Models, agents and the AI Act in practice.
What we learn on the job: when training a model pays off, how to build an agent you can trust, and what the law actually asks of companies. With numbers where we have them.
9 notes
-
GraphRAG or plain RAG for company documents? When a knowledge graph pays off
When plain RAG is enough for company documents and when a knowledge graph pays off: failing questions, extraction cost, Slovenian inflection, how to start.
Read → -
Can you fine-tune a model on customer data under GDPR? EDPB Opinion 28/2024 in practice
What EDPB Opinion 28/2024 means for fine-tuning on customer data: legal basis, anonymisation before training, memorisation tests, DPIA and a DPO checklist.
Read → -
AI invoice and contract extraction on your own server: when a SaaS is enough and when you need your own model
When a SaaS for incoming invoices is enough, when contracts and sensitive documents need your own model, how to measure accuracy per field, and how to start.
Read → -
A small fine-tuned model for customer support in Slovenian: accuracy, frontier fallback, how to start
Which tickets suit a model, how many past replies you need, a 4B–12B model with retrieval and a frontier fallback, how we measure it and how to start.
Read → -
Anonymising Slovenian documents with a local model: accuracy, GDPR and how to start
Why regex fails on Slovenian names and EMŠO, how a local 4B–12B model plus rules is measured for recall, what GDPR counts as anonymous, and how to start.
Read → -
AI agents with human approval for small companies: autonomy tiers, real examples and how to start
What an AI agent is and is not, five autonomy tiers, a correspondence agent that waits for approval, what to measure, the AI Act and how a pilot works.
Read → -
Running a private LLM on your own server: models, setup and how to start
Which model size fits a narrow task, GGUF or vLLM, air-gapped setup, GDPR and the AI Act, cascades and EU cloud. And how to start.
Read → -
Fine-tuning or RAG for documents in your language?
When retrieval (RAG) is the right answer, when training a model on your data is, and when you need both. With numbers from our public work.
Read → -
AI Act for SMEs after the Digital Omnibus: what still applies on 2 December 2026
What a company must do under the EU AI Act by 2 December 2026, what the Digital Omnibus changed, and a checklist for chatbots, voice agents and HR tools.
Read →