Prompting
Prompt Engineering
The practice of crafting inputs to an AI model carefully to get better, more reliable outputs.
01 ——
In plain English
Prompt engineering is the skill of writing instructions, examples, and context for an AI model in a way that reliably produces the output you want. It's less about magic words and more about clear communication.
Techniques that work:
- Be specific — "Write a 3-bullet summary for a non-technical audience" beats "summarise this"
- Give examples — showing the model what a good output looks like (few-shot prompting)
- Set a role — "You are a senior tax accountant reviewing this contract..."
- Chain of thought — ask the model to "think step by step" before answering
- Constrain the output — specify format, length, tone, and what to avoid
Is it still relevant? Yes — even as models improve, well-structured prompts consistently outperform vague ones.
02 ——
Related terms
LLM
Large Language Model — the type of AI behind tools like ChatGPT and Claude, trained to understand and generate text.
Chain of Thought
A prompting technique where you ask the AI to "think step by step" before giving an answer — usually leading to better reasoning.
System Prompt
The high-level instructions given to an AI model at the start of a conversation that define its role, behaviour, and constraints.
Temperature
A setting that controls how random or creative an AI model's responses are — lower values produce focused answers, higher values produce more varied ones.
Few-shot Learning
A prompting technique where you include a handful of examples in the prompt so the AI learns the pattern you want it to follow.
Back to glossaryLast reviewed May 2026