Europe is investing billions in satellites, ground segments, and federated services through initiatives like Domino-E. But infrastructure alone does not guarantee impact. For Earth Observation (EO) to become a true driver of sovereignty and competitiveness, it must be usable—not just by experts in mission control centres, but also by municipalities, SMEs, and civil actors who need timely information.
Yet today, access to EO often depends on costly consultancy. Ordering an image requires not only knowing which constellation to task but also understanding orbital schedules, technical constraints, and metadata standards. For non-experts, the barrier is steep. The result: a transformative European technology remains underused.
Domino-E’s Virtual Assistant (VA) aims to remove that barrier. By translating natural language into technical requests and guiding users through the process, it makes EO accessible to thousands of new actors.
From Complexity to Simplicity
The starting point for Tilde, the Baltic language-technology company developing the assistant, was simple: most potential users of EO do not know what to ask for. As Director of R&D Raivis Skadiņš recalls, his team shared that confusion at the beginning: Earth Observation was a new field for them, and terms like “ground segment” or “missions” were unfamiliar. That outsider’s perspective, he notes, proved valuable: it mirrored the reality of non-expert users, who face the same confusion when trying to access EO services.
“In the 1990s, we started with proofing tools, and then we moved to dictionaries, machine translation, speech technology, speech synthesis, and recognition. For the past ten years, we’ve been working on virtual assistants. When we started, nobody spoke about virtual assistants. We began with animated heads because we thought that was where the industry was headed. Later, we discovered that people care more about the quality of the conversation. Users prefer virtual assistants that feel natural and smart, and that has guided our direction ever since.”
(Raivis Skadiņš, Domino-E interview)
The assistant therefore acts as a bridge. Instead of expecting a municipal planner or SME to navigate technical menus, it asks them about their needs—geographical area, timing, or conditions—and translates these into parameters the system can process. If an image already exists, it helps them find it. If not, it forwards a properly structured request to Domino-E’s Coverage Service.
Augmenting Human Expertise
A key feature of the Virtual Assistant is that it does not replace operators—it enables them. Today, EO customers rely on domain experts who interpret needs, consult with clients, and book observations. But experts are finite. By collecting routine information up front and handling standard cases, the assistant frees operators to focus on non-standard, creative, or critical tasks. In practice, this means reduced repetition, fewer bottlenecks, and a smarter division of labour between people and machines.
“We don’t see virtual assistants as replacing people but as enabling them. Currently, customers rely on domain experts—operators—to consult with them, specify needs, and book satellite observations. These experts are limited in capacity. By automating routine tasks, the virtual assistant allows operators to focus on creative, complex situations that require their expertise.”
(RaivisSkadiņš, Domino-E interview)
Designing such an assistant is not a one-time effort but a continuous process of learning by doing. The first version of the VA already organizes dialogues, asks for requirements, and gathers parameters. But the real test comes when diverse users interact with it. People ask unexpected questions, use unfamiliar terminology, or phrase requests in ways the system has not seen before.
“We start by imagining how conversations will flow, creating scenarios, and testing them with users to see if the system performs as expected. Then, we invite testers who are unfamiliar with the system to interact with it from scratch. The assistant needs to handle unexpected or out-of-context questions gracefully.”
(Raivis Skadiņš, Domino-E interview)
Tilde approaches this iteratively: first scripting scenarios, then testing with fresh users, and refining based on feedback. The assistant is treated “like an employee,” as Skadiņš puts it—requiring training, updates, and retraining as systems evolve and new data sources become available. This lifecycle approach ensures that the VA remains useful, relevant, and aligned with user needs over time.
Conclusion: From Complexity to Competitiveness
The impact of this development goes far beyond smoother dialogues. By lowering entry costs, the assistant opens EO to thousands of SMEs and local authorities who previously lacked the resources to engage. Instead of hiring expensive consultants to translate their needs, they can now rely on a system that guides them directly.
This democratization matters economically. The more actors access EO, the more innovation emerges—whether in precision agriculture, climate services, smart cities, or emergency response. Instead of a handful of expert providers controlling the market, EO becomes a widely available input into Europe’s digital economy. In this sense, the VA is not just a tool—it is a competitiveness multiplier bridging the gap between complex EO infrastructures and the everyday needs of municipalities, SMEs, and innovators. It complements human expertise rather than replacing it, scales through iterative learning, and empowers a far larger community of users.
For Tilde, joining Domino-E has been, in Skadiņš’s words, “a challenging but deeply rewarding journey.” For Europe, it is a step toward turning its EO investments into a mainstream driver of growth, resilience, and sovereignty. By lowering barriers and broadening access, the Virtual Assistant ensures that Earth Observation is not just about satellites orbiting above—but about data empowering people on the ground.