Strategic Takeaways from AGNTCON Europe 2026
While building a basic AI agent is easy, securely governing it and preventing long-term code degradation in production is the real challenge. Discover why engineering leaders must radically rethink software architecture and implement robust AI Control Planes to safely scale agentic workflows.
The "chat to data" promise vs. reality: evaluating native text-to-SQL models
While Text-to-SQL promises effortless data democratization, can Snowflake Cortex and Databricks Genie replace manual SQL in production? Testing reveals execution accuracy plummets. Discover what managers must do first.
Can AI agents act without being trusted?
Give AI agents the flexibility to plan, but keep the authority to act in accountable hands. Discover how separating an agent's reasoning from independent authorization services ensures secure, governable automation.
Tech insights from AGNTCON Europe 2026
Step beyond the hype and dive into real-world production war stories from AGNTCON + MCPCon Europe 2026. Discover how engineering leaders are securely scaling multi-agent systems using stateless MCP, robust identity brokers, and deterministic control planes.
Why we rewrote the Euranova Manifesto
Why Euranova updated its engineering manifesto: moving from headquarters-centric rituals to a production operating manual for distributed Data & AI teams.
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.
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.
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…
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.
Muppet: A Modular and Constructive Decomposition for Perturbation-based Explanation Methods
The topic of explainable AI has recently received attention driven by a growing awareness of the need for transparent and accountable AI. In this paper, we propose a novel methodology to decompose any state-of-the-art perturbation-based explainability approach into four blocks. In addition, we provide Muppet: an open-source Python library for explainable AI.
Tech insights from GTC Paris 2025
Among the NVIDIA GTC Paris crowd was our CTO Sabri Skhiri, and from quantum computing breakthroughs to the full-stack AI advancements powering industrial digital twins and robotics, there is a lot to share!
Development & Evaluation of Automated Tumour Monitoring by Image Registration Based on 3D (PET/CT) Images
Tumor tracking in PET/CT is essential for monitoring cancer progression and guiding treatment strategies. Traditionally, nuclear physicians manually track tumors, focusing on the five largest ones (PERCIST criteria), which is both time-consuming and imprecise. Automated tumor tracking can allow matching of the numerous metastatic lesions across scans, enhancing tumor change monitoring.
Unlocking the power of unsupervised learning with interpretable graph embeddings
Unsupervised learning offers immense potential, but deciphering the results is often a challenge. Discover INGENIOUS, a groundbreaking framework from Euranova that generates interpretable graph embeddings that reveal the 'why' behind complex data patterns, empowering organizations to make informed decisions with confidence.
Tech Insight from IEEE Big Data 2023
Our CTO, Sabri Skhiri, recently travelled to Sorrento for IEEE Big Data 2023. In this article, Sabri explores for you the various keynotes and talks that took place during the conference, highlighting the noteworthy insights and the practical applications shared by industry leaders.
Robust ML Approach for Screening MET Drug Candidates in Combination with Immune Checkpoint Inhibitors
Present study highlights the significance of dataset size in ICI microbiota models and presents a methodology to enhance the performances of a multi-cohort-based ML approach.
Augment to Interpret: Unsupervised and Inherently Interpretable Graph Embeddings
In this paper, we study graph representation learning and show that data augmentation that preserves semantics can be learned and used to produce interpretations. Our framework, which we named INGENIOUS, creates inherently interpretable embeddings and eliminates the need for costly additional post-hoc analysis.
TS-Relax : Interprétation des représentations apprises pour les séries temporelles
Les modèles d’apprentissage de représentations sont de plus en plus utilisés, mais des modèles d’IA explicables et de confiance sont nécessaires. Ce travail présente l’adaptation aux séries temporelles d’une méthode d’interprétation de représentation initialement conçue pour les images.
Comparison of Machine Learning Approaches for POD24 Prediction
Early identification of patients with relapsing follicular lymphoma (FL) is critical but remains elusive. We initiated a collaboration between the academic CALYM Carnot Institute aiming at developing interpretable artificial intelligence (AI) models based on PET images to predict POD24.
A Fair Classifier Embracing Triplet Collapse
In this paper, we study the behaviour of the triplet loss and show that it can be exploited to limit the biases created and perpetuated by machine learning models.