โSPARK is going to completely change how our portfolio and project teams interact with data. It moves us from static reports to real-time, intelligent conversations with our information, empowering our people to make quicker, better-informed decisions and unlocking value we simply couldn't reach before. It's genuinely exciting!โ - Allan Mason, Programme and Project Delivery Manager, Business Analytics
Scottish Water had the data needed to manage its Capital Investment programme, but access was fragmented across reports and often depended on specialist support. Using Databricks Genie, curated data layers and governed semantic definitions, the company built SPARK: a natural-language interface that helps project teams ask questions and get trusted answers in Microsoft Teams.
Key highlights:
- From report hunting to direct questions: A typical project-data lookup that previously took around eight clicks plus dashboard load time can now start with a single question.
- Faster access to project insight: In many cases, a four- to five-step search through SharePoint and reporting hubs becomes a direct question-and-answer experience.
- Governed by design: Curated gold-layer data, metric views and Unity Catalog bring access control, lineage and shared business definitions into the foundation.
- Built into the flow of work: Teams users ask questions through Copilot, which connects to a Genie Agent via the Model Context Protocol (MCP).
- Designed for measurable impact: Based on a modeled scenario of 100 users asking three questions per week, Scottish Water estimates potential savings of roughly 10 to 25 hours per week.
๐ Check out the full story ๐
