Can AI agents act without being trusted?
An AI assistant that answers a question can make a mistake. An AI agent that reads files, delegates tasks and calls tools can turn a mistake into an action. That difference matters as organizations…
AGNTCON Europe 2026 Conference Report
GNTCon \+ MCPCon Europe 2026 was held in Amsterdam. It is a practitioner conference dedicated to building, securing and operating AI agents in production, and to the Model Context Protocol that most…
Why We Rewrote the Euranova Manifesto
A company culture is frequently packaged as static branding: abstract values printed on a poster, repeated during onboarding, and forgotten during system outages. For an engineering organization,…
Internship Offers 2026-2027
Every year, Euranova opens master's thesis and end-of-study internship tracks embedded directly within our consulting practices and prototyping lab. Explore our internship opportunities.
Beyond the illusion of anonymity: a pragmatic approach to data privacy
Stripping obvious identifiers from your datasets is rarely enough to protect user privacy or avoid massive regulatory fines. Discover a structured, risk-based blueprint for true data anonymization that perfectly balances rigorous legal compliance with real business utility.
GraphRAG: unlocking enterprise knowledge with knowledge graphs
Standard RAG struggles with complex enterprise queries. Discover how GraphRAG uses Knowledge Graphs, ontology-driven pipelines, and AI agents for smarter retrieval.
Who judges the AI? Fine-tuning Mistral 7B as a specialized evaluator
As organizations scale their Generative AI from prototypes to production, verifying output quality has become the next major cost bottleneck. Do you really need a 'frontier' LLM to judge your AI? We investigated whether a smaller, specialized model could do the job.
Engineering Beyond the Hype: How Knowledge Sharing Drives Production-Hardened AI and Data Systems
In modern enterprise data and AI engineering, technology moves faster than governance frameworks can adapt. New open-source models, orchestration platforms, and vector paradigms emerge weekly. For…
Flight safety boosted with AI-powered obstacle detection
A leading helicopter manufacturer sought a cost‑effective way to detect thin obstacles during low‑altitude flights, requiring an accurate vision‑based system trained with diverse real and synthetic data to improve safety in challenging environments.
Beyond Vector Search: Building and Benchmarking Enterprise GraphRAG Architectures
Retrieval-Augmented Generation (RAG) has become the standard pattern for grounding Large Language Models (LLMs) in enterprise domain knowledge. However, standard RAG architectures—relying primarily…
Engineering On-Premise LLM Infrastructure: Architecture, Benchmarking, and Production Realities
By Pierre Hockers - Data scientist For organizations operating under strict regulatory bounds or high security requirements, cloud-based LLM APIs present an operational bottleneck. When data…
Sovereign AI Infrastructure in Europe: an engineering and architectural evaluation
By Pierre Hockers - Data scientist European enterprises evaluating Generative AI face a complex infrastructure decision. While the pressure to adopt Large Language Models (LLMs) is high, operating…
Mastering Sovereign AI & Local LLMs
Don’t Let Your Data Become a Liability: navigating the evolving landscape of data modeling
This article serves as a practical guide to choosing the right architectural blueprint to bridge the gap between chaotic raw data and structured insights.
Sovereign compute at scale: architecting for the Belgian AI Factory Antenna
The Belgian AI Factory Antenna gives SMEs and startups unprecedented access to EuroHPC supercomputers, but it comes with strict access rules and technical trade-offs. Discover how to architect your AI workflows for the EuroHPC landscape in our latest guide.
Pioneering the future of aerial intelligence through advanced 3D digital twins
How do we inspect critical infrastructure safely and efficiently? To tackle this, dive into the combination of aerial platforms with advanced AI to create photorealistic, queryable 3D Digital Twins.
Quantifying Retrieval Quality in GraphRAG: A Schema-Agnostic Approach
In this paper, we propose a novel schema-agnostic framework for the automated generation of synthetic evaluation datasets from KGs. Unlike previous approaches, our framework establishes a rigorous, deterministic ground truth to specifically quantify the retriever performance across nine distinct query categories, including multi-hop and aggregation tasks.
Bridging the Gap: The "Lab-to-Fab" Protocol for Production-Hardened Data Systems
The primary bottleneck in modern data engineering is not a lack of innovative ideas; it is the friction encountered when transitioning a successful prototype into a production-hardened system. When…
Navigating the AI transition in marketing
IEEE Big Data 2025: the shift from scale to smart
IEEE Big Data 2025 signals a shift to secure, hybrid intelligence. CTO Sabri Skhiri unpacks the engineering reality from the conference: the practical shift to embeddings, the real need for security layers, and the limitations of AI agents in production.
Evaluation of GraphRAG Strategies for Efficient Information Retrieval
Traditional RAG systems struggle to capture relationships and cross-references between different sources unless explicitly mentioned. This challenge is common in real-world scenarios, where information is often distributed and interlinked, making graphs a more effective representation. Our work provides a technical contribution through a comparative evaluation of retrieval strategies within GraphRAG.
Flight Load Factor Predictions based on Analysis of Ticket Prices and other Factors
The ability to forecast traffic and to size the operation accordingly is a determining factor, for airports. However, to realise its full potential, it needs to be considered as part of a holistic approach, closely linked to airport planning and operations. To ensure airport resources are used efficiently, accurate information about passenger numbers and their effects on the operation is essential. Therefore, this study explores machine learning capabilities enabling predictions of aircraft load factors.
Investigating a Feature Unlearning Bias Mitigation Technique for Cancer-type Bias in AutoPet Dataset
We proposed a feature unlearning technique to reduce cancer-type bias, which improved segmentation accuracy while promoting fairness across sub-groups, even with limited data.
Beyond the hype: how NVIDIA GTC Paris 2025 trends are shaping industry
NVIDIA GTC Paris 2025 revealed an unprecedented scale and breadth of innovation, with a clear focus: not on predicting the future of AI, but on demonstrating how existing technologies are being put to work today. Our CTO Sabri Skhiri was on the ground to bring back insights.