Prompt management

Keeping the prompts an application sends to a model as templates with placeholders, stored and versioned apart from the code that calls them, so a change of wording is not a deployment. What people conflate under it: the template filled at runtime, the registry it lives in, and the orchestration step that fills it.

Overview

InBTP/BAIPassessed
SAP SHIPS

SAP AI Core carries both halves: templating as a module of its orchestration service, and the Prompt Registry, where a template is stored and versioned and then referenced from an orchestration call.

Not covered: At the template. What a prompt should say, and whether it still behaves after a model change, is not in the service; that question sits with agent evals.

THE COMMUNITY ADDS

No community artifact is documented here.

InCAPassessed
SAP SHIPS

@sap-ai-sdk/prompt-registry is the client for the registry and @sap-ai-sdk/orchestration fills a template at call time; nothing in @sap/cds knows what a prompt is.

Not covered: At the SDK call. The template is filled in the service; where it is stored, who may change it and how a change is reviewed are the registry's, on the BTP door.

THE COMMUNITY ADDS

A prompt registry inside the application: cds-plugin-llm registers templates by name for CAP handlers, can load them from a Git repository so a wording change goes through pull request review, and pins which version a call gets.

Artifacts4

Group by4 of 4 artifacts
ArtifactSignals
CDS plugins1
@saptarishi/cds-plugin-llmCAP service kind putting eleven model providers behind one API
Signals
none
Packages2
@sap-ai-sdk/orchestrationOrchestration Service client for templating, grounding and masking
Signals
none
@sap-ai-sdk/prompt-registryClient for prompts kept in SAP's prompt registry
Signals
none
Services1
SAP AI CoreAI runtime on BTP with the Generative AI Hub
Signals
none

Content2

Group by
Piece, what it offers
🟣 Enable Your AI application to Run on Multiple Models to Ensure Resilience and Compliance
YouTube — SAP Developers playlists, SAP Developers, Talk
Prompt Templating
SAP BTP AI Best Practices, SAP, DocThe reasoningA reference
🟣 Enable Your AI application to Run on Multiple Models to Ensure Resilience and Compliance
YouTube — SAP Developers playlists, SAP Developers, Talk
Prompt Templating
SAP BTP AI Best Practices, SAP, DocThe reasoningA reference

Seen working3

ArtifactSignals
Samples3
SAP BTP AI Best Practice Demo - Prompt Registry - CAPCAP samples using SAP AI Core's Prompt Registry for templates
Functional boundary
SAP BTP AI Best Practice Demo - Prompt Templating - CAPCAP samples filling a prompt template sent to SAP AI Core
Functional boundary
sap-btp-ai-best-practicesSample implementations for AI-powered applications on SAP BTP
none

Details

Coverage
statecore only, BTP/BAIP
assessed
state in CAPcore and community, assessed
also inCAP
For your agent
Ref
capability:prompt-management
JSON
/capabilities/prompt-management.json
MCP
Connecting an agent