AnnouncementIntroducing MongoDB 8.0, the fastest MongoDB ever! Read more >
NEWSLearn why MongoDB was named a leader in the 2024 Gartner® Magic Quadrant™ Read the blog >
AnnouncementIntroducing Search Demo Builder, the newest addition to the Atlas Search Playground Learn more >

Swisscom Stands Up New Gen AI Banking Use Case Within 12 Weeks With MongoDB

Photo of a woman spiking on a mobile phone.

INDUSTRY

Information and Communication Technology

PRODUCT

MongoDB Atlas Vector Search,
MongoDB Atlas

USE CASE

GenAI

CUSTOMER SINCE

2023
THEIR CHALLENGE

Streamlining access to a wealth of library content in record time

Swisscom is Switzerland’s leading provider of mobile, internet, and TV services. In a country of nearly nine million people, Swisscom has more than six mobile connections and two million broadband customers. It’s a household name, but it’s also so much more than a consumer-facing brand. Swisscom provides information and communications technology services to some of the country’s leading enterprises and the buoyant small and medium-sized enterprise sector. It sees its role as empowering Switzerland’s digital future and claims to be the most trusted Swiss technology innovator.

The business plans to invest CHF100 million ($117M) in AI solutions in the coming years. It is working with Nvidia to build generative AI (gen AI) full-stack supercomputers, based on Nvidia accelerated computing and Nvidia AI software. Swisscom wants to take a leadership position in AI, helping find and develop go-to-market AI services relevant to Swiss customers.

As part of this, Swisscom is keen to embrace AI within its own operations and is exploring several use cases.

One particular case is e.foresight, Swisscom’s independent “think tank for the banking industry.” The financial services sector accounts for nearly 10% of the Swiss gross domestic product; e.foresight identifies, monitors, and analyzes trends and behavioral and technological developments in the global financial sector. Used by 30 of the country’s leading banks, it has built up a sizable library of expert content over the years.

Swisscom is using MongoDB Atlas to apply gen AI to this extensive library. The engagement enables Swisscom to extract maximum value from its content, producing bespoke content for the hundreds of e.foresight users within the 30 banks subscribing to its services. By doing so, it is transforming the speed, accuracy, and relevancy of search requests. Rather than forwarding six reports for users to pore over, it can use gen AI to produce a condensed summary within seconds.

“e.foresight has over 3,500 documents about trends in the banking industry in its library, with more being added each day,” said Dr. Martin Lorenz, Product Manager, Banking Front Solutions, Swisscom. “MongoDB Atlas enables us to store and search all that information and create something relevant to a specific request.”

OUR SOLUTION

Enriching large language models with MongoDB Atlas Vector Search

In practical terms, the Swisscom gen AI application needed to enable large language models (LLMs) to make sense of the e.foresight document library. The library is not only large but also diverse. It includes unstructured data, such as written reports, recordings of live events, graphics, and external studies, and it continues to grow.

MongoDB was critical to achieving Swisscom’s goal by helping power its retrieval-augmented generation (RAG) application. Now all documents in the e.foresight library are stored in MongoDB Atlas—a single, secure database for storing and searching vectors alongside operational data. Swisscom can then convert the unstructured data into vector embeddings and use MongoDB Atlas Vector Search to find segments of relevant context to feed the LLMs up-to-date contextual, domain-specific data. As a result, the application can generate more accurate, highly relevant responses for users.

In a fast-moving industry, with constant breakthroughs in gen AI capabilities, MongoDB empowered Swisscom to move quickly from idea to production, enabling faster speed to market. Lorenz reached out to MongoDB on February 6, 2024, and had a prototype based on a subset of data fully built on the MongoDB Atlas Developer Data Platform by February 15. After a month of testing alongside MongoDB and the university of applied science ZHAW, the Swisscom internal team took over the platform operations.

The team added new features, and after another month of in-house testing, the platform went into production in early May.

“Total development effort for the first solution was around six days. Importantly for a project where you’re exploring ground-breaking ideas, working with MongoDB enabled us to move quickly, learn, and reuse.”

Dr. Martin Lorenz, Product Manager, Banking Front Solutions, Swisscom

OUTCOME

Underlining leadership in the creation of AI applications

The success of the project has, first and foremost, improved the e.foresight experience for subscribers. Rather than pointing users to a 4,000-word article, the application can use gen AI to efficiently extract and accurately summarize specific content from multiple sources. Additionally, the team has found that the difference in relevancy of answers via AI is “night and day” compared to content produced by ChatGPT, feeding from general online sources.

“Our answers are much more concrete and accurate. Any industry, but particularly the banking industry, wants solid answers, reliable sources, and up-to-date metrics,” said Lorenz.

The quality of answers will only improve as the platform is refined. Users can uptick answers, helping flag accurate searches and train the model for better results. All content also includes links to source material. “It’s important we demonstrate we’re a partner of trust,” Lorenz added.

The rate at which the e.foresight library adds new content will also increase: it will apply gen AI to help write new-trends analyses, and refine content based on user activity. The gen AI application will have more and better-quality content to consume. Ultimately, Swisscom has found that e.foresight is seen as a progressive, user-focused, and more-trusted source for valuable insights in the banking industry.

At a broader level, the project has enabled Swisscom to demonstrate its progress in creating meaningful AI use cases. The company is not just investing money in AI but is also taking practical steps to upskill its teams and develop services relevant to its target markets. The company now has a variety of AI projects underway, from chatbots to search to content creation.

Lorenz explained that the experience on e.foresight will play out across Swisscom. As part of its Swiss AI Platform, the company is launching GPU Rental, GenAI Studio, and AI Work Hub, all services aimed at encouraging the uptake of AI among Swiss enterprises.

“We have many AI specialists working at Swisscom and there are several ways we can build our gen AI experience by using MongoDB Atlas Vector Search to build specific RAGs. In Switzerland and especially for our clients in banking there is always the issue of sensitive data, and with this project we’ve proved we can create something powerful using data held only in Switzerland. Vectorized search will become increasingly important.”

Dr. Martin Lorenz, Product Manager, Banking Front Solutions, Swisscom

To learn more, visit MongoDB Atlas.

What will your story be?

MongoDB will help you find the best solution.