From Data to Dialogue: How S&P Global Energy Made Its Structured Data Estate Conversational with Databricks Genie Agents and MCP

• Domain experts curate focused Genie Agents per dataset group without writing agent code, establishing a governed semantic layer.
• Genie Agents act as managed MCP servers that are composed via a FastMCP proxy into composite endpoints for cross-domain queries.
• This architecture significantly shortened time-to-market for conversational data products while preserving Unity Catalog governance.

S&P Global's goal was to fundamentally improve how customers discover and consume insights across our data and research products. While AI powered search and summarization are important, the larger business value comes from enabling faster decision making through natural language access to trusted data, richer cross-commodity analytics, and the ability to connect insights that traditionally exist in separate business lines. AI agents help customers uncover relationships, generate research more efficiently, and derive actionable intelligence from a broader set of information than was previously possible.   —Priyanka John, Vice President, S&P Global Energy

If you have ever tried to make a large, complex structured data estate available to AI agents and assistants, you have likely run into the same wall we did: agents are only as good as the context they can reach, and enterprise data rarely lives in one neat, well-documented place.

At S&P Global Energy, our data spans Chemicals, Crude Oil, Refined Products, Gas & Power, Liquified Natural Gas (LNG) and more — and each commodity is itself a rich family of datasets. LNG alone includes facility specifications, cargos , outages, supply and demand fundamentals, netbacks, historical and forecast prices, and contracts. Chemicals span capacity, production, utilization, trade, demand by end use and by derivative, inventory change, and country- and region-level supply–demand balances. Our other commodities follow similar patterns. This data lives across Databricks and several non-Databricks sources.