Automation and AI

Prompt Engineering

Also called Prompting, prompt design

The craft of writing instructions, context and examples that get a usable answer out of an AI tool consistently.

Quick facts: Prompt Engineering

Category
Automation and AI
Also called
Prompting, prompt design
Level
Beginner
Affects
Draft quality, editing time, accuracy of AI output, consistency across a team
Where to see it
ChatGPT, Claude, Gemini, and the prompt fields inside marketing and automation tools
In this article4
  1. How prompt engineering works
  2. Why prompt engineering matters
  3. Common mistakes with prompt engineering
  4. How to act on it

How prompt engineering works

An AI tool answers from what is in front of it. If you give it a vague request it will fill the gaps with the most ordinary version of an answer, which is why generic prompts produce generic text. A prompt is engineered when it removes the guessing: it says who is speaking, who is being spoken to, what the answer is for, what must be included, and what would make the answer wrong.

Most working prompts contain the same ingredients:

  • Role and audience — who is writing, and who reads it.
  • Task — one clear job, not four bundled together.
  • Context — your own material: the brief, the transcript, the product details, the page it must match.
  • Constraints — length, tone, spelling convention, things it must never claim.
  • Example — a short sample of an answer you already consider good.

The example does more work than anything else. A model shown one piece of writing you approve of will imitate its shape far more reliably than it will follow an adjective like “professional”.

Why prompt engineering matters

It decides whether AI saves time or quietly costs it. A weak prompt returns something plausible that then needs rewriting, and the rewriting takes longer than the original task would have. A good prompt returns a draft that a person edits rather than rebuilds.

It also decides how much invention creeps in. Vague prompts invite a model to supply figures, sources and confident detail it has no basis for, which is a genuine business risk when the output ends up on a website or in a proposal. A prompt that says which facts may be used, and instructs the model to leave a marker where it lacks one, keeps the fabrication out where you can see the gap.

Common mistakes with prompt engineering

The biggest is asking for output without supplying material. If you have not given the tool your service details, your notes or your existing pages, everything it produces is an average of what it has seen elsewhere — which is why so much AI content reads identically to everyone else’s.

Second is stacking several jobs into one request: research, structure, write and check, all at once, so a weakness at any step contaminates the rest. Third is treating a good result as a lucky accident instead of saving the prompt. Fourth is polite vagueness — “make it engaging” — where a specific instruction such as “open with the question a customer actually asks” would have worked.

How to act on it

Keep the prompts that worked in a shared file, with a short note about what each was for, and improve them rather than rewriting from scratch. Split large jobs into steps and check each one before continuing. Always give the tool your own context, and state plainly what it must not assert — treating every unverified figure as something to flag rather than fill.

Then read the output as an editor, not a reviewer: check names, claims and numbers against a source you trust, because a fluent sentence is not evidence of a true one. If you want to build this into a working habit across a team, structured AI training is more effective than passing prompts around informally, and it is worth understanding why AI tools invent details before relying on any output.

Do and do not

Do

  • Give the tool your own material, not just instructions
  • Show one example of an answer you approve of
  • Save prompts that worked and reuse them

Do not

  • Bundle research, structure and writing into one request
  • Ask for vague qualities like engaging or professional
  • Publish output before checking every name and claim

Questions people ask about this

Do I need technical skills to write good prompts?

No. The skill is closer to briefing a new team member than to programming. If you can explain what the job is, who it is for, what good looks like and what would be unacceptable, you can write a strong prompt. People who write clear briefs for humans usually get good results from AI tools quickly.

Why does the same prompt give different answers each time?

These tools generate text with an element of variation built in, so repeated runs will differ in wording even when the instruction is identical. That is normal. You reduce the variation that matters by supplying your own source material, giving an example of an acceptable answer, and being specific about structure and constraints.

Can a good prompt stop an AI tool from making things up?

It reduces it substantially but never removes it. Giving the tool your own documents to work from, telling it to answer only from what you supplied, and asking it to mark anything it cannot verify all help. Even so, every claim, name and figure in the output needs checking against a source before it is published.

Related terms

Found this useful?

Share it, or ask an AI to summarise it

Back to the glossary

Knowing the term is the easy part

Applying it to your own site and budget is the work. Book a call and I will tell you what actually applies to you.