On January 14, 2026, the Flemish research institute VITO announced the launch of SAIL (Sustainable Agentic Intelligence Lab), which aims to develop agentic AI that uses validated data from environmental measurement campaigns, materials science, and industrial systems.
Anyone involved in the digitization of processes is familiar with the saying “garbage in, garbage out.” The result of automated data processing can only be as good as the data on which it is based. Most Internet-based AI systems use the data provided by the Internet. And this data is noisy, unstructured, and has no connection to physical reality.
With SAIL, VITO aims to overcome these disadvantages and develop an agentic AI that weighs up and acts on the operational logic of a physical system.
| What is agentic AI? |
| To understand the difference between generic AI, as we know it from text or image generation programs, and agentic AI, I applied generic AI. According to this, the difference between generic and agentic AI is that between a tool (generic) and an agent: tools execute commands, and each action requires a new command or question. An agent acts independently, pursues specific goals, plans its operations accordingly, uses data and tools independently, checks the results of its actions, and adjusts its next operations accordingly. Hildegard Lyko |
The three pillars of SAIL
The SAIL AI laboratory aims to pioneer work in three areas:
- Development of agentic AI in the form of a multi-agent system that uses open standards and can automatically weigh up, act and coordinate.
- Designing the context of this AI (context engineering): strategic design and management of the information provided to the AI.
- Scientific machine learning, i.e., the development of physically based models and digital twins that combine data-driven methods and simulations.
“The challenge is not to create ever larger models,” says Shane Ó Seasnáin, Director of Digitalization at VITO. “Rather, it is to develop systems that are based on the real physical world by taking into account soil properties, atmospheric dynamics, material properties, and infrastructure constraints. This is what VITO has been working on for decades: measurement and modeling.”
The lab will develop architectural patterns and reusable software components, domain-specific benchmarks, evaluation frameworks for contextual AI, and energy-efficient approaches that are consistent with the principles of sustainable AI. Together, these pillars provide practical tools and frameworks for customers and partners in Flanders and Europe. The aim is to ensure that innovations can be deployed more quickly in industry, that governments can use AI more quickly and efficiently for more effective public services, and that SMEs are given a realistic path to integrating AI into their operations.
First application: Access to Earth observation
In the first SAIL project, openEO API, the ESA-supported open source interface for the joint processing of Earth observation data, is to be expanded to include agentic capabilities.
VITO already contributes significantly to the EO ecosystem and runs large-scale applications on the Copernicus Data Space Ecosystem and the Terrascope platform. In the future, users will no longer have to decide which data is available and how it should be processed, as AI agents will interpret analysis requests on demand and independently compile processing workflows using the available tools and data sets.
“When we have access to Earth observation data and time series, we can rely on objective monitoring of changes on our planet. This forms a solid basis for modelling the future. Today, the transformation of this data into usable knowledge, insights and predictions is still largely carried out by highly trained experts. By adding an agent layer to the European reference implementations of the openEO API, we lower the barrier to using these vast volumes of data, enabling their impact and integration into future business processes to be fully realised”, says Dennis Clarijs, Head of Remote Sensing Services at VITO.
“SAIL is committed to open-source development and European technological sovereignty by creating reusable AI tools that connect VITO products and contribute to a European AI ecosystem independent of proprietary platforms. By linking digital technology with our scientific expertise, we help industry and governments respond and anticipate much faster and more effectively to what lies ahead”, says Inge Neven, CEO of VITO.