Engineering notes
Engineering writing on enterprise AI, ERP processes and system integration. Notes that come out of the work.
AI projects that handle personal data have three architectural options: mask the data before it reaches the model, use an enterprise cloud hosted in a European region, or run an open model on your own infrastructure. The choice is a trade-off between cost and risk, and which data goes where should be put in writing at the start of the project.
In most enterprise projects the right answer is RAG. Fine-tuning does not teach a model new knowledge; it teaches behaviour and format. Use RAG when your information changes, when answers must cite a source or when your document volume is large. Add fine-tuning when you need a fixed tone, format or domain language.
Tell us briefly and we will get back to you. The first call is not a pitch: we listen to what you need and say plainly whether it can be solved. If you need an NDA, please let us know before the call.