Glossary · 3 · Working with models: prompts and context
Prompt
Also known as: Instruction, User prompt
A prompt is the input given to a generative AI model — an instruction, a question, examples, reference material or a combination — that the model uses as the starting point for its output.
- Beginner
- Technical writers
- Technical marketers
- Technical project managers
In one sentence
What a prompt is: the instruction, context and examples you give a generative AI model — the first skill on the AI learning path.
Example
“You are editing a user manual for field technicians. Rewrite the following paragraph as numbered steps, keep all warnings and use imperative mood: …”
Why it matters on your learning path
- Technical writers: A good prompt reads like a good writing brief: audience, purpose, format, constraints and source.
- Technical marketers: Prompts encode brand voice. Shared, tested prompts keep a team’s AI output consistent — see prompt library.
- Technical project managers: Prompts are project assets: version them, review them and test changes like any other requirement.
The anatomy of a prompt
- Role and audience — who the model writes as and for whom
- Task — one clear instruction
- Context — source text, facts, terminology
- Format — length, structure, output type
- Constraints — what to avoid, what to do when information is missing