Microsoft Public Sector Spain

Madrid Destino / Madrid City Council

Customer Service Automation · Enterprise Knowledge Search · Marketing Personalization

The City of Madrid recognized the potential of generative AI to connect with visitors in an innovative way. It relied on iUrban‘s expertise and Microsoft Azure OpenAI Service to develop the VisitMadridGPT AI virtual assistant. The City decided on Azure because it wanted a platform that could easily support growth and interoperation with existing systems.

City of Madrid created VisitMadridGPT with Microsoft Azure OpenAI Service, offering tourists accurate, real-time info and personalized responses in 95-plus languages.
In 2023, Madrid attracted 10.6 million visitors, boosting the local economy, and creating new employment opportunities.
On average, users ask 2.8 questions per session and spend about four minutes and 18 seconds using the assistant.
The assistant has a low bounce rate, with users spending an average of four minutes and 18 seconds per session.

Reported impact

Business outcome

The VisitMadridGPT assistant has significantly improved the City’s tourism experience by providing accurate and timely information, offering personalized experiences, and allowing the City to analyze conversations and understand the real needs and behaviors of tourists.

  • Customer Experience
  • Scalability

Solution

Madrid Destino / Madrid City Council built this solution on Azure OpenAI Service. The City of Madrid recognized the potential of generative AI to connect with visitors in an innovative way. It relied on iUrban‘s expertise and Microsoft Azure OpenAI Service to develop the VisitMadridGPT AI virtual assistant. Azure OpenAI Service provides the generative AI model layer used for summarization, drafting, classification, or copilots in the workflow. City of Madrid created VisitMadridGPT with Microsoft Azure OpenAI Service, offering tourists accurate, real-time info and personalized responses in 95-plus languages. It also helps the City analyze conversations to better understand tourist needs. Messages, calls, or requests enter the existing workflow, Azure OpenAI Service classifies or summarizes them, and the reviewed output is surfaced to agents and frontline staff.

Data flow

Messages, calls, or requests enter the existing workflow, Azure OpenAI Service classifies or summarizes them, and the reviewed output is surfaced to agents and frontline staff.

Solution architecture

1 components · 1 layer
  1. Compute
    • Azure OpenAI Service Provides the generative AI model layer used for summarization, drafting, classification, or copilots in the workflow.

Architecture clues

  • The implementation relies on Azure OpenAI Service as a core technical building block.

Evidence from the source

City of Madrid created VisitMadridGPT with Microsoft Azure OpenAI Service, offering tourists accurate, real-time info and personalized responses in 95-plus languages.
The City of Madrid recognized the potential of generative AI to connect with visitors in an innovative way.
The VisitMadridGPT assistant has significantly improved the City’s tourism experience by providing accurate and timely information, offering personalized experiences, and allowing the City to analyze conversations and un
The assistant has a low bounce rate, with users spending an average of four minutes and 18 seconds per session.
Transparency Evidence & methodology 90/100 reference value · 89% 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 value90/100
  • 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 specificity20/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact25/25
    2 metrics describe measurable impact.
  • Deployment scale5/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence89%
  • 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
    4 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 specificity10/10
    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

    Madrid Destino / Madrid City Council customer story

    First-party
    https://www.microsoft.com/en/customers/story/19546-madrid-destino-madrid-city-council-azure-open-ai-service
    Source type
    Vendor-published customer story
    Published
    Nov 1, 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 Nov 1, 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.