Italgas Embeds Agent Bricks Machine Learning and Genie Natural-Language Queries into Gas Distribution Operations
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.
Overview
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.
This entry has 14 published fields tied to exact passages in an immutable source capture.
Inspect the highlighted sourceThe challenge
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.
The solution
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.
Reported business value
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.
Sources
Open any source and check the claim yourself — that is the point of the register.
This record was researched and written with AI assistance, and its claims were checked against the sources above. (EU AI Act art. 50 transparency notice.)
Other energy entries in the register.
Building a clean energy future with natural language analytics
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.
Eneco eMobility uses Dynamics 365 Contact Center with generative AI to support its customer care agents
Eneco eMobility, a charging services provider in Europe, worked with Capgemini to roll out Microsoft Dynamics 365 Contact Center, a Copilot-first contact center powered by generative AI, in an iterative pilot-led rollout; the first groups were live five weeks after ideation. The source reports a 50% reduction in average wrap-up time and training time cut from four hours to one, with the Belgian rollout expanded to the Netherlands.
Plenitude builds machine learning models on Databricks to forecast energy demand and renewable production
Eni-owned energy company Plenitude, which serves 10 million households and businesses across Europe, uses statistical models and machine learning on the Databricks Data + AI Platform to forecast customer energy consumption at hourly and daily granularity, forecast wind and solar generation from its renewable asset portfolio, and run customer segmentation and propensity models across 60 implemented use cases.
Shell delivers innovative energy solutions with data and AI on Databricks
Shell built its Shell.ai platform on Databricks to unify data, analytics, and AI workloads for its 600-member mathematics, computational and data science team, running over 100 AI applications including an inventory prediction model running 10,000+ simulations across spare parts and facilities, and an AI-powered recommendation engine for its loyalty program.
Was this helpful?
Your feedback helps us improve our use case database

