Last updated on

ChatGPT Prompt Template: Framework, Examples, and Copyable Prompts

Two years ago I went deep on a research project where I tested seven generative AI tools to see whether they could replace human writers, especially for technical long-form content.

They failed. Hard.

But the technology moved quickly, and many of the limitations I hit back then have become smaller, or disappeared entirely.

Since then, I’ve spent a lot of time, both privately and at work, figuring out how to get consistently useful output from ChatGPT and similar tools.

The main lesson: good prompting isn’t magic. It’s structure. If you’ve been looking for a ChatGPT prompt template, a prompt framework, or practical examples you can reuse, start with the five-part format below.

Quick answer: what is a good ChatGPT prompt?

A good ChatGPT prompt gives the model the same briefing context you would give a capable colleague: role, task, constraints, example, and output format. My five-part prompt template is Situation, Precision, Guidance, Example, and Output. It works because it removes ambiguity before the model starts writing.

If your prompt feels weak, one of those five pieces is usually missing. I still skip one when I am in a hurry. Then I get a vague answer and have to do the little walk of shame back to the prompt.

Copyable ChatGPT prompt template

Use this as a starting point when you want a clear, reusable ChatGPT prompt. I would rather start with a slightly structured prompt than spend five minutes arguing with a vague answer afterwards.

You are [role] helping me with [context].

Your task is to [specific outcome].

Use [tone/style/criteria]. Avoid [things to avoid]. Keep in mind [constraints].

Use this example or reference as guidance: [example/input].

Return the answer as [format, structure, length].

Here is the short version:

Act as [role]. Help me [task]. Use [constraints]. Follow [example]. Return [format].

The longer version is usually better for work that needs accuracy, tone, or a specific structure. The short version is fine when the task is simple and the stakes are low.

What is a ChatGPT prompt?

A ChatGPT prompt is the instruction, question, or brief you give the model. A weak prompt only names the task. A stronger prompt explains the role, context, constraints, examples, and output format.

That distinction matters because ChatGPT does not know what you forgot to say. If you want useful output, you need to give it the parts of the brief that would normally live in your head, a Slack thread, or a half-remembered meeting.

The practical move is simple: stop treating the prompt as a sentence and start treating it as a tiny brief.

The 5-part ChatGPT prompt framework

After a lot of trial and error, I landed on a simple ChatGPT prompt framework that helps you get clearer, more accurate output without turning every prompt into a novel.

The framework has five components:

  • Situation: Define the role of the AI
  • Precision: Specify the task clearly
  • Guidance: Set tone and constraints
  • Example: Provide a reference or pattern to follow
  • Output: Define the format you want back

It works because it forces you to provide the same context you’d include when briefing a human.

Compare:

“Write a Facebook ad for my webshop.”

vs.

“You are a direct-response copywriter. Draft two Facebook ad variations for Danish parents buying children’s clothing. Start with a hook, use curiosity and urgency carefully, and output as two versions with headline + primary text.”

One gives you generic output. The other gives you something usable.

If you want the framework as a checklist, use this:

  1. Situation: “You are [role] helping me with [context].”
  2. Precision: “Your task is to [specific outcome].”
  3. Guidance: “Use [tone], avoid [things], keep in mind [constraints].”
  4. Example: “Model it after [sample/input] where relevant.”
  5. Output: “Return it as [format, length, structure].”

I still catch myself skipping one of these when I’m in a hurry. Every time I do, output quality drops.

ChatGPT prompt examples

Here are a few copyable prompt examples using the same framework. Treat them as starting points, not sacred scripts. You should change the role, constraints, and output format every time the task changes.

Simple writing prompt

You are an editor helping me improve a draft.

Your task is to make the text clearer without changing the meaning.

Use plain language, keep my voice, and avoid making the text sound corporate.

Return three things:
1. a cleaner version
2. the biggest clarity problems you fixed
3. any sentence that still needs a human decision

Marketing copy prompt

Situation
You are a marketing copywriter for my webshop selling children’s clothing.

Precision
Draft an email newsletter that informs readers about a specific product/topic and gets them to click to read the full story.

Guidance
Open with a strong hook. Use psychological triggers like curiosity and fear of missing out—without being spammy.

Example
Here is a previous email that performed well. Follow the tone and structure.

Output
Write two variations:

  • one tailored to a Danish audience, primarily aimed at mothers
  • one aimed more broadly at fathers who could be in-market

This is one of the easiest ways to create useful prompts for ChatGPT without overcomplicating your workflow.

SEO prompt example

You are an SEO editor helping me improve an existing blog post.

Your task is to identify title, meta description, heading, intro, and internal linking improvements for the article below.

Prioritize search intent match, clarity, and useful reader outcomes. Do not keyword-stuff. Preserve the writer's voice.

Use the Search Console query data and article draft as input.

Return a prioritized list of changes with the reason for each change.

CRO prompt example

You are a CRO specialist reviewing a low-traffic landing page.

Your task is to find the clearest friction points and recommend changes that do not require an A/B test to justify.

Focus on message match, CTA clarity, proof placement, form friction, and above-the-fold comprehension.

Use the page copy and campaign source as input.

Return a table with issue, why it matters, recommended change, and confidence level.

Content workflow prompt example

You are a content operations assistant helping me turn a rough idea into a reusable workflow.

Your task is to break the work into repeatable stages, identify which steps need human review, and define the output format for each step.

Use practical marketing operations language. Avoid generic AI productivity advice.

Return the workflow as stages with inputs, actions, QA checks, and outputs.

ChatGPT prompt templates by use case

If you want a faster way to adapt the framework, start from the template closest to your task. I use this approach when I do not want to rebuild the whole prompt from scratch, but I still need the output to fit the work in front of me.

Research prompt template

Use this when you need a clear first pass on a topic, especially when you already have notes or source material.

You are a research assistant helping me understand [topic].

Your task is to summarize the most important points, separate facts from assumptions, and flag what needs verification.

Prioritize practical implications over trivia. If something is uncertain, say so clearly.

Use this context: [notes, source text, or question].

Return a concise summary, key findings, open questions, and recommended next steps.

Strategy prompt template

Use this when you are comparing options and need a recommendation, not just a list of pros and cons.

You are a strategy sparring partner for [company/project].

Your task is to evaluate [decision, plan, or idea] and identify the strongest option.

Use practical business judgment. Consider audience, constraints, risk, effort, and upside.

Use this context: [current situation, goals, constraints, data].

Return your recommendation, reasoning, tradeoffs, and the first three actions to take.

Editing prompt template

Use this when the draft already has the right ideas, but the writing needs to become sharper.

You are an editor helping me improve this draft.

Your task is to make the writing clearer, tighter, and more useful without changing the meaning.

Keep my voice. Remove vague phrasing, repetition, and unnecessary complexity.

Use this draft: [paste draft].

Return the revised version and a short list of the most important changes.

Data analysis prompt template

Use this when you have an export, table, or report and want the model to find the useful signal before you decide what to do.

You are a data analyst helping me find useful patterns in this export.

Your task is to identify the biggest changes, strongest opportunities, and likely causes.

Focus on business impact, not vanity metrics. Call out data limitations before making recommendations.

Use this data: [paste table or upload file].

Return a ranked list of findings with supporting numbers and recommended actions.

The point isn’t just “better prompts.” It’s better thinking.

These tools are getting better—but they still don’t replace judgment.

The win is combining AI speed with human intent and quality control:

  • use AI to accelerate drafts and exploration
  • use humans to decide what matters, what’s true, and what’s good

With a clear framework, prompting becomes repeatable—and you stop gambling on random outputs.

When a prompt should become a workflow

A prompt is enough when the task is small, low-risk, and one-off.

But when you repeat the same task every week, the better question is not “what is the best prompt?” It is “what workflow should this prompt belong to?”

That usually means defining:

  • the input format
  • the review step
  • the quality bar
  • the output format
  • the next action after the model responds

That is why I keep prompts and workflows connected. The prompt framework helps you write a better single request. The workflow layer helps you turn repeated requests into a system. I wrote more about that in AI Marketing Workflows: From Prompts to Reusable Skills.

Quick FAQ

What is the 5-part ChatGPT prompt framework?

The five parts are Situation, Precision, Guidance, Example, and Output. Together they define who the model should act as, what it should do, what constraints matter, what pattern to follow, and how the answer should be returned.

How do I write a ChatGPT prompt?

Use a clear structure: define role, task, constraints, example, and output format. If your result is weak, it is usually because one of those five parts is missing.

What is a good prompt for ChatGPT?

A good prompt is specific enough that someone else could execute it the same way. In practice, that means clear context, clear objective, and a defined output format.

How long should a ChatGPT prompt be?

Long enough to remove ambiguity, short enough to stay focused. Most strong prompts are a compact brief, not a one-liner and not a full strategy deck.

Why do ChatGPT prompts fail?

Most prompts fail because they hide the real context. The model gets a task, but not the audience, constraints, examples, success criteria, or output format. Add those pieces and the result usually improves fast.

More writing connected to this topic, based on shared tags.