Use Case Intelligence RSS Search use cases Search
Microsoft Software / SaaS United Kingdom

Iceland

Enterprise Knowledge Search

"We wanted to capture and consolidate that knowledge." To achieve this, the Iceland team has built an ingenious new tool through which colleagues can interact with business knowledge - an app called Genie which leverages the natural language capabilities of Azure OpenAI Craig Robinson, Software Engineering Manager at Iceland, explains, "We'd had this idea of consolidating our knowledge base.

Read the original story Explore all use cases

Reported impact

Business outcome

The Genie app is helping colleagues find answers faster.

  • Cost Reduction
  • Customer Experience
  • Productivity Improvement
  • Revenue Growth

Solution

Iceland built its Microsoft solution to improve knowledge retrieval and expert-assistance workflows. "We wanted to capture and consolidate that knowledge." To achieve this, the Iceland team has built an ingenious new tool through which colleagues can interact with business knowledge - an app called Genie which leverages the natural language capabilities of Azure OpenAI Craig Robinson, Software Engineering Manager at Iceland, explains, "We'd had this idea of consolidating our knowledge base. Key components included GitHub Copilot delivered dashboards, apps, or copilots to users, and Microsoft Fabric held and organized governed data. Operational data flows into Microsoft Fabric, where Microsoft Fabric applies transformations and business logic before Microsoft Fabric delivers governed insights to teams across Iceland. The stack stayed governed and extensible on Microsoft. The Genie app is helping colleagues find answers faster.

Data flow

Operational data flows into Microsoft Fabric, where Microsoft Fabric applies transformations and business logic before Microsoft Fabric delivers governed insights to teams across Iceland.

Solution architecture

4 components · 4 layers
  1. Compute
    • Azure OpenAI Service Runs large language models that generate grounded responses, summaries, and copilots.
  2. Storage
    • Microsoft Fabric Unifies data engineering, analytics, and business-intelligence workloads on one cloud platform.
  3. Serving
    • GitHub Copilot Assists developers with code generation and software-delivery tasks inside engineering workflows.
  4. Orchestration
    • Azure AI Studio Provides the build environment for prompt orchestration, safety controls, and model tuning.

Architecture clues

  • "It would fit easily within our existing app landscape and, as a platform as a service, it is easy to set up and configure - and it's all there for us wrapped up in the Microsoft infrastructure and security ecosystem." Custom Iceland apps built on the Microsoft stack Iceland has a tradition of creating key line of business apps in-house, opting to build on the Microsoft Azure technology stack.
  • Genie runs in Azure Container Apps and uses a Cosmos DB no-SQL database.
  • That's been important, especially when setting up Microsoft Fabric A best-practice data platform for further AI innovation As part of Iceland's strategy to enhance the data infrastructure of the business and enable rapid, data-driven decision making, the team has begun implementing Microsoft Fabric, the AI-powered analytics platform that unites data and services.

Evidence from the source

"A few of our developers, including myself, had a personal licence for GitHub Copilot so we became big advocates for it.
"GitHub Copilot has been fantastic for supporting the developers who are more familiar with C# to work with the Python functions we're using.
"We wanted to capture and consolidate that knowledge." To achieve this, the Iceland team has built an ingenious new tool through which colleagues can interact with business knowledge - an app called Genie which leverages the natural language capabilities of Azure OpenAI Craig Robinson, Software Engineering Manager at Iceland, explains, "We'd had this idea of consolidating our knowledge base.
Iceland is using GitHub Copilot to boost development delivery velocity.
Our CEO is very interested in how it can be applied to business statistics, so we can ask 'what were the top selling products last week?' or 'what were the sales in London?' for example." Delivering more, faster with GitHub Copilot Another AI innovation is helping Iceland's software engineering squads to deliver these new capabilities for Genie, as well as for other apps.
The Genie app is helping colleagues find answers faster.
Transparency Evidence & methodology 66/100 reference value · 85% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value66/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth20/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity16/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact0/25
    0 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence85%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability21/25
    10 of 12 key fields link to a named source.
  • Direct evidence20/20
    6 direct source quotes retained.
  • Date provenance10/10
    The publication date comes from the source page or publisher.
  • Source transparency8/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity6/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. Microsoft

    Iceland customer story

    First-party
    https://www.microsoft.com/en/customers/story/19766-iceland-github-copilot
    Source type
    Vendor-published customer story
    Published
    Dec 3, 2024
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes
    • Publication date

Date evidence

  • Published on source page Dec 3, 2024 · Microsoft · First-party
    Open date source
Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.

Related

Similar use cases

See all like this
Microsoft Jan 9, 2025 Wrtn Software / SaaS South Korea South Korean startup Wrtn Technologies is transforming everyday life with its AI "superapp," designed to enhance productivity, entertainment, and emotional connections. Discover more details CUSTOMER Wrtn PRODUCTS Azure AI Content Safety Azure OpenAI Service Azure AI Foundry… Enterprise Knowledge Search Azure AI Foundry · Azure OpenAI Service · Microsoft Azure Microsoft Dec 30, 2024 Document360 Software / SaaS United Kingdom With an aim to help businesses improve document efficiency and transparency, Document360 wanted to build an AI-powered knowledge base and service platform. Andrew Cloke, Chief Operating Officer, Document360 Increased customer engagement by 50% Reduced costs by up to… Customer Service AutomationEnterprise Knowledge Search Azure · Azure AI Search · Azure App Service Microsoft Dec 3, 2024 Harvey Software / SaaS United States In an industry traditionally underserved by digital innovation, the founders at Harvey are delivering professional-class AI to lawyers around the world. In fact, one corporate lawyer said using Harvey saved them 10 hours of work per week. Document ProcessingEnterprise Knowledge Search Azure Kubernetes Service · Azure OpenAI Service