{"ref":"capability:prompt-management","page":"/capabilities/prompt-management","json":"/capabilities/prompt-management.json","generated":"2026-10-26","drafted_with_ai":true,"entity":{"id":"prompt-management","name":"Prompt management","domain":"ai-and-agents","ecosystems":["btp","cap"],"universal":true,"description":"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.","short":"Prompt templates stored and versioned apart from the code","core_coverage":{"state":"core-only","assessed_at":"2026-09-14","what_core_does":"[SAP AI Core](artifact:btp-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.","where_it_stops":"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](capability:agent-evals).","sources":[{"url":"https://btp-ai-bp.docs.sap/docs/technical-view/generative-ai/plain/prompt-templating","title":"Prompt Templating — SAP BTP AI Best Practices","checked":"2026-09-14","quote":"When using AI core this is achieved using the prompt registry."},{"url":"https://btp-ai-bp.docs.sap/docs/technology/sap-ai-launchpad","title":"SAP AI Launchpad — SAP BTP AI Best Practices, Technologies","checked":"2026-09-14","quote":"This feature lets you compose prompts with placeholders that are filled during inference."}]},"coverage_by_ecosystem":{"cap":{"state":"core-and-community","assessed_at":"2026-09-14","relationship":"unassessed","what_core_does":"[@sap-ai-sdk/prompt-registry](artifact:sap-ai-sdk-prompt-registry) is the client for the registry and [@sap-ai-sdk/orchestration](artifact:sap-ai-sdk-orchestration) fills a template at call time; nothing in [@sap/cds](artifact:sap-cds) knows what a prompt is.","where_it_stops":"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.","community_adds":"A prompt registry inside the application: [cds-plugin-llm](artifact:saptarishi-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.","sources":[{"url":"https://sap.github.io/ai-sdk/docs/js/orchestration/chat-completion","title":"Orchestration Chat Completion — SAP Cloud SDK for AI (JavaScript)","checked":"2026-09-14","quote":"Additionally, it provides features like templating, content filtering, grounding and more to enhance the interaction with generative AI models."}]}},"drafted_with_ai":true,"history":[{"date":"2026-10-26","field":"coverage_by_ecosystem.cap.state, coverage_by_ecosystem.cap.relationship, coverage_by_ecosystem.cap.community_adds","from":"core-only","to":"core-and-community, relationship unassessed, community_adds names cds-plugin-llm","reason":"Reassessed against the graph (check:capabilities): an independent cds-plugin provides this capability behind the CAP door."},{"date":"2026-10-26","field":"core_coverage.note","from":"Every provider behind this door is SAP's, so core-only is a assessment of the corpus rather than a quote from the core.","to":"(removed)","reason":"Reassessed against the graph (check:capabilities): the note was a claim about who provides, which the option list derives."}]},"sap_delivery":{"door":"btp","all":{"built_in":[],"documented_pattern":[],"announced":[],"packages":[{"ref":"artifact:btp-ai-core","name":"SAP AI Core","json":"/artifacts/btp-ai-core.json"}]},"by_flavor":{}},"edges":{"use_cases":[],"shared_tasks":[],"related_tasks":[],"options":[{"ref":"artifact:sap-ai-sdk-orchestration","name":"@sap-ai-sdk/orchestration","json":"/artifacts/sap-ai-sdk-orchestration.json","ecosystem":"cap","origin_ring":"sap-official"},{"ref":"artifact:sap-ai-sdk-prompt-registry","name":"@sap-ai-sdk/prompt-registry","json":"/artifacts/sap-ai-sdk-prompt-registry.json","ecosystem":"cap","origin_ring":"sap-official"},{"ref":"artifact:saptarishi-cds-plugin-llm","name":"@saptarishi/cds-plugin-llm","json":"/artifacts/saptarishi-cds-plugin-llm.json","ecosystem":"cap","origin_ring":"independent"},{"ref":"artifact:btp-ai-core","name":"SAP AI Core","json":"/artifacts/btp-ai-core.json","ecosystem":"btp","origin_ring":"sap-official"}],"samples":[{"ref":"artifact:sap-samples-btp-ai-bp-prompt-registry-cap","name":"SAP BTP AI Best Practice Demo - Prompt Registry - CAP","json":"/artifacts/sap-samples-btp-ai-bp-prompt-registry-cap.json"},{"ref":"artifact:sap-samples-btp-ai-bp-prompt-templating-cap","name":"SAP BTP AI Best Practice Demo - Prompt Templating - CAP","json":"/artifacts/sap-samples-btp-ai-bp-prompt-templating-cap.json"},{"ref":"artifact:sap-samples-sap-btp-ai-best-practices","name":"sap-btp-ai-best-practices","json":"/artifacts/sap-samples-sap-btp-ai-best-practices.json"}],"explained_by":[{"ref":"content:devtoberfest-2026-ai21-multiple-models","name":"🟣 Enable Your AI application to Run on Multiple Models to Ensure Resilience and Compliance","json":"/content/devtoberfest-2026-ai21-multiple-models.json"},{"ref":"content:btp-ai-bp-prompt-templating","name":"Prompt Templating","json":"/content/btp-ai-bp-prompt-templating.json"}],"normative_context":[]}}