Every article and note from the engine room, newest first.
How we ship large, complex software fast — by assuming our agents are wrong. Essentially all production code here is written by AI agents. The question people ask is how you trust any of it; the answer is that we don't trust the agents, we build the machinery that catches them.
Aidan is AI + Danmark: built in Aalborg, answers in Danish, data stays in Europe. The story of an assistant who learned his job from twelve colleagues — and why he says so when he doesn't know.
From 24 August, ChatGPT shows ads in Denmark. They are not personalised — they are picked from the question the user just typed. That makes the question the new audience, and it changes what is worth building.
AI is no longer a question of *whether*, but *how*. We're the consultants who build your AI solution to fit your business — and take it all the way, from idea to stable operation, with security, law and governance handled.
Inline editing lets you click straight on a piece of text on your live website and fix it on the spot. Under the hood it's a real headless CMS — so everything you change lands in the same place, whether you do it on the page or in the admin.
"Chat with your site" isn't a future vision — it's the screen that greets you at login. 60+ tools, translation on command, and the same engine available as a headless CMS via REST/MCP.
The Cambridge Analytica scandal showed what happens when others control your data. The EU is now tightening cloud sovereignty requirements — and that's exactly why broberg.ai is built from scratch without a single line of code depending on a tech giant's infrastructure.
Model Context Protocol is quietly changing how AI agents interact with the systems around them — including your CMS. Here's what it means for your website, your workflows, and your business.
Last night I asked our AI for a screenshot. It couldn't get a real one working — so it built its own and sent it as proof. Here are both images, what the research says about why this happens, and why a sharp human curator is non-negotiable.
Karpathy, Tan, and Liu all start from the same diagnosis — your agent is a retriever, not a thinker. They reach three different architectures: retrieve (RAG), compile (LLM Wiki), and act (Fat Skills / GBrain). Trail picked Compile, deliberately.
Anyone can claim an AI-generated feature works. The interesting question is whether anyone has actually watched it do that — in a real browser, not just a log line that says "build succeeded."
We never route an AI task to a specific model because it's the one we're used to. We route by the task — and the moment it touches your customers' data, it's automatically sent to a model hosted in the EU.
broberg.ai isn't built by one developer at a time. It's built by a fleet of AI agents working in parallel, checking each other's work, and never calling anything done until it's been proven in a real browser.
Supervised Fine-Tuning has become the new buzzword — but it's one tool out of four. We walk the full staircase from prompt engineering through RAG to SFT, and add our own fourth path: Trail, a compile-at-ingest knowledge engine.
Every site in the broberg.ai universe — this one included — runs on the exact same engine. Here's a look behind the curtain at cms: how it works, and why it matters for you as a customer.
AI writes first now. That doesn't change what makes a piece of content good — it changes who writes it first, and what your job becomes afterward: deciding what's worth keeping.
If AI starts designing, what will designers do? We build AI tooling for a living — and our answer is that designers will design how AI decides. Not less design. Design at a higher altitude.