Daniel & Friends / Glossary / Prompt engineering
AI and automationPrompt engineering
Prompt engineering is the design and testing of instructions for a model: choosing the role, context, examples and answer format so that the output is reliably usable. It is more an experimental craft than an exact science.
Daniel Votruba ·
In practice
Keep tested prompts in a shared library and version them. The team then does not start from zero every time.
Read more: The most popular AI tools of 2026, by category
Related terms
- Prompt: A prompt is the instruction a model receives.
- Context window: The context window is the amount of text a model can process at once, including the instruction and the answer.
- Large language model (LLM): A large language model is a model trained on a huge amount of text that predicts the next words and can write, summarise and answer.
- RAG (retrieval-augmented generation): RAG is a method in which a model first retrieves relevant documents, for example company knowledge, and answers from them.
More terms in the group AI and automation
Prompt injection · Predictive analytics · Reasoning model · Open-weight model · RPA (robotic process automation) · No-code and low-code · Semantic search · NLP (natural language processing) · Shadow AI · Neural network · Small language model (SLM) · Multimodal model · Speech-to-text · Multi-agent system · System prompt · Model evaluation (evals) · Temperature · Model bias (AI bias) · Text-to-image · MCP (Model Context Protocol) · Text-to-speech (TTS) · Machine learning (ML) · Text-to-video · Token
Terms in practice
Need help putting them to work?
Terms are one thing, putting them to work is another. We go through which of them pay off for you and say so plainly. You get a first opinion for free and we reply within 24 hours.
Book a call