SAP AI Agent · Basis · SM37 · ST22 Configurable
Design scenario · how the agent is configured to work
Why it matters
Billing, MRP, interface and closing jobs fail at night. By the time someone reads the dump, the business is already waiting, and restarting the wrong job can do more harm than good.
How it works
The same four steps as every Artificio agent. The agent does the research and the paperwork; your teams make the decisions.
Cancelled, delayed and long-running jobs, plus new short dumps.
Reads the job log, the dump and recent changes.
Checks whether the job is safe to repeat.
Restarts after approval and checks the result.
Worked example
The nightly billing job cancels with a memory dump. Here is what the agent finds before the billing team starts work.
The variant was changed on 30 Oct and lost its billing date range, so the job selected every open delivery and ran out of memory.
| Check | Finding | Why |
|---|---|---|
| Dump | Memory exhausted in selection | Internal table grew past the memory limit |
| Variant | No date range since 30 Oct | Changed during month-end |
| Billing created? | None | The job failed before creating any billing documents |
| History | No failures before 30 Oct | Ran in about 12 minutes every night |
| Proposed restart | Restore range, restart once | Variant fixed first; then one restart |
The job is restarted only after the variant is fixed. Because no billing documents were created, a single restart won't duplicate anything.
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. Ruiz (Billing team) to confirm the date range for variant NIGHTLY, asked Mon 2 Nov at 02:20.
Once confirmed, Basis approves the restart. Billing for about 1,400 deliveries is waiting.
| Step | Owner | Status |
|---|---|---|
| Diagnosis | Agent | Done |
| Restore variant date range | J. Ruiz · Billing | Waiting |
| Restart job | Basis | On hold |
| Verify billing output | Agent | Scheduled |
Restore the billing date range in variant NIGHTLY to yesterday, as it was before 30 Oct, and restart the job?
Illustration of how this agent's cases appear on the Artificio platform · names and values are fictional
Capabilities
Every failure gets the same investigation, whenever it happens.
Ownership
You map jobs and failure types to teams. Whoever answers first decides, and anything unassigned goes to the Basis 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 restarting a job that failed on a lock when the failed run created nothing, 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.
| Background jobs | Status, logs, steps and history |
|---|---|
| Short dumps | Runtime errors with their context |
| System log | Related system messages |
| Documents | Output created by the failed run |
| Restarts | Approved restarts through the background processing interface |
|---|---|
| Variants | Changed by the job owner, with approval |
| Alerts | Diagnoses sent to the owning team |
| 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 jobs in scope, the owners, restart rules and approvals.
Watch real jobs in shadow mode: the agent diagnoses, Basis restarts.
Review the four measures, then add jobs and approved automatic restarts.
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 job monitoring and overnight operations with our team, and see how a similar agent works on the Artificio platform.
Request DemoScope a pilot on your business-critical jobs in your SAP QA or sandbox system, with the four measures agreed up front.
Discuss an SAP pilot
