The difference between a decent answer and a production-ready result lies in the prompt and the context.
Generative models are powerful but erratic. If you prompt systematically and supply the right context, you get reliable results; if you 'just try something', you keep on guessing.
You learn to work like a professional: reproducible and testable. Prompts as building blocks under version control, test sets to guard quality, and retrieval to feed the model your organisation's knowledge.
This subject did not exist, and it is already changing under your hands. The prompt tricks of two years ago have been overtaken by models that got better at guessing what you mean. What remains is the question underneath: which context does the model get to see, and which does it not.
That makes this the strangest programming subject there is: you write in natural language, for a compiler allowed to answer differently to the same input. Version control, test sets and evaluation are not polish — without them you have no discipline, only a guess.
You build prompt pipelines for real tasks from your own work — tested, documented and transferable.
A consultant unlocks hundreds of policy documents through retrieval and systematically tests whether the answers are correct.
An analyst has the model deliver reports in a fixed format, ready for the next system in the chain.
A team lead builds a test set that automatically checks every prompt change.
You take this module the way you take the whole programme: classes every other week on Friday and Saturday, with a study load of 15–20 hours per week, of which 10–15 hours is self-study. The teaching is a mix of classroom sessions, workplace learning, blended learning and working groups or study teams — taught by lecturers who practise the profession themselves on a daily basis.
You conclude each theme with a professional product or a technical solution addressing a real situation in your own work, which you discuss in an assessment with the lecturer. This way your portfolio grows with real work — and your employer benefits directly.
The format is not new: the teaching approach and the AI modules have been running for three years at the AI Proeflokaal — with business, with government, and across part-time modules and minors. What you meet in class here has already been worn in elsewhere.
After this module you deliver reproducible, tested prompt pipelines that colleagues can adopt and trust.
Email or call the programme team — we are happy to think it through with you.