AI Agent Risks and Controls
Why this needs its own article An agent takes actions. A single-step AI feature produces text somebody reads. That difference
AI Agents in Business Systems
Start with what already works Before reaching for an agent, know what your system already does. Odoo has automated actions,
What Is an AI Agent?
The difference from everything else Most AI in a business system does one thing when asked. Read this document. Draft
AI for Quality Management
The constraint that shapes everything Quality and compliance decisions are auditable. Somebody may ask how a conclusion was reached —
What a Fine-Tuned Model Cannot Do
Why this article exists Most writing about fine-tuning covers what it achieves. Knowing the limits matters more, because that is
Choosing a Model Size
What the number means A model’s size is its parameter count — 1B is one billion, 3B is three billion,
Synthetic Training Data
The data problem Fine-tuning needs examples. Thousands of them, in a consistent format. For most business subjects, those examples do
Case Study: A Compliance Analyzer
What it is A LoRA adapter fine-tuned on Llama 3.2 3B, built to analyse statements about how an organisation operates
Case Study: A Quality Management Model
What it is A LoRA adapter fine-tuned on Llama 3.2 1B, trained on quality management systems and ISO standards. Published
Running AI Models Locally
Why run a model locally Three reasons, and any one can decide it. Your data does not leave. Nothing is