Glossary AI technique

Prompt engineering

What is prompt engineering?

Prompt engineering is carefully formulating the instruction to an AI model, so it reliably produces the desired result.

Also known as promptingprompt design

The same model gives a mediocre or an excellent answer, depending on how you phrase the question. Prompt engineering is the craft of getting that instruction right: stating the task, the context, the desired format and the boundaries clearly. Providing good examples often helps more than a longer explanation.

In a serious application the prompt is not a loose sentence, but a deliberate piece that is tested and version-controlled. If you change it, you measure with evals whether it gets better or worse, because a small rephrasing can make an unexpectedly large difference.

Prompt engineering is the cheapest dial to turn: you often solve a problem with a better instruction before you reach for RAG or fine-tuning.

Last updated: 18 June 2026

Relatedterms

Read on in the glossary

All terms

AI techniqueLLM (Large Language Model)An LLM is a large language model trained on enormous amounts of text, which lets it understand and generate language; it is the engine under tools like ChatGPT, Claude and Gemini.AI techniqueEvalEvals are automated tests for AI features that measure how accurately, safely and stably they perform on a fixed set of representative examples.AI techniqueRAG (Retrieval-Augmented Generation)RAG lets a language model first retrieve the right documents from your own sources and base its answer on those, so it draws on your knowledge instead of only its training.AI techniqueFine-tuningFine-tuning is training an existing language model further on your own examples, so it fits a specific task, tone or field better.

Where does most of your time go?
That is where we start.

Tell us which work comes back every week. We show you what AI prepares, and what you only still approve.

Book a call

Not ready for a conversation yet? See what we built first →

30 minutes. Online or in Enschede. You decide.

Where does most of your time go?That is where we start.

Where does most of your time go?
That is where we start.