How Class Editori Built MFGPT, Italy’s First Generative AI Media Agent

Class Editori, a leading Italian media company specializing in finance, fashion, and lifestyle with 40 years of content archives, partnered with Softlab to build MFGPT on Google Cloud — one of Italy’s first generative AI agents in the media industry. The system unified four decades of journalistic archives and real-time financial data into BigQuery, powered by Gemini and Vertex AI, converting trial users into paid subscribers and securing B2B enterprise agreements with major financial institutions.

Outcomes

One of Italy’s first AI agents in the media landscapeMFGPT launch milestone
40 years of content plus real-time financial dataArchive ingested into BigQuery
Trial users converted to paid subscribers; B2B enterprise agreements securedRevenue outcome

Tools & Technologies

1F
Firestore
NoSQL document database by Google Cloud for real-time data syncing in mobile and web applications.
2GC
Google Cloud Run
Serverless container platform by Google Cloud for deploying containerized apps without infrastructure management.
3GD
Google Dataflow
Managed streaming data pipeline service by Google for processing large-scale batch and real-time data.
4GB
Google BigQuery
Serverless enterprise data warehouse for analytics
5GV
Google Vertex AI
Google Cloud unified ML platform for building, deploying, and scaling AI models and generative AI applications.
6GC
Google Cloud Functions
Serverless compute service by Google Cloud for running event-driven code without managing infrastructure.
7GG
Google Gemini
Google multimodal AI model family

AI Categories

Challenge

Four decades of high-quality journalistic content and real-time financial data were spread across disconnected systems with no unified infrastructure, making it impossible to deliver the personalized, conversational content experience that subscribers and enterprise clients now expected.

Solution

Class Editori built a unified data platform on Google Cloud using BigQuery and Dataflow, then deployed MFGPT — a multi-agent generative AI system built on Gemini and Vertex AI — that lets subscribers query the full archive and financial data through a conversational interface with automated alerts via Cloud Functions.

Full Story

Class Editori has published financial and lifestyle news in Italy for four decades, operating newspapers, magazines, TV channels, and digital platforms under brands including Milano Finanza and Gambero Rosso. The company launched one of Italy’s first websites in 1996 and built itself into a major data broker for stock exchange information. But by the early 2020s, the competitive pressure had shifted: global platforms like Google, Amazon, and Netflix were training consumer expectations around personalized, conversational content discovery. A media house with 40 years of verified, high-quality journalism needed a way to deliver that archive in a format audiences now demanded.

Access 457+ AI use cases, 428+ tools, and adoption signal rankings.

Source

GOOGLE
March 2026
Original case study ↗

Similar Cases

1AS
How AXA Switzerland Uses BigQuery and Vertex AI to Cut Query Times by 95%
AXA Switzerland
Over 95%Query and processing time reduction
2M
How Morrisons Reduced Data Reporting Lag by 99% with BigQuery and Looker
Morrisons
98.96%Data reporting lag reduction
3TW
How The Washington Post Uses AI Agents to Eliminate Tax Overpayments
The Washington Post
100%Invoice tax accuracy coverage
4S
How Super-Pharm Uses Vertex AI to Improve Inventory Accuracy from 50% to 90%
Super-Pharm
50% to 90%Inventory Accuracy
5TM
How The Met Uses OpenAI to Bring Historical Fashion Exhibits to Life
The Metropolitan Museum of Art
6S
How Shopify Scales AI-Powered Sidekick to Millions of Merchants with Claude on Vertex AI
Shopify
< 24 hoursModel Upgrade Deployment
7HE
How Hershey Entertainment & Resorts Saves 8 Staff Hours Daily with Google AI Agents
Hershey Entertainment & Resorts
8 hoursStaff hours saved daily
8DH
How Delivery Hero's Herogen Agent Merges 100+ Pull Requests a Day with Claude
Delivery Hero
>100Merged pull requests per day from Herogen
9E
How Etsy Uses Gemini and Vertex AI to Personalize 90 Million Shopping Experiences
Etsy
~80xListings per theme increase via algotorial curation
10E
How Erewhon Automated 70% of Customer Service Tickets and Saved $40K Annually with Zapier
Erewhon
70%Customer service tickets automated
See all use cases →