{"slug":"italgas-embeds-agent-bricks-machine-learning-and-genie-natural-language-queries-into-gas-distribution-operations","url":"https://findausecase.com/use-cases/italgas-embeds-agent-bricks-machine-learning-and-genie-natural-language-queries-into-gas-distribution-operations","title":"Italgas Embeds Agent Bricks Machine Learning and Genie Natural-Language Queries into Gas Distribution Operations","description":"Italgas unified its siloed gas-distribution data systems on the Databricks Data + AI Platform, using Delta Lake, Unity Catalog and Databricks SQL to process 1TB of data daily and give 80% of employees self-service AI/BI Dashboards, cutting platform costs by 70% and workload costs by 73% versus its prior Azure Synapse setup. Italgas plans to embed the Genie Conversation API into its DEVA meter-management and DANA control-room systems for natural-language queries.","company":"Italgas","industry":"Energy","country":"Italy","aiCapabilities":["Predictive Analytics"],"technology":["Databricks SQL","Delta Lake","Unity Catalog","AI/BI Dashboards","Lakeflow Connect","Agent Bricks","Genie"],"deployment":"Public Cloud","problemStatement":"Italgas faced significant challenges due to siloed data systems and manual processes, resulting in over 90,000 unresolved customer complaints in 2023. Operators were constantly switching between multiple systems, including Salesforce, Meter Data Management and GasToGo, meaning they spent more time gathering and cross-referencing data than resolving customer issues.","solutionApproach":"Italgas turned to the Databricks Data + AI Platform, eliminating intermediate services like Azure Synapse and Analysis Services and implementing Delta Lake with a medallion (Bronze/Silver/Gold) architecture. The system now processes 1TB of data daily across 1,738 pipelines, 23 models and 155 dashboards for over 3,000 active users. Databricks SQL, powered by the Photon Engine, and self-service AI/BI Dashboards let 80% of the company derive insights without relying on technical teams, while Unity Catalog governs 100% of workloads. Italgas plans to embed the Genie Conversation API into its DEVA meter-management system and DANA Control Room application so users can query system performance and detect safety concerns using natural language, alongside expanding Agent Bricks machine learning models.","businessValue":"Italgas achieved a 70% reduction in platform costs and a 73% reduction in workload costs compared with Azure Synapse, a 20% performance increase powered by SQL warehouses running 50% faster, and empowered 80% of employees with self-service analytics across its 3,000 active users, enabling faster customer complaint resolution.","evidence":{"band":"high"},"sourceUrl":"https://www.databricks.com/customers/italgas/ai-bi","dates":{"publishedAt":"2026-10-07T05:46:45.280Z","publishedAtSource":"pipeline","updatedAt":"2026-10-07T05:46:45.280Z"},"license":"Open for reading and citing with a link to https://findausecase.com/use-cases/italgas-embeds-agent-bricks-machine-learning-and-genie-natural-language-queries-into-gas-distribution-operations. Bulk republication requires permission."}