material data | Batches, units and inspection settings |
| Goods receipts | Posted after receiver confirmation |
|---|---|
| Variance cases | Sent to buyers and quality |
| Case notes | Slip image filed with the receipt |
| Responses | Every SAP response recorded on the case |
ScopeThe exact interfaces, objects and fields in scope are confirmed for your SAP release and deployment during technical discovery. S/4HANA Cloud Public Edition is reviewed case by case, and some landscapes may need additional configuration.
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 plants, suppliers, tolerances and receivers.
Read real slips in shadow mode: the agent matches, receivers post.
Review the four measures, then add docks and approved automatic receipts.
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 receiving process and packing slips with our team, and see how a similar agent works on the Artificio platform.
Request DemoScope a pilot on one dock and your top suppliers in your SAP QA or sandbox system, with the four measures agreed up front.
Discuss an SAP pilot
