Google Cloud Real Estate and Construction Spain

Metrovacesa

Customer Service Automation · Sales Automation

Metrovacesa needed to qualify thousands of property leads around the clock because manual call-center processes could not keep up with multilingual demand or high-conversion off-hours interactions.

Read the original story Explore all use cases

Achieved a 94.8% performance improvement and 38% reduction in customer service time

Attained a 77% user satisfaction rating with an average score of 8.75 out of 10

Captured around 3,000 confirmed visit requests representing €70m in potential business volume

Managed 56% of customer conversations outside traditional business hours through 24/7 AI engagement

Reported impact

Business outcome

Metrovacesa reported Metrovacesa: Capturing €70m in business using AI Agents with Google Cloud and Lutech, Captured around 3,000 confirmed visit requests representing €70m in potential business volume, and Achieved a 94.8% performance improvement and 38% reduction in customer service time, improving multi-agent lead qualification and property support with measurable gains in revenue growth, customer experience, productivity improvement, and speed to market.

Solution

Metrovacesa uses Dialogflow CX, Vertex AI, Gemini, and Vertex AI Search to support multi-agent lead qualification and property support. Metrovacesa needed to qualify thousands of property leads around the clock because manual call-center processes could not keep up with multilingual demand or high-conversion off-hours interactions. In practice, the implementation stores or organizes core datasets in Vertex AI Search, coordinates repeatable workflows with Dialogflow CX, runs transformation or AI logic on Vertex AI, and delivers outputs through Dynamics 365 CRM. Lead, conversation, and crm data are consolidated into Vertex AI Search; pipeline execution is coordinated with Dialogflow CX; Vertex AI applies analytics or model logic; results are surfaced through Dynamics 365 CRM. The case study reports Metrovacesa: Capturing €70m in business using AI Agents with Google Cloud and Lutech, Captured around 3,000 confirmed visit requests representing €70m in potential business volume, and...

Data flow

Lead, conversation, and crm data are consolidated into Vertex AI Search; pipeline execution is coordinated with Dialogflow CX; Vertex AI applies analytics or model logic; results are surfaced through Dynamics 365 CRM.

Solution architecture

6 components · 4 layers

Compute
- Vertex AI Supports model development, tuning, evaluation, or managed generative ai inference
- Gemini Provides the language or embedding model used for reasoning, retrieval, or response generation
Storage
- Vertex AI Search Indexes domain content for retrieval-augmented answers and grounded responses
Serving
- Dynamics 365 CRM Connects operational applications and customer workflows to the analytics or ai layer
- Looker Studio Serves dashboards, reporting, and business-facing analytics on top of governed data
Orchestration
- Dialogflow CX Coordinates agentic or multi-step conversational workflows for the use case

Architecture clues

Managed 56% of customer conversations outside traditional business hours through 24/7 AI engagement
The platform is designed for near-real-time or streaming analysis rather than batch-only reporting.
Uses serverless or elastic compute so capacity can scale up and down with workload demand.

Evidence from the source

"We were seeing increasing demand from international buyers requiring 24/7 multilingual support," explains Borja Guaita, Commercial Manager at Metrovacesa.

Achieved a 94.8% performance improvement and 38% reduction in customer service time

Captured around 3,000 confirmed visit requests representing €70m in potential business volume

Managed 56% of customer conversations outside traditional business hours through 24/7 AI engagement

Metrovacesa: Capturing €70m in business using AI Agents with Google Cloud and Lutech

Transparency Evidence & methodology 95/100 reference value · 79% confidence · 1 source

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

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 value95/100

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
6 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.

Traceability

Sources & provenance

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

Google Cloud
Metrovacesa customer story

First-party
https://cloud.google.com/customers/metrovacesa

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 9, 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 Feb 27, 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.

Similar use cases

See all like this

Google Cloud Modified · Jun 16, 2026 Allvest Securities Private Limited Financial Services India The evolution of Allvest Securities Private Limited is rooted in a fundamental mission: bridging the gap between sophisticated capital markets and the millions of Indian investors seeking a transparent, ethical entry… Achieved 99.9% uptime during peak trading hours on Google Cloud Customer Service AutomationSales Automation Agent Development Kit (ADK) · Agent Platform · BigQuery

Google Cloud Jun 4, 2026 Renault Group Automotive France and Spain Renault needed a consistent, reliable, and personalized way to guide online vehicle shoppers from discovery to servicing, especially for electric and hybrid questions, without forcing visitors to manually search across… 60% of the questions relate to vehicles and their configuration first. Financing is the third topic of interest. Customer Service AutomationSales Automation Gemini 2.5 Flash · Renault brand configurator · Renault brand website

Salesforce Nov 25, 2025 Lennar Real Estate and Construction United States Rising costs and a shifting housing market amplify the need to remove barriers to buying a home. Since 1954, Lennar has helped more than 1.5 million families achieve one of life’s biggest milestones: buying a home. 000 annual appointments expected to be scheduled by Agentforce Customer Service AutomationSales Automation Agentforce · Data 360 · Field Service and Operations