Why R&D Data Belongs in the Lakehouse - and Why Agents Need It There

Summary

cellcentric describes how it built a governed lakehouse foundation for R&D data so industrial AI agents can reason over engineering context, not isolated source-system records. On Azure and Databricks, the Data Hub combines Unity Catalog governance, Lakehouse Federation, Delta Sharing, Declarative Automation Bundles, and an MCP interface for agents. Its Fuel Cell Passport unifies five enterprise systems, models seven hierarchy levels, refreshes daily, and uses a state-based temporal model for point-in-time configuration and rework-history questions. The platform treats context coverage as a data-quality metric, with 27 published products averaging 90% column-comment coverage, while authenticated user identity and Unity Catalog authorization constrain agent access. For many R&D and process-development workflows, work that once took weeks now ships in days, though complex multi-source investigations still require substantial domain review.

Takeaways

1. 1

   The Fuel Cell Passport combines SAP S/4HANA, two MES systems, a laboratory database, and an IoT telemetry platform across seven hierarchy levels, with daily refreshes and state-based temporal modeling.

2. 2

   Context coverage is tracked as a visible quality metric: 27 published data products average 90% column-comment coverage, with most comments AI-assisted and reviewed by engineers before merge.

3. 3

   Agents access data on behalf of authenticated users, so Unity Catalog permissions, masking, and governed views apply equally to UI queries, SQL tools, Genie calls, and MCP interactions.