SAP AI Agent · SD · Quotations Configurable
Design scenario · how the agent is configured to work
Why it matters
Customers send RFQs as emails, PDFs and spreadsheets, often with their own part numbers or plain descriptions. Sales retypes each line, looks up prices and checks dates, and the fastest competitor wins.
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 RFQs from email, PDF or Excel.
Finds the customer and the right SAP materials.
Prices each line from SAP and simulates delivery.
Creates the quotation once sales reviews it.
Worked example
A customer sends an Excel RFQ with their own part numbers and one line described in words. Here is what the agent prepares.
Line 6 matches stainless 6-inch impeller IMP-0620-SS, which this customer ordered twice this year for P-200 pumps.
| Line | Price and date | Why |
|---|---|---|
| Lines 1–5 | Priced, on time | Customer price list with quantity scales |
| Line 6 | IMP-0620-SS, on time | Matched from description and order history |
| Line 7 | Priced, 10 Dec | Six days late; component lead time |
| Line 8 | No customer price | List price used; sales to confirm discount |
| Total | $84,260.00 | Within your margin floor |
The quotation is created and sent only after the sales rep reviews it.
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. Morgan (Sales rep) to review the draft quotation, asked Mon 2 Nov at 13:11.
Once approved, the quotation is created in SAP and the reply is ready for the sales rep to send.
| Step | Owner | Status |
|---|---|---|
| Read and match 8 lines | Agent | Done |
| Price and simulate dates | Agent | Done |
| Review draft | K. Morgan · Sales | Waiting |
| Create quotation | Agent | On hold |
Draft quotation for Lakeside Pumps totals $84,260.00. Line 7 can ship on 10 Dec, six days after the requested date, and line 8 has no customer price, so list price is used. Approve, or adjust first?
Illustration of how this agent's cases appear on the Artificio platform · names and values are fictional
Capabilities
Every RFQ read, matched and priced the same way, whatever format it arrives in.
Ownership
You map customers and regions to sales owners. Whoever answers first decides, and anything unassigned goes to the sales manager.
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 creating quotations where every line matches and is priced from the customer's price list, 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.
| RFQs | Email, PDF and Excel |
|---|---|
| Customers | Customer master and material info |
| Pricing | Conditions, price lists and scales |
| Availability | Stock, supply and lead times |
| Quotations | Created after approval |
|---|---|
| Customer replies | Drafted for sales to send |
| Case notes | Matches, prices and reasons |
| 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 mailbox, customers, pricing rules and approvers.
Prepare real quotes in shadow mode: the agent drafts, sales quotes.
Review the four measures, then add teams and approved automatic quotations.
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 RFQ and quotation process with our team, and see how a similar agent works on the Artificio platform.
Request DemoScope a pilot on one sales team and its RFQ mailbox in your SAP QA or sandbox system, with the four measures agreed up front.
Discuss an SAP pilot
