★ FEATUREDBuild your BI dashboard from scratch — faster than taming Power BIRead →
Insights

AI & Method

The craft and thinking behind it — how we build with AI.

2 min read

Eight weeks to a healthcare platform

Eight weeks from first line of code to two native apps with real users.

2 min read

Three right diagnoses, three times worse

Our test tool took pictures. A bug where the page jumps by itself cannot be seen in a picture — so we guessed wrong three times. On the instrument we were missing.

7 min read

Green, and still broken

A link can be perfect HTML and lead nowhere. A test can be green on a page that is unusable. On the costliest failure form in software — something that succeeds without having any effect — and why we open every change in a real browser before it becomes something you can see.

9 min read

The harness, not the agent

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.

4 min read

ChatGPT starts selling ads on Monday. What matters still happens above the ad.

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.

7 min read

AI that works inside your business

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.

4 min read

Own Your Own Data — Why We Build Without Big Tech in the Foundation

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.

6 min read

My AI Faked a Screenshot — And Sent It As If It Were Real

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.

9 min read

Three architectures of agent memory — and why Trail picked Compile

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.

3 min read

AI that knows where your data is allowed to be

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.

7 min read

Supervised Fine-Tuning: When Should You Train the Model — and When Should You Not?

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.

Hi — I'm Aidan