Prompt Engineering Basics
The essential principles behind writing prompts that get great AI responses — every time.
A prompt is the instruction you give an AI. Prompt engineering is the skill of making that instruction as clear and effective as possible.
The five elements of a strong prompt
Role
Tell the AI who to be. "Act as a biology tutor…" gives the response a consistent voice and expertise level.
Task
State exactly what you want done. "Explain… / Summarise… / List… / Compare…" — a clear verb is your best friend.
Context
Provide relevant background. Who is the audience? What's the situation? The more the AI knows, the better it can help.
Format
Specify how the answer should look. "…in 3 bullet points", "…as a table", "…in under 100 words".
Constraints
Add limits and guardrails. "…avoid technical jargon", "…for a 12-year-old", "…cite sources".
Before → After examples
Tell me about climate change.
Act as a science teacher. Explain the top 3 causes of climate change to a 14-year-old student in simple language, using one real-world example for each. Keep it under 200 words.
Write an email.
Write a professional but friendly email to a client explaining that their project will be delayed by 2 weeks due to supplier issues. Keep the tone apologetic, offer a revised timeline, and end with a next step. Max 150 words.
Common mistakes
- Too vague — "Tell me about AI" gives the model no direction.
- No audience — Without specifying who it's for, the level and tone will be unpredictable.
- No format — "Explain it" could produce a paragraph, a list, or an essay.
- Too long — Burying the key request in 10 sentences of context confuses the model.
- Asking for everything at once — Break complex tasks into smaller prompts.