---
title: Insights
source: https://rubradigital.com/insights
site: Rubra Digital
description: Writing on RAG architecture, LLM evaluation and AI governance.
---

# Insights

**Summary:** Writing on RAG architecture, LLM evaluation and AI governance.

## The EU AI Act: what engineering teams actually have to build

Most EU AI Act coverage is written for lawyers. This is the engineering view: which articles translate into logging, evaluation, documentation and oversight work, what each one concretely requires, and how much of it a well-run team is already doing.

Published: 2026-07-20

Full page: https://rubradigital.com/insights/eu-ai-act-what-engineering-teams-actually-need-to-do

## Most RAG failures are retrieval failures

In the RAG systems I audit, most wrong answers are cases where the correct passage never reached the model. That is a retrieval bug, not a hallucination, and prompt engineering cannot fix it. This piece explains how to diagnose the difference and what to change.

Published: 2026-07-02

Full page: https://rubradigital.com/insights/most-rag-failures-are-retrieval-failures

## Your evaluation set is the real product

Models change, frameworks are replaced, architectures get rewritten. A well-built labelled evaluation set survives all of it and makes every future decision cheaper. It is the highest-leverage artefact in an AI project and the one most often cut.

Published: 2026-05-12

Full page: https://rubradigital.com/insights/evaluation-is-the-product

---

Rubra Digital. Independent LLM and RAG consulting for regulated and document-heavy organisations in Europe and North America.
Contact: hello@rubradigital.com · https://rubradigital.com/contact