Analytics Legends The knowledge platform for SAP Analytics
Academy module

Databricks Mosaic AI on BDC — ML on SAP Data Products

Databricks Mosaic AI on BDC — ML on SAP Data Products — 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.

For consultants scoping or reviewing a Databricks-side build (agent or ML model) against SAP data shared zero-copy via Business Data Cloud Connect. Covers the OpenSharing setup sequence and security model (GA October 2025), why semantic metadata syncing into Unity Catalog matters specifically for ML, Mosaic AI Agent Framework's narrow value proposition (Delta tables, registered ML models, vector search in one reasoning loop) versus a simpler direct chain, building tools via Unity Catalog functions and Vector Search with MCP as a bridge to SAP-exposed tools, Unity Catalog/Unity Gateway governance as the Databricks-side equivalent of a Datasphere DAC review, model signatures tied to data-product version pinning, and the bidirectional write-back path that returns Databricks-computed results to SAP as governed assets. Closes with the Mosaic-AI-or-SAP-AI-Core decision and three exercises.

What you will learn

  • Explain how SAP Business Data Cloud Connect moves SAP data into Databricks via zero-copy Delta Sharing, including the OpenSharing setup sequence and security model
  • Explain why semantic metadata syncing into Unity Catalog (comments, keys, governance tags) matters specifically for ML workloads, not just chat agents
  • State Mosaic AI Agent Framework's narrow value proposition and decide when it is the right runtime versus a simpler direct chain
  • Build agent tools on SAP data using Unity Catalog functions and Mosaic AI Vector Search, and explain MCP's role in reaching SAP-exposed tools
  • Apply Unity Catalog and Unity Gateway governance as the Databricks-side equivalent of a Datasphere DAC review
  • Design a write-back path so a Databricks-computed result (score, forecast, flag) reaches SAP-side consumers as a governed asset

Module overview

Who this is for. You have completed M343 (data products for AI agents) and your client's data-science team wants to build machine learning and agents on Databricks against SAP data — not a Joule agent, a Mosaic AI agent, run by a team that may never open the BDC catalog UI. This module covers that build: how SAP data actually reaches Databricks without copying it, what lands in Unity Catalog and why that matters for ML specifically, when Mosaic AI Agent Framework is the right runtime versus a simpler chain, and how to keep governance intact across a boundary that used to be a hard system edge and is now a configured connection.

Prerequisites

  • M343 (SAP Business Data Cloud Data Products for AI Agents) or equivalent understanding of data products and governance metadata
  • Working familiarity with Databricks fundamentals: Unity Catalog, Delta Lake, workspace concepts
  • Basic understanding of zero-copy sharing / Delta Sharing (C016)

Outcomes

  • Trace a real zero-copy share and verify, not assume, that semantic metadata synced into Unity Catalog.
  • Decide correctly between Mosaic AI Agent Framework and a simpler direct chain for a given agent's requirements.
  • Configure Unity Catalog governance to mirror SAP-side governance tags rather than leaving default grants in place.
  • Design a write-back path that returns a Databricks-computed result to SAP as a governed, consumable asset.

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