Analytics Legends The knowledge platform for SAP Analytics
Academy module

The Semantic Layer as LLM Context

The Semantic Layer as LLM Context — Analytics Legends section illustration for the SAP Analytics knowledge base (concepts, studies, Academy)

As of 2026-09-25

Edited by , sole editor and publication director — 27 years in the SAP ecosystem. How these pages are produced, and where automation is used.

Reframes SAP Datasphere business-layer modelling (dimensions, facts, the Analytic Model) as literal LLM context, using SAP's own documented JustAsk pipeline: semantic search over indexed model metadata in a customer-specific Vector DB, LLM-generated OData/SQL, and HANA Gateway execution under principal propagation. Explains why the Analytic Model — SAP's 'go-to analytic consumption entity for both Data Layer & Business Layer' — is the object an LLM-driven query actually reads, and cross-validates the discipline (descriptions as machine input, synonyms, value dictionaries, join cardinality) against Databricks Genie's independent best-practice guidance inside SAP Business Data Cloud. Three exercises rewrite labels for machine legibility, design a scoped analytic model, and diagnose model sprawl. Builds on M346; feeds M348 and M349.

What you will learn

  • Explain why a language model depends on the semantic layer absolutely, with the context-window argument from M333
  • Describe SAP's Analytic Model as the documented consumption entity for both the Data Layer and Business Layer, and its role in JustAsk
  • Trace JustAsk's three-step pipeline: semantic search over indexed model metadata, LLM query generation, HANA Gateway execution under principal propagation
  • Write dimension, measure and KPI descriptions precise enough for a retrieval step to disambiguate correctly
  • Use Databricks Genie's independent best-practice guidance (descriptions, synonyms, value dictionaries, join cardinality) to cross-check a Datasphere business layer design

Module overview

Who this is for. You have built dimensions, facts and analytic models in SAP Datasphere for dashboards and stories. This module reframes the same modelling work for a second consumer that reads it just as literally as SAP Analytics Cloud does: a large language model, through SAP's JustAsk and Joule pipeline. It assumes M346 (AI-ready data) and feeds M348 (natural-language query) and M349 (vector search on analytic data).

Prerequisites

  • M346 (AI-Ready Data) or equivalent understanding of catalog metadata and lineage
  • Hands-on experience building analytic models, dimensions and facts in SAP Datasphere or BW/4HANA
  • M333 (AI & LLM Fundamentals) or working knowledge of context windows and grounding

Outcomes

  • Design a business layer object legible to both a human building a story and an LLM generating a query.
  • Explain JustAsk's pipeline precisely enough to diagnose why a specific question returns the wrong model's answer.
  • Apply cross-platform evidence (SAP JustAsk plus Databricks Genie) to justify semantic-layer investment to a sceptical client.
  • Diagnose and remediate analytic-model sprawl as a semantic-layer, not a prompting, problem.

Full module available to members. The full module adds: the decision framework · the end-to-end scenario walkthrough · the KPI scorecard · the anti-patterns · the code blocks · the knowledge check · the diagrams.

Open in the app →

Next in this track