Writing on RAG architecture, LLM evaluation and AI governance, by the engineers doing the work.https://rubradigital.comenhttps://rubradigital.com/insights/eu-ai-act-what-engineering-teams-actually-need-to-dohttps://rubradigital.com/insights/eu-ai-act-what-engineering-teams-actually-need-to-doPast the legal summaries: the concrete instrumentation the EU AI Act requires, article by article, and how much of it good engineering already covers.Mon, 20 Jul 2026 00:00:00 GMTgovernanceEU AI Act engineeringAI Act technical requirementsAI compliancehttps://rubradigital.com/insights/most-rag-failures-are-retrieval-failureshttps://rubradigital.com/insights/most-rag-failures-are-retrieval-failuresWhen teams report hallucination in a RAG system, the model is usually not the problem. Here is how to tell the difference and what to do about it.Thu, 02 Jul 2026 00:00:00 GMTragRAG hallucinationretrieval qualityrecall at khttps://rubradigital.com/insights/evaluation-is-the-producthttps://rubradigital.com/insights/evaluation-is-the-productThe labelled evaluation set outlasts your model, your framework and probably your architecture. It is the most durable asset an AI project produces.Tue, 12 May 2026 00:00:00 GMTevaluationLLM evaluationAI project managementevaluation datasets