Google Cloud Public Sector Spain

Ayuntamiento de Valladolid

Customer Service Automation · Real-time Analytics · Security and Compliance

The city of Valladolid in Spain faces a challenge common to many medium-sized cities: managing and delivering a vast, complex web of services—from social services and public works to registrations and rural activities—across a diverse population. For citizens, finding specific information often meant navigating a tangle of departments and "invisible barriers".

Achieved 100% factual information delivery by grounding the AI assistant in audited municipal data sources
Expanding 24/7 support to improve resident experiences
Manages 300 to 500 citizen queries daily, significantly reducing burden on traditional service channels
Provides 24/7 automated support for all municipal inquiries with gen AI agent

Reported impact

Business outcome

Provides 24/7 automated support for all municipal inquiries with gen AI agent; Manages 300 to 500 citizen queries daily, significantly reducing burden on traditional service channels; Achieved 100% factual information delivery by grounding the AI assistant in audited municipal data sources; Optimizes public spending and maximizes government responsiveness using dashboards with real-time data tracking.

  • Customer Experience
  • Productivity Improvement
  • Risk Reduction
  • Scalability

Solution

Successfully transitioned from on-premises systems to a secure, flexible cloud environment using Gemini and BigQuery The centerpiece of the city’s transformation is Ana, a generative AI assistant built on Google Cloud using Gemini and with help from LuceIT. To encourage internal adoption, the council "humanized" the technology. They named the assistant after a long-serving colleague, Ana, even creating an avatar in her likeness. This helped reframe AI as an ally that handles routine administrative burdens, allowing human workers to focus on high-value citizen care. LuceIT led the technical deployment, integrating Gemini with municipal data while adhering to strict security and regulatory requirements. By using flexible infrastructure in Google Cloud, the council successfully transitioned from traditional on-prem systems to a modern cloud.

Data flow

stored or unified in BigQuery, processed with Vertex AI, and surfaced through Gemini

Solution architecture

3 components · 3 layers
  1. Compute
    • Vertex AI Hosts and orchestrates machine learning and generative AI capabilities inside the solution.
  2. Storage
    • BigQuery Stores and queries the analytics and AI-ready datasets that power the workload.
  3. Serving
    • Gemini Powers natural-language reasoning, summarization, generation, or assistance inside the workflow.

Architecture clues

  • Implementing secure, human-focused AI with Gemini
  • Products: Vertex AI
  • Successfully transitioned from on-premises systems to a secure, flexible cloud environment using Gemini and BigQuery

Evidence from the source

Achieved 100% factual information delivery by grounding the AI assistant in audited municipal data sources
Manages 300 to 500 citizen queries daily, significantly reducing burden on traditional service channels
Optimizes public spending and maximizes government responsiveness using dashboards with real-time data tracking
Provides 24/7 automated support for all municipal inquiries with gen AI agent
Successfully transitioned from on-premises systems to a secure, flexible cloud environment using Gemini and BigQuery
Transparency Evidence & methodology 100/100 reference value · 79% 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 value100/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth25/25
    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
    4 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence79%
  • 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
    5 direct source quotes retained.
  • Date provenance0/10
    The publication date has no documented provenance.
  • 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. Google Cloud

    Ayuntamiento de Valladolid customer story

    First-party
    https://cloud.google.com/customers/valladolid
    Source type
    Vendor-published customer story
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes

Date evidence

  • First archived Mar 21, 2026 · Internet Archive · Independent First Wayback Machine capture; confirms the page existed by this date, not when it was published.
    Open date source
  • Sitemap last modified Mar 19, 2026 · Google Cloud · Publisher metadata Publisher-reported modification timestamp; not a publication date.
    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