SAP's own API Policy (§2.2.2) quietly restricts pointing autonomous AI at SAP over its APIs. Get the 1-page checklist and find out in 7 questions where your setup really stands — before it reaches production.
Free: the §2.2.2 Compliance Checklist for agentic AI on SAP — 1 page, printable.
✔ Done — open your checklist here. João will also follow up by email.
Work email preferred. No spam — the checklist, and occasional notes on governed AI in SAP. Unsubscribe anytime.
"SAP prohibits API use for … interaction or integration with (semi-)autonomous or generative AI systems that plan, select, or execute sequences of API calls … except through SAP-endorsed architectures."
Why it matters
The interface most tools drive SAP through — the ADT REST layer — is internal, not a Published API. Add an autonomous agent on top and you're squarely in §2.2.2 territory. The line between a safe developer tool and a policy problem is sharper than it looks:
Green
Local dev tooling. Dev system, your own authorizations, read-only. Same surface Eclipse already uses.
Amber
Tighten first. Write enabled, team use, or data leaving to an LLM. Add gates and get sign-off.
Red
Stop. Agentic AI on production SAP via a non-Published API, outside endorsed pathways.
Work with me
Three ways in — pick the one that matches where you are. No procurement circus to start.
First come, first served. Architects & dev leads preferred.
Opening soon — waitlist gets first slots and the checklist now.
Fits a training budget — one signature, no procurement.
Who's behind this
João Pace — SAP Manager & AI Adoption Lead. I lead SAP S/4HANA across four company codes and my company's AI adoption, and I build the connectors that let AI agents work with SAP safely. This checklist is the same one I run internally.