{"slug":"building-a-clean-energy-future-with-natural-language-analytics","url":"https://findausecase.com/use-cases/building-a-clean-energy-future-with-natural-language-analytics","title":"Building a clean energy future with natural language analytics","description":"Williams, a large-scale natural gas infrastructure operator, deployed Databricks AI/BI Genie to give commercial, regulatory, accounting and technical staff natural-language, self-serve access to analytics. The team flattened 27 disparate tables into SQL models that Genie Spaces reason over, encoding internal acronyms and business logic into Genie's instructions, powered by Databricks Unity Catalog. A data request that previously took an analyst five days now completes in seconds with validated accuracy, and the weekly backlog of data requests dropped from up to ten to one or two, freeing analysts for predictive modeling and enterprise projects.","company":"Williams","industry":"Energy","aiCapabilities":["Natural Language Processing"],"technology":["Databricks AI/BI Genie","Databricks Unity Catalog"],"deployment":"Public Cloud","problemStatement":"Williams' business intelligence was historically centralized, with analysts using tabular tools and legacy reporting that became increasingly obsolete as data volumes and demands surged across commercial, regulatory, accounting and technical services groups; requests from executives could require days of coding, iterative validation and collaboration, with analysts sometimes spending up to a week compiling complex reports.","solutionApproach":"Williams built subject matter expert agents called Genie Spaces for core domains like contracts, billing, allocations and geolocation, flattening 27 different tables into large SQL models that Databricks AI/BI Genie could reason over, and encoding internal acronyms and business logic into Genie's instructions. The solution is powered by Databricks Unity Catalog and Databricks AI/BI Genie's natural language querying, exposing underlying SQL and logic for transparency.","businessValue":"A data request that previously took an analyst five days, covering 25 different attributes, now completes in only seconds with validated accuracy. The weekly backlog of data requests dropped from up to ten to just one or two, freeing analysts for higher-value initiatives like predictive modeling and enterprise projects. Databricks AI/BI Genie empowered 100+ employees across business areas with near-instant, self-serve analytics, and helped Williams uncover new market capacities in 2025.","evidence":{"band":"high"},"sourceUrl":"https://www.databricks.com/customers/williams","dates":{"publishedAt":"2026-08-18T09:03:53.617Z","publishedAtSource":"pipeline","updatedAt":"2026-08-25T19:46:07.014Z"},"license":"Open for reading and citing with a link to https://findausecase.com/use-cases/building-a-clean-energy-future-with-natural-language-analytics. Bulk republication requires permission."}