--- title: How Scottish Water Made Its Capital Investment Data... description: Scottish Water built an internal tool called SPARK using Databricks Genie to let Capital Investment teams ask natural-language questions about project status,... canonical: https://daily.dev/posts/how-scottish-water-made-its-capital-investment-data-conversational-with-databricks-genie-imeuvoaiz twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: How Scottish Water Made Its Capital Investment Data Conversational With Databricks Genie | daily.dev og:description: Scottish Water built an internal tool called SPARK using Databricks Genie to let Capital Investment teams ask natural-language questions about project status,... og:url: https://daily.dev/posts/how-scottish-water-made-its-capital-investment-data-conversational-with-databricks-genie-imeuvoaiz og:image: https://api.daily.dev/og/posts/imEuVOaIZ.png og:image:alt: How Scottish Water Made Its Capital Investment Data Conversational With Databricks Genie og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # How Scottish Water Made Its Capital Investment Data Conversational With Databricks Genie **[databricks](https://daily.dev/sources/databricks)** · 11 min read · 0 upvotes · 0 comments ## Summary Scottish Water built an internal tool called SPARK using Databricks Genie to let Capital Investment teams ask natural-language questions about project status, risks, and finances directly in Microsoft Teams via Copilot. The system connects through MCP to a Genie Space querying governed data in Unity Catalog, with a curated gold layer and semantic metric views ensuring consistent, trustworthy answers. The case study covers accuracy tuning with business-rule instructions and benchmark suites, ongoing monitoring of adoption and query performance, and repeatable deployment using Databricks Asset Bundles across dev, test, and production environments via Azure DevOps. Estimated time savings range from 520 to 1,300 hours per year. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How does Databricks Genie integrate with Microsoft Teams for natural language data queries? Users submit questions in Teams through Copilot, which is orchestrated by a Copilot supervisor agent that connects to a Databricks Genie Space via the Model Context Protocol (MCP). Genie translates the question into a SQL query, runs it against governed data in Unity Catalog, and returns the result to the user inside Teams, avoiding the need for a separate interface. _Explore how daily.dev surfaces practical patterns for wiring conversational AI into governed data platforms._ ### How do you make a Databricks Genie space give accurate answers on business-specific terminology? Accuracy comes from curating business-rule instructions covering fiscal periods, milestone gate ordering, and project ID/date conventions, plus worked example questions paired with matching SQL to teach the assistant how users phrase queries. A benchmark suite tests accuracy repeatably whenever the space definition or underlying data changes, and user testing feeds real-world phrasing back into further refinements. _daily.dev helps teams tuning conversational analytics track proven accuracy techniques as they emerge._ ## Similar posts on daily.dev - [Transforming industries with conversational AI: Partner solutions built on Databricks Genie](https://daily.dev/posts/transforming-industries-with-conversational-ai-partner-solutions-built-on-databricks-genie-fpt7jn5jz) · databricks · 0 upvotes · 0 comments - [Scaling Enterprise Conversational Intelligence: Cross-industry Technology and Functional Solutions Powered by Databricks Genie](https://daily.dev/posts/scaling-enterprise-conversational-intelligence-cross-industry-technology-and-functional-solutions-p-76wlbmjsc) · databricks · 0 upvotes · 0 comments - [From Data to Dialogue: How S&P Global Energy Made Its Structured Data Estate Conversational with Databricks Genie Agents and MCP](https://daily.dev/posts/from-data-to-dialogue-how-s-p-global-energy-made-its-structured-data-estate-conversational-with-dat-gvdbh91cb) · databricks · 1 upvotes · 0 comments --- Tags: [#mcp](https://daily.dev/tags/mcp), [#databricks](https://daily.dev/tags/databricks), [#unity-catalog](https://daily.dev/tags/unity-catalog) [View this post on daily.dev](https://daily.dev/posts/how-scottish-water-made-its-capital-investment-data-conversational-with-databricks-genie-imeuvoaiz) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"How Scottish Water Made Its Capital Investment Data Conversational With Databricks Genie","url":"https://daily.dev/posts/how-scottish-water-made-its-capital-investment-data-conversational-with-databricks-genie-imeuvoaiz","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/how-scottish-water-made-its-capital-investment-data-conversational-with-databricks-genie-imeuvoaiz"},"datePublished":"2026-08-13T21:02:30.413Z","dateModified":"2026-08-13T21:13:48.470Z","description":"Scottish Water built an internal tool called SPARK using Databricks Genie to let Capital Investment teams ask natural-language questions about project status,...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/e3c8215324c34007d5dbd7e564644c7e?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/e3c8215324c34007d5dbd7e564644c7e?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"databricks","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"databricks","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/fa7aa720f2db4d1eba826814730482c8","url":"https://daily.dev/sources/databricks"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/how-scottish-water-made-its-capital-investment-data-conversational-with-databricks-genie-imeuvoaiz","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"mcp,databricks,unity-catalog","timeRequired":"PT11M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"databricks","item":"https://daily.dev/sources/databricks"},{"@type":"ListItem","position":3,"name":"How Scottish Water Made Its Capital Investment Data Conversational With Databricks Genie"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/how-scottish-water-made-its-capital-investment-data-conversational-with-databricks-genie-imeuvoaiz#faq","mainEntity":[{"@type":"Question","name":"How does Databricks Genie integrate with Microsoft Teams for natural language data queries?","acceptedAnswer":{"@type":"Answer","text":"Users submit questions in Teams through Copilot, which is orchestrated by a Copilot supervisor agent that connects to a Databricks Genie Space via the Model Context Protocol (MCP). Genie translates the question into a SQL query, runs it against governed data in Unity Catalog, and returns the result to the user inside Teams, avoiding the need for a separate interface. Explore how daily.dev surfaces practical patterns for wiring conversational AI into governed data platforms."}},{"@type":"Question","name":"How do you make a Databricks Genie space give accurate answers on business-specific terminology?","acceptedAnswer":{"@type":"Answer","text":"Accuracy comes from curating business-rule instructions covering fiscal periods, milestone gate ordering, and project ID/date conventions, plus worked example questions paired with matching SQL to teach the assistant how users phrase queries. A benchmark suite tests accuracy repeatably whenever the space definition or underlying data changes, and user testing feeds real-world phrasing back into further refinements. daily.dev helps teams tuning conversational analytics track proven accuracy techniques as they emerge."}}]} ```