Home Case Studies CAF Signalling Facilitating information consumption with gen AI
CAF Signalling + IBM
illustration of watsonx.ai as purple circles intersecting
Extracting volumes of information

CAF Signalling, CAF Group’s comprehensive solutions division for railway signalling systems, is a Spanish company that designs and provides integral solutions for railway signalling and control all over the world.

Its dedicated on-board systems development team navigates a challenging landscape of dense and complex documentation, the European Rail Traffic Management System (ERTMS) standards, on a daily basis. This work entails constant search, interpretation, implementation and, of course, adaptation to evolving standards, which secures the intricate task of ensuring interoperability among trains across different countries.

Given the intricate nature of this task, compounded by the continuous evolution of standards and the complexity of the documentation, CAF Signalling recognized the need for a strategic approach. The objective was to streamline access to ERTMS information, making it more accessible and facilitating smoother integration with the evolving standards.

In response to this multifaceted challenge, CAF Signalling embarked on a project to identify optimal tools and establish robust connections that would enhance the team’s ability to navigate and extract pertinent information from the ERTMS documentation. All, with the overarching goal to create a more efficient workflow, reducing the complexities and ensuring the seamless compliance of CAF’s trains with on-rail signaling requirements, thereby promoting interoperability across international rail networks.

3 weeks
duration of proof-of-concept (POC)

1
unique point for more centralized knowledge and homogenized sources
Consuming information with gen AI assistants

To meet its information gathering challenges, CAF Signalling collaborated with IBM® Client Engineering to explore a combination of tools and generative AI (gen AI). They decided to conduct a proof-of-concept (POC) test of the solution during a period of three weeks in which together, the team used IBM watsonx™ Assistant, IBM Watson® Discovery and IBM watsonx.ai™ to facilitate access to the ERTMS standards. This approach assured a more efficient workflow while reducing complexity, and it helped CAF Signalling manage compliance of CAF’s trains with on-rail signaling requirements, thereby promoting interoperability across international rail networks.

Gathering information more efficiently and optimally with gen AI

 

The solution proved to be a new beginning of an automation journey through document governance, which helped increase productivity and efficiency and save time. For one thing, now knowledge is more centralized, and sources are homogenized so documents are no longer consumed one by one, but in one unique point. Monitoring capabilities were also incorporated, giving additional data about how users interact with the information. With the information all in one place, and in natural language, employee satisfaction and autonomy also increased while the learning curve among employees decreased.

In the future, the team hopes to scale the solution and its benefits across the entire organization.

CAF logo in red
About CAF Signalling

CAF Signalling (link resides outside of ibm.com), the technological subsidiary of CAF Group, is focused on the design, development, manufacturing, supply and maintenance of rail signalling systems, thus providing integrated signalling solutions for infrastructures and rolling stock, both in Spain and internationally.

Watsonx.ai is helping companies custom build AI solutions to suit their specific needs.
Explore watsonx.ai Start your free trial
Legal

© Copyright IBM Corporation 2024. IBM Corporation, New Orchard Road, Armonk, NY 10504.

Produced in the United States of America, January 2024.

IBM, the IBM logo, ibm.com, IBM Watson, IBM watsonx, watsonx, and watsonx.ai are trademarks or registered trademarks of International Business Machines Corporation, in the United States and/or other countries. Other product and service names might be trademarks of IBM or other companies. A current list of IBM trademarks is available on A current list of IBM trademarks is available on ibm.com/legal/copyright-trademark.

This document is current as of the initial date of publication and may be changed by IBM at any time. Not all offerings are available in every country in which IBM operates.

All client examples cited or described are presented as illustrations of the manner in which some clients have used IBM products and the results they may have achieved. Actual environmental costs and performance characteristics will vary depending on individual client configurations and conditions. Generally expected results cannot be provided as each client’s results will depend entirely on the client’s systems and services ordered. THE INFORMATION IN THIS DOCUMENT IS PROVIDED “AS IS” WITHOUT ANY WARRANTY, EXPRESS OR IMPLIED, INCLUDING WITHOUT ANY WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND ANY WARRANTY OR CONDITION OF NON-INFRINGEMENT. IBM products are warranted according to the terms and conditions of the agreements under which they are provided.