Blog
Insights & ideas
Engineering notes on AI, software development and building products that hold up in production.
AI agents
AI agent architecture that survives production
Why production agents need narrow tools, explicit states and a human hand-off — and how to structure them.
AI development
RAG vs fine-tuning: which one does your AI product need?
A practical way to decide between retrieval-augmented generation and fine-tuning, and when to use both.
AI development
Running LLMs on a single 16 GB GPU: what's realistic
Notes on model size, quantisation and serving when self-hosting open-weight models on consumer hardware.
Start here
Have an AI product in mind?
Send a short brief. We'll reply personally with questions or a suggested next step — usually a technical discovery call.