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
@sap-ai-sdk/orchestration@sap-ai-sdk/orchestrationThe Orchestration Service client of SAP's AI SDK, which applies templating, grounding, filtering and masking around a model call rather than in the application.sap official, cap 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.
cap-llm-plugincap-llm-pluginGenerative AI in a CAP application with the sensitive fields anonymised through SAP HANA before the prompt leaves, so the model never sees the confidential half.independent, cap does the anonymisation in SAP HANA before the prompt leaves the database, which is a different place to do the same job.
Artifacts
Content
Seen working
Every CDS service in both samples is marked `@requires: 'any'` and left publicly accessible, which the README says simplifies the testing and deployment process, and it asks for proper authentication mechanisms to be applied in their place.
Details
Coverage
For your agent
- Ref
capability:data-masking- JSON
- /capabilities/data-masking.json
- MCP
- Connecting an agent