Use Case Intelligence RSS Search use cases Search
Google Cloud Media and Entertainment Italy

Class Editori

Data Lake / Data Warehouse Modernization · Marketing Personalization · Real-time Analytics

With global giants like Google, Amazon, and Netflix setting new standards for personalized content delivery, Class Editori recognized that consumer habits were shifting toward conversational interfaces.

Read the original story Explore all use cases
Converted trial users into paid subscribers and secured B2B enterprise agreements
Ingested 40 years of archives and real-time financial data into BigQuery

Reported impact

Business outcome

Launched MFGPT, one of Italy’s first AI agents in the media landscape; Ingested 40 years of archives and real-time financial data into BigQuery; Accelerated time-to-market from concept to revenue-generating technology; Converted trial users into paid subscribers and secured B2B enterprise agreements.

  • Customer Experience
  • Revenue Growth
  • Risk Reduction
  • Scalability

Solution

Class Editori partnered with Softlab to build a scalable data platform on Google Cloud and MFGPT, one of Italy's first generative AI financial news agents. By using BigQuery, Firestore, and Vertex AI, the company unified decades of content to deliver personalized, revenue-generating experiences for subscribers and enterprise clients. The flagship achievement of this partnership is MFGPT, one of Italy’s first generative AI agents in the media landscape. Built using Gemini Flash and Pro models, MFGPT provides subscribers with a conversational interface to query articles, podcasts, videos, and real-time financial data. The platform uses BigQuery as its central data warehouse for structured data, while Dataflow manages complex pipelines. For its AI capabilities, Class Editori chose Vertex AI, citing its completeness for both standard machine learning and generative AI.

Data flow

stored or unified in BigQuery, processed with Vertex AI, and surfaced through Gemini Enterprise, Gemini Flash, Gemini, Cloud Run

Solution architecture

6 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 Enterprise Provides a secure enterprise environment for teams to use Gemini with governed data access.
    • Gemini Flash Handles high-volume generative AI tasks with lower latency and lower serving cost.
    • Gemini Powers natural-language reasoning, summarization, generation, or assistance inside the workflow.
    • Cloud Run Runs application services and proprietary code in a managed container environment.

Architecture clues

  • "Vertex AI enables efficient access and onboarding of models while also offering tools for tracking experiments, building pipelines, and deploying endpoints," says Andrea Pazzaglia, Head of AI at Class Editori.
  • Enabled scalable, multi-agent AI capabilities using Vertex AI Cloud Run , and Firestore
  • Ingested 40 years of archives and real-time financial data into BigQuery
  • Products: Gemini Enterprise Cloud Functions Dataflow
  • Vertex AI provides access to many generative AI models through a single point. It’s a complete solution both for standard machine learning and more advanced generative AI.

Evidence from the source

Accelerated time-to-market from concept to revenue-generating technology
Converted trial users into paid subscribers and secured B2B enterprise agreements
Enabled scalable, multi-agent AI capabilities using Vertex AI Cloud Run , and Firestore
Ingested 40 years of archives and real-time financial data into BigQuery
Launched MFGPT, one of Italy’s first AI agents in the media landscape
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.

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 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
    2 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

    Class Editori customer story

    First-party
    https://cloud.google.com/customers/classeditori
    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 Apr 13, 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 24, 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
Google Cloud Modified · Oct 9, 2026 ICA Retail Sweden Previously, however, ICA’s fragmented technical environment was holding it back. Data was siloed across legacy platforms and SQL server environments, creating high maintenance costs and preventing teams from sharing… ICA Gruppen is a leading Swedish retailer, with a portfolio covering grocery, pharmacy and banking. Serving… Data Lake / Data Warehouse ModernizationMarketing Personalization BigQuery · Bigtable · Gemini Google Cloud Archived · Jun 8, 2026 Clear.bio Healthcare The Netherlands Clear.bio is transforming diabetes management by using Google AI to scale its personalized digital nutritional interventions through automated data prediction workflows, thus replacing inefficient manual processes. As… , a health-tech startup founded in 2019, offers a 12-week digital nutritional intervention to help thousands… Data Lake / Data Warehouse ModernizationMarketing Personalization BigQuery · Cloud Run · Gemini Databricks Jan 14, 2025 Seven West Media Media and Entertainment Australia Legacy systems made it difficult to access real-time insights, slowing down decision-making and leaving some revenue opportunities on the table. Workflows that once took hours of manual effort are now possible in… $16M Incremental ad revenue from re-engagement campaigns Data Lake / Data Warehouse ModernizationMarketing Personalization Agent Bricks