The deployEMDS project continues to demonstrate its impact across Europe, with the Flanders use case in Belgium providing a particularly clear example of its progress. The region’s implementation site has not only advanced the way mobility data is shared and used but also enabled commercial innovation that is being publicly recognised.
Gader, developed independently by the private company Movias, is an AI assistant that makes traffic measurement data accessible through a natural-language chat interface. It is built on the Flanders Traffic Measurements Data Space created under the deployEMDS use case. Gader stands as a full commercial product, capable of bringing together traffic measurements from all over Flanders and making them queryable through a Large Language Model. It serves as an excellent example of how data spaces can enable new types of value creation.
This innovation has been recognised twice in Belgium. Gader recently won the Smart Mobility Award, and shortly thereafter, the Geospatial Award 2025 in the “Best Project” category. As Movias highlighted when announcing the win, this achievement was possible thanks to the solid data infrastructure and collaboration established through deployEMDS, Digitaal Vlaanderen, data partners, and clients across the region.
The Flanders implementation site has also been active in sharing these achievements and insights with the broader mobility and data ecosystem. deployEMDS was represented at the first Belgian NAP User Day in Brussels, providing a platform to discuss the future of transport data access. Recently, the project was also featured at the ITS.be Congress 2025, where data and AI were at the center of discussions. Steven Logghe, representing the deployEMDS Flanders use case, moderated a session on the future of connected mobility, highlighting how data spaces and AI can contribute to safer and smarter transport systems.
Beyond the Gader chat interface, as part of the deployEMDS use case, Flanders partners imec and Digitaal Vlaanderen are also exploring the potential of transfer learning with an AI model trained on data in the Flanders traffic measurement data space. In the future, the model could be transferred to another region, supporting analysis and prediction even where local data is limited. Using Model Context Protocol, external sources, such as weather data and holiday calendars could also be connected to the regional traffic measurement data space, further enriching the model’s insights. These efforts not only demonstrate what deployEMDS enables today but also suggest new cross-border use cases that could be explored.
Looking ahead, work continues on refining these tools and strengthening technical foundations. What is already clear is that deployEMDS is enabling more than data exchange; it is opening the door to innovative services, better decision-making, and new value chains for mobility. The progress in Flanders shows how far this approach can go: from early experiments to award-winning products now shaping the future of transport intelligence.

