Data masking

Replacing the personal or confidential values in a prompt with placeholders before it leaves for a model, and putting them back in the answer. Anonymisation, where the values are gone for good, and pseudonymisation, where they return, are the two forms; which fields count as sensitive is the application's question, not the module's.

Overview

InBTP/BAIPassessed 2026-09-14

SAP SHIPS

A module of the orchestration service in SAP AI Core: the prompt is masked before the model sees it, by anonymisation or pseudonymisation, and with pseudonymisation the placeholders in the response are unmasked again.

Not covered: At the prompt text. The module works on what is in the prompt it is handed, with the entity types chosen per call; anything a model reaches by another route is outside it.

Every provider behind this door is SAP's, so core-only is a assessment of the corpus rather than a quote from the core.

SAP AI Core

SourceSAP AI Launchpad — SAP BTP AI Best Practices, Technologieschecked 2026-09-14

THE COMMUNITY ADDS

No community artifact is documented here.

InCAPassessed 2026-09-14

SAP SHIPS

@sap-ai-sdk/orchestration carries the same masking module into a Node.js or CAP service, configured per call and per fallback configuration.

Not covered: At the call. What the SDK masks is what the orchestration service masks; the fields the application chooses to send are its own decision.

SourceOrchestration Chat Completion — SAP Cloud SDK for AI (JavaScript)checked 2026-09-14

THE COMMUNITY ADDS

cap-llm-plugin does the anonymisation in SAP HANA before the prompt leaves the database, which is a different place to do the same job.

cap-llm-plugin