https://boroica.com/insights Practical notes on AI automation, workflow selection, document processing and the engineering behind a reliable AI step. en Sun, 25 Oct 2026 09:00:00 GMT https://boroica.com/insights/where-ai-automation-saves-time https://boroica.com/insights/where-ai-automation-saves-time Sat, 24 Oct 2026 09:00:00 GMT A practical model for choosing a workflow: volume, handling time, exception rate and the cost of the review step. Includes a one-page decision test. Automation https://boroica.com/insights/ai-act-article-50-engineering https://boroica.com/insights/ai-act-article-50-engineering Thu, 22 Oct 2026 09:00:00 GMT Article 50 transparency obligations are due from 2 December 2026. What engineering teams must build, what is legal work, and how to avoid overclaiming. Compliance engineering https://boroica.com/insights/when-fine-tuning-beats-prompting https://boroica.com/insights/when-fine-tuning-beats-prompting Tue, 20 Oct 2026 09:00:00 GMT A decision guide for engineering leaders: the four problems fine-tuning solves, the volume threshold where it pays, and how to measure whether it worked. Fine-tuning https://boroica.com/insights/evaluating-rag-before-users-do https://boroica.com/insights/evaluating-rag-before-users-do Sun, 18 Oct 2026 09:00:00 GMT A practical evaluation protocol for RAG: golden sets, retrieval metrics, rubrics, LLM judges and a CI gate that catches regressions before users do. Evaluation https://boroica.com/insights/on-premise-llm-deployment https://boroica.com/insights/on-premise-llm-deployment Thu, 15 Oct 2026 09:00:00 GMT Hardware sizing, quantization, serving, security and operations: an honest checklist for running an LLM on infrastructure you own, without the demo math. Deployment