---
title: "How Scottish Water Made Its Capital Investment Data Conversational With Databricks Genie"
description: "Scottish Water’s Capital Investment teams had project data, reports, and metrics available, but non-technical users often struggled to find answers, creating duplicated reporting and delays. SPARK addresses this access problem through a natural-language interface in Microsoft Teams: Copilot routes questions via a supervisor agent and MCP to the Databricks Genie Agent, which queries governed Unity Catalog data. The implementation curates use-case data in a gold layer, adds metric views as a semantic layer, and configures business rules, examples, benchmarking, feedback, and monitoring for accuracy and performance. Environment-parameterised Databricks Asset Bundles, separate environments, Azure DevOps approvals, Entra ID, and Key Vault support repeatable deployment. The post reports lookup journeys shrinking from around eight clicks or four to five search steps to a direct question, with an estimated 520 to 1,300 hours saved annually under a stated usage scenario."
---

# How Scottish Water Made Its Capital Investment Data Conversational With Databricks Genie

[Databricks](https://yomu.fyi/company/databricks) · Sourav Gulati, Poppy Harvey · Aug 13, 2026

**Type:** Problem & solution

## Summary

Scottish Water’s Capital Investment teams had project data, reports, and metrics available, but non-technical users often struggled to find answers, creating duplicated reporting and delays. SPARK addresses this access problem through a natural-language interface in Microsoft Teams: Copilot routes questions via a supervisor agent and MCP to the Databricks Genie Agent, which queries governed Unity Catalog data. The implementation curates use-case data in a gold layer, adds metric views as a semantic layer, and configures business rules, examples, benchmarking, feedback, and monitoring for accuracy and performance. Environment-parameterised Databricks Asset Bundles, separate environments, Azure DevOps approvals, Entra ID, and Key Vault support repeatable deployment. The post reports lookup journeys shrinking from around eight clicks or four to five search steps to a direct question, with an estimated 520 to 1,300 hours saved annually under a stated usage scenario.

## Context

Scottish Water’s Capital Investment function had extensive reporting and underlying data, but limited visibility and difficult access caused duplicated reporting, delayed answers, and reliance on analysts or data specialists for information extraction.

## Approach / What changed

SPARK provides a natural-language interface in Microsoft Teams. Copilot and a supervisor agent connect through MCP to Databricks Genie, which queries curated, governed Unity Catalog data through metric views and returns answers. The implementation adds business rules, worked examples, benchmarking, user feedback, monitoring, and environment-parameterised deployment through Databricks Asset Bundles.

## Takeaways

- SPARK brings governed Capital Investment data into Microsoft Teams, allowing users to ask questions such as current project risk scores, expiring risks, and future contractors in plain English.
- The data foundation uses curated gold-layer data and metric views to standardise measures, dimensions, and business terminology before Genie queries the information.
- For a stated scenario of 100 users asking three questions weekly, saving two to five minutes per request represents approximately 520 to 1,300 hours saved per year.

**Tags:** [Architecture](https://yomu.fyi/topic/architecture), [Azure](https://yomu.fyi/topic/azure), [MCP](https://yomu.fyi/topic/mcp), [Monitoring](https://yomu.fyi/topic/monitoring)

- Source: [Databricks](https://www.databricks.com/blog/how-scottish-water-made-its-capital-investment-data-conversational-databricks-genie)
- Source URL: https://www.databricks.com/blog/how-scottish-water-made-its-capital-investment-data-conversational-databricks-genie
- Ingested by Yomu: 2026-08-30T16:51:18.608Z

[Read original post](https://www.databricks.com/blog/how-scottish-water-made-its-capital-investment-data-conversational-databricks-genie)