Start here · 3:29
Where CO-STAR comes from
This lesson explains what a prompt framework is, where CO-STAR came from, and why the detail you put in each slot matters more than the acronym itself.
- A prompt is the request you type into an AI tool such as ChatGPT, Claude or Gemini. A prompt framework is a reusable structure for that request, usually named with an acronym so it is easy to remember.
- The AI fills in whatever you leave out with generic guesses. A framework makes sure you include the parts that change the answer, such as who it is for, what you want to achieve and the format you need.
- Frameworks make prompts repeatable. You fill the same parts each time, save the prompt as a template and share it with colleagues.
- Frameworks are not magic words. The value comes from the detail you put in each part. They help most when a request is complex or open to interpretation, while a quick, simple question can stay short.
- There are well over sixty named frameworks, and most of them remix the same ingredients: role, task, context, audience, format, constraints and examples.
- CO-STAR was published by GovTech Singapore's Data Science and AI team in its Prompt Engineering Playbook in August 2023. Data scientist Sheila Teo made it famous when she won Singapore's first GPT-4 prompt engineering competition and wrote it up in December 2023. It is now the most cited acronym framework, and researchers still extend it. COSTAR-A, from 2025, adds an answer anchor.
| Term | What it means |
|---|---|
| Prompt | The request you type into an AI tool |
| Prompt framework | A reusable structure for that request, usually an acronym |
| CO-STAR | A fill-in-the-slots framework with six parts |
| GovTech Singapore | Published CO-STAR in August 2023 |
| Sheila Teo | Won Singapore's first GPT-4 prompt engineering competition |
| COSTAR-A | A 2025 extension that adds an answer anchor |
Do this in your own tools, step by step. Ticks are saved on this device.
What is a prompt framework?
A reusable structure or checklist for the request you type into an AI tool, usually named with an acronym.
Who published CO-STAR and when?
GovTech Singapore's Data Science and AI team, in its Prompt Engineering Playbook in August 2023.
What does COSTAR-A add to CO-STAR?
An answer anchor.
Paula Welcome to CO-STAR Prompt Framework: Write for Any Audience. This course is part of Complete AI Training; you'll find the full library at complete A I training dot com. It takes six short chapters.
Abby This part explains what a prompt framework is, where CO-STAR came from, and why it became the most cited acronym in prompt writing. It gives you the foundation for the rest of the course.
Paula A prompt is the request you type into an AI tool such as ChatGPT, Claude or Gemini. A prompt framework is a reusable structure for that request. Think of it as a short checklist of the parts a good prompt contains, usually named with an acronym so it is easy to remember.
Abby Why does a checklist help. The AI fills in whatever you leave out with generic guesses. A framework makes sure you include the parts that change the answer, such as who it is for, what you want to achieve and the format you need.
Paula Frameworks also make prompts repeatable. You fill the same parts each time, save the prompt as a template and share it with colleagues. They are not magic words. The value comes from the detail you put in each part.
Abby Frameworks help most when a request is complex or open to interpretation. A quick, simple question can stay short. There are well over sixty named frameworks, and most of them remix the same ingredients: role, task, context, audience, format, constraints and examples.
Paula This course focuses on one of them. CO-STAR is a fill-in-the-slots framework. It is an acronym where each letter stands for one part of your prompt. Context, Objective, Style, Tone, Audience, Response. Six slots, one prompt.
Abby Where did it come from. CO-STAR was published by GovTech Singapore's Data Science and AI team in its Prompt Engineering Playbook in August 2023. It was written for public servants who needed a clear way to brief an AI.
Paula It became famous through a data scientist named Sheila Teo. She won Singapore's first GPT-4 prompt engineering competition and wrote up how CO-STAR helped her in December 2023. Today it is the most cited acronym framework, and researchers still extend it. COSTAR-A, from 2025, adds an answer anchor.
Abby Here is CO-STAR in a real job. A communications officer needs a public service announcement about a road closure. Watch how each slot carries a different kind of detail.
Paula Now the same prompt as one message. Notice the six parts are still there, just written as sentences. The AI has everything it needs, so it does not have to guess who the announcement is for or how long it should be.
Abby One common mistake is treating CO-STAR as magic words. The acronym does nothing on its own. What changes the answer is the detail you put in each slot. A vague audience or a missing objective gives you a vague announcement. Fill the slots with real information from your job.
Paula So remember the foundation. CO-STAR is a reusable checklist from GovTech Singapore, made famous by Sheila Teo, and still extended by researchers today. The acronym reminds you what to include. Your detail is what makes the answer useful.
Abby Your turn. Take a request you would normally send to ChatGPT, Claude or Gemini in your own job. Rewrite it with the six CO-STAR slots, filling each one with real detail from your work.
Get the other 5 chapters, the exam and your certificate for LinkedIn, plus all 700+ AI courses.