Master Generative AI with the CREATE Framework

Unlock better, faster, and more reliable results from any AI model by learning this simple, structured approach to prompt engineering.

In the world of generative AI, the quality of your output is directly tied to the quality of your input. This is the core principle behind prompt engineering, the process of designing and refining inputs to guide AI models. The CREATE AI Framework, developed by AI consultant Dave Birss, offers a systematic method for building detailed and effective prompts. It provides a simple way to remember the key components needed to give an AI clear instructions. A well-designed framework like CREATE transforms a vague idea into a precise, actionable instruction for large language models, reducing ambiguity and the risk of AI hallucinations.

The CREATE acronym stands for Character, Request, Examples, Adjustments, Type of Output, and Extras. By addressing each element, you provide the AI with a comprehensive brief that covers the task's what, who, how, and why. This structured approach is ideal for tasks requiring precision and customization, leading to more sophisticated and relevant outcomes.

Breaking Down the CREATE Framework

Each component of the CREATE framework plays a vital role in shaping the AI's response. By systematically working through each letter, you can build a prompt that is clear, contextual, and complete.

C: Character – Defining the AI’s Persona

The first step is to assign a role or prompt persona for the AI to adopt. This sets the tone, voice, and expertise level for the response, ensuring the output is tailored to a specific perspective. Thinking of the AI as an actor helps you define the character it should play.

Key Question Purpose Example
Who is the AI acting as? Sets the tone and expertise. "Act as an expert copywriter with 20 years of experience."

R: Request – Stating the Core Task

This is the core instruction or prompt task for the AI. Be as specific and clear as possible, providing enough context for the AI to understand the job. A vague request leads to a generic result, so ensuring prompt clarity is crucial for a targeted and useful output.

Key Question Purpose Example
What is the specific job? Defines the primary action. "Write a persuasive sales email for an electric sports car."

E: Examples – Providing a Clear Benchmark

Including examples, also known as few-shot prompting, helps clarify your expectations for style, tone, and format. You can provide reference images, text samples, or other materials to give the AI a concrete model of what you want.

Key Question Purpose Example
What should the output look like? Clarifies style and structure. "Here are three headlines I like. Emulate their punchy style."

A: Adjustments – Setting Constraints and Rules

Adjustments refine the output by setting boundaries and rules. Use prompt constraints to specify what to avoid, such as jargon or a certain tone. This is also where you can use techniques like negative prompting or instruct the AI to use Neutral Language for a more objective and factual analysis, which helps reduce bias.

Key Question Purpose Example
What are the boundaries? Refines content and style. "Keep the response under 150 words and avoid bullet points."

T: Type of Output – Specifying the Final Format

Clearly define the final prompt format you need. Whether it's a JSON object, a markdown table, a bulleted list, or a script, specifying the output type ensures the response is delivered in a usable structure, saving you time on reformatting.

Key Question Purpose Example
How should it be delivered? Dictates the response's structure. "Provide the output as a markdown table with three columns."

E: Extras – Adding Final Context

Extras are where you can add supplementary details or meta-instructions. This can include asking the AI to use a chain of thought process to explain its reasoning, requesting that it ask clarifying questions, or providing other details to ensure context is king. These final instructions help guide the AI's process for complex tasks.

Key Question Purpose Example
What other information is needed? Adds context and meta-instructions. "Think step-by-step before answering and explain your reasoning."

Ready to transform your AI into a genius, all for Free?

1

Create your prompt. Writing it in your voice and style.

2

Click the Prompt Rocket button.

3

Receive your Better Prompt in seconds.

4

Choose your favorite AI model and click to share.

Frequently Asked Questions

Who developed the CREATE AI Framework?
The CREATE AI Framework was developed by AI consultant and author Dave Birss. He designed it as a simple, memorable method for constructing detailed and effective prompts for generative AI.
Do I need to use all six parts of CREATE every time?
No, you don't have to use all six elements for every prompt. CREATE is a flexible framework, not a rigid rule. For simple tasks, a clear 'Request' and 'Type of Output' might be enough. For more complex or creative tasks, using all six components will give the AI the detailed context it needs to produce a high-quality, nuanced response.
What is the biggest benefit of using a framework like CREATE?
The primary benefit is consistency and clarity. A structured framework like CREATE reduces ambiguity, which is the main cause of generic or incorrect AI outputs. By systematically providing context, examples, and constraints, you get more predictable, relevant, and higher-quality results, saving you time on revisions.
Can I use the CREATE framework for AI image generation?
Yes, absolutely. The principles apply directly to image prompting.
  • Character: "Act as a National Geographic photographer" or "in the style of a vintage comic book artist."
  • Request: The subject of the image, like "a red panda sleeping on a branch."
  • Adjustments: Details like "cinematic lighting," "wide-angle shot," or negative prompts like "no text."
The framework helps you move beyond simple descriptions to art-direct the AI.
Is the order of the CREATE acronym important?
The acronym is a mnemonic to help you remember the key components, not a strict sequence you must follow when writing. However, starting with 'Character' (C) and 'Request' (R) is a good practice as it establishes the core foundation of the prompt who the AI should be and what it needs to do. The most important thing is to include the necessary details, regardless of the order.
What's a common mistake when using this framework?
A common mistake is being too vague within the structure. For example, in the 'Request' section, simply saying "write about marketing" is too broad. A better request would be "Write a 500-word blog post for beginners on the top 3 benefits of email marketing." The framework provides the sections, but you still need to fill them with specific, clear details.
How does CREATE compare to other prompt frameworks?
Many prompt frameworks exist, such as CO-STAR, RACE, and RTF, each with its own strengths. CREATE is highly regarded for being intuitive, comprehensive, and easy to remember. Its inclusion of 'Character' at the start and 'Extras' at the end provides a robust structure for both simple and highly complex tasks, making it a versatile choice for most users.
What's the difference between 'Adjustments' and 'Extras'?
'Adjustments' are constraints on the final output itself. They define what to do or what to avoid in the content ("keep it under 200 words," "avoid technical jargon," "use a formal tone"). 'Extras' are meta-instructions about the AI's process. They guide how the AI should "think" to get to the answer ("think step-by-step," "ask me clarifying questions if my request is ambiguous," "explain your reasoning").
Why is the 'Character' (persona) element so important?
Assigning a 'Character' or persona is one of the most powerful ways to influence the AI's output. It instantly sets the tone, expertise, style, and vocabulary. Telling the AI to "act as a seasoned legal expert" versus "act as a friendly blogger" for the same topic will produce dramatically different and more tailored results, aligning the response with your specific needs.
How can I practice and get better at using CREATE?
Start with a simple, familiar task, like rewriting an email or summarizing a short article. Consciously apply each of the six CREATE elements to your prompt. Observe how each element changes the AI's response. Using a tool like the Betterprompt Prompt Rocket can also help you see how a basic prompt can be transformed into a well-structured CREATE prompt, accelerating your learning.