From Data to Dialogue: How S&P Global Energy Made Its Structured Data Estate Conversational with Databricks Genie Agents and MCP
S&P Global Energy turned its structured data into a conversational agent interface—not a chatbot wrapper, but a production system handling real customer queries through Databricks Genie and MCP.
Why it matters
A vendor case study showing how to ground agentic systems in enterprise structured data at scale. Practitioners will see the integration pattern (Databricks Genie + MCP + customer data) and the architectural trade-offs; enterprise AI buyers will evaluate whether this deployment model reduces time-to-agent without sacrificing governance or query correctness.
The key facts
6 to knowS&P Global Energy deployment uses Databricks Genie Agents and Model Context Protocol (MCP)
Focus: conversational access to structured data estate for customer discovery and consumption workflows
Deployment status: production (not pilot framing in Databricks blog)
Integration: Databricks + MCP + S&P Global's proprietary data
No pricing, quota, or measured outcome (latency, error rate, adoption) disclosed
No independent verification or third-party benchmark
Go to the source
Databricksdatabricks.com
Publisher excerpt: S&P Global's goal was to fundamentally improve how customers discover and consume...