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.
Static FAQ replaced by smart chatbot
A Belgian telecom provider wanted to cut support calls by replacing its static FAQ with a scalable RAG‑powered chatbot that delivers accurate, immediate answers through a simple search‑based interface.
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.
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.
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.
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.
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!
Turning an intranet into an AI assistant
Sales and support agents can’t live without it : MAiA turns Proximus’ intranet into realtime knowledge, cutting search time and powering 1.4 million questions since launch.
The LLM coding revolution needs a rulebook
Teams ship AI-generated code faster than ever — and accumulate debt just as fast. The problem isn't the tools. It's the missing process around them.