6 Formulas and Prompt Structures for ChatGPT: Going Beyond the Basics

In 2025, interacting with artificial intelligence tools like OpenAI’s ChatGPT, xAI’s Grok, or Google’s Gemini has become essential for countless tasks—from agile content creation to the efficient automation of complex processes. However, obtaining accurate, relevant, and truly useful results isn’t always straightforward. That’s where the importance of prompt engineering comes in: a set of advanced techniques that transforms ordinary interactions into powerful and productive dialogues with today’s top AI tools.

In this guide, you’ll discover 19 tested and proven prompt formulas and structures, specifically designed to enhance the quality and accuracy of your interactions with various models. Whether you’re a content creator, marketing professional, educator, or someone looking for clearer insights and creative solutions, these frameworks will help you unlock the full potential of today’s AI tools—from OpenAI and Google to Anthropic and Microsoft.

Learn how to create the perfect prompt formula for ChatGPT, Claude, Perplexity, or any other LLM. Discover practical prompt examples and master the art of structuring prompts.

Ready to unlock the power of AI? Dive into detailed examples and adaptable strategies to meet your needs, complemented by our new guide on prompt techniques, frameworks, and formulas. Whether for content creation or insights generation, these structures will transform your AI experience.

Examples of Formulas and Prompt Structures

1. RTF: Role, Task, Format

The RTF structure is a simple yet effective approach to crafting prompts that clearly direct interactions with AI models like ChatGPT, as well as others like Anthropic’s Claude or Google’s Gemini. This method helps define the role the AI should take on (Role), the specific task or problem to be addressed (Task), and the expected format of the response (Format).

Using the RTF structure helps you get more targeted and accurate responses, making it especially useful in practical applications like content creation or quick analysis.

Let’s quickly break down the components:

Role: Defines who is performing the action in the prompt. This could be a person, an entity, or the AI assuming a specific role.
Task: Clearly states what needs to be done. It should directly describe the desired action or required information.
Format: Specifies how you want the response to be structured. These could include a list, explanatory text, a table, or other practical ChatGPT output formats depending on your communication goal.

Practical example using the RTF structure:
As a nutrition expert (Role), provide a list of five protein-rich foods (Task) in a numbered list format (Format).

This example clearly shows how to apply the RTF structure to generate organized and specific answers. By defining a role (nutrition expert), stating a concrete task (list protein-rich foods), and setting the desired format (numbered list), you significantly improve the quality of AI-generated responses.

2. CTF: Context, Task, Format

The CTF structure is a powerful prompt engineering tool that enables you to clearly define the scenario in which the AI interaction is taking place (Context), specify the exact action expected (Task), and indicate the format you want for the response (Format). This method greatly optimizes the quality of responses across AI tools—not only ChatGPT but also Claude from Anthropic and Gemini from Google.

By clearly defining these three elements, you’ll receive more useful and targeted responses. This is especially effective for practical scenarios such as content generation, specific analyses, or structured problem-solving.

Let’s break down the components of the CTF structure:

Context: Provides essential information to clearly situate the scenario or problem. Context helps the AI understand the specific setting of your prompt.
Task: Directly and precisely describes what you expect the AI to do. It should clearly detail the objective or desired action.
Format: Defines how you want to receive the response—this could be a list, structured paragraph, table, or any other useful format.

Suppose you’re asking ChatGPT to compile a list of practical energy-saving tips for households. Using the CTF prompt structure, your prompt would be:

Context: “With rising energy prices and growing concern for environmental sustainability, many people are looking for ways to reduce their household energy consumption.”
Task: “Create a list of practical and easy-to-implement tips that homeowners can use to save energy.”
Format: “Present the tips in a numbered list, providing a brief explanation for each.”

Practical CTF example:
Considering the increase in energy tariffs and concern for sustainability, create a numbered list of practical energy-saving tips for homes. The tips should be easy to implement and accompanied by a brief explanatory description.

This example clearly demonstrates how to use the CTF structure to guide detailed and specific AI responses. By providing a clear context, defining the desired task, and specifying the response format, you can significantly enhance the quality of AI-generated outputs.

3. PECRA: Purpose, Expectation, Context, Request, Action

The PECRA structure is a versatile prompt engineering tool that emphasizes clarity and specificity when interacting with language models like ChatGPT, Grok, and DeepSeek. Let’s break down each component:

Purpose: States the reason why the prompt is being created. It clarifies the general intention of the interaction.
Expectation: Describes the type of response or result expected from the model.
Context: Provides the additional information needed for the model to fully understand the prompt and generate an appropriate response.
Request: Clearly specifies what is being asked of the model.
Action: Indicates the specific action the model is expected to perform.

Let’s imagine you want ChatGPT to create a study plan for a student preparing for an important math exam. Here’s how to apply the PECRA structure:

Purpose: “The purpose of this prompt is to help a student effectively prepare for a math exam.”
Expectation: “I expect to receive a detailed study plan that covers the main topics needed for the exam.”
Context: “The student has 2 weeks until the exam, can study about 3 hours a day, and struggles mainly with algebra and geometry.”
Request: “Based on this information, please create a study plan.”
Action: “Structure the plan starting with algebra fundamentals, followed by geometry, and include regular review sessions.”

Practical PECRA example:
Considering a student who is preparing for an important math exam in 2 weeks and can dedicate 3 hours daily to studying, with difficulties in algebra and geometry, create a detailed study plan. The plan should start with the fundamentals of algebra, progress to geometry, and include regular reviews, aiming for effective preparation for the exam.

This example shows how the PECRA structure can be used to craft a clear and detailed prompt, guiding ChatGPT to deliver a response that meets the user’s specific expectations.

4. CREATE: Character, Request, Examples, Adjustments, Type, Extras

The CREATE structure is a comprehensive method for prompt formulation, aimed at creating efficient and well-directed interactions with AI models like ChatGPT. This detailed approach allows users to clearly specify the context and expectations of the interaction. Let’s look at each component:

Characterization: Assigns a specific role or persona to ChatGPT, guiding its responses based on a defined profile or function. This helps shape the nature of the answers according to the desired context.
Request: Clearly and objectively defines what is expected of the model, detailing the task at hand.
Examples: Provides examples of the expected output, giving the model a clear reference for the type of content or response desired.
Adjustment: Allows the user to request refinements or specific modifications to previous responses, helping to better meet task needs.
Type of Output: Specifies the expected format of the answer—such as a narrative, list, detailed plan, and so on. This guides how the AI structures the information.
Extras: Offers the opportunity to add additional or contextual information, enriching the prompt and enabling more precise and aligned responses.

Imagine you want Gemini to create a personalized travel guide for a city you plan to visit. Here’s how to apply the CREATE structure:

Characterization: “Acting as an experienced local travel guide,”
Request: “create a personalized travel guide.”
Examples: “Include sections like accommodations, food, tourist attractions, and transport tips.”
Adjustment: “Prioritize budget-friendly and family-appropriate options.”
Type: “Organize the guide into clearly defined sections with recommendations and brief descriptions.”
Extras: “I’ll be traveling in July, so include relevant seasonal events and activities.”

Practical CREATE example:
Acting as an experienced local travel guide, create a personalized guide for my trip to Barcelona in July. Include accommodations, gastronomy, tourist attractions, and transportation tips, prioritizing options that are budget-friendly and suitable for families. Organize the guide into clearly defined sections, with recommendations and brief descriptions for each item, and don’t forget to add relevant seasonal events and activities for the period of my visit.

This example demonstrates how to use the CREATE structure to craft a detailed and specific prompt, guiding Gemini to produce a response that aligns with the user’s expectations and needs.

5. CREO: Context, Request, Explanation, Outcome

The CREO structure is a methodology designed to optimize prompt formulation for more effective interactions with language models like Grok, Perplexity, and ChatGPT. It emphasizes the importance of providing context, making a clear request, explaining the task in detail, and defining the desired outcome.

Context: Provides background information needed for the model to understand the situation or topic.
Request: Clearly states what is expected from the model.
Explanation: Describes the task in detail to help the model fully understand the goal of the request.
Outcome: Specifies the type of answer or result the user expects to receive from the model.

Let’s imagine you want ChatGPT to generate a list of suggestions for boosting personal productivity. Here’s how to apply the CREO structure:

Context: “Given that many people work from home and face frequent distractions,”
Request: “create a list of suggestions.”
Explanation: “These suggestions should be practical and easy to implement for those working from home.”
Outcome: “I expect a list that includes time management techniques, workspace setup advice, and well-being tips.”

Practical CREO example:
Considering many people work from home and face frequent distractions, create a list of practical and easy-to-implement suggestions to increase personal productivity. These suggestions should cover time management techniques, workspace setup, and wellness tips, aiming to improve focus and efficiency in the home environment.

This example illustrates how the CREO structure can be used to create clear and objective prompts, guiding ChatGPT to produce responses that effectively meet the user’s specific needs.

6. PAIN: Problem, Action, Information, Next Steps

The PAIN prompt structure is a prompt engineering methodology focused on identifying and solving specific problems using AI. It guides the formulation of requests in a way that elicits precise and applicable solutions.

Problem: Identifies the issue that needs to be resolved, clarifying the user’s challenge or need.
Action: Specifies the action or type of assistance expected from ChatGPT, directing it toward problem-solving.
Information: Requests detailed insights or clarifications that ChatGPT can provide to better understand the context or nuances of the problem.
Next Steps: Asks for an action plan, resources, or subsequent steps the user can follow to resolve the issue or achieve the desired goal.

Let’s say you’re struggling to manage your time effectively and want ChatGPT to help create a personalized time management plan. Here’s how to apply the PAIN structure:

Problem: “I’m struggling to manage my time effectively,”
Action: “I need a personalized time management plan.”
Information: “What strategies or tools would you recommend?”
Next Steps: “Provide a step-by-step plan I can start following immediately.”

Practical PAIN example:
I’m struggling to manage my time effectively and need a personalized time management plan. What strategies or tools would you recommend? Please provide a step-by-step plan that I can start following immediately, considering my day is often interrupted by unexpected tasks.

This example shows how the PAIN structure can be used to craft a targeted and effective prompt, guiding ChatGPT to offer practical and personalized solutions for specific user challenges.

Temukan berbagai E-Book terbaru dan terlaris yang siap membantu Anda meningkatkan kemampuan di berbagai bidang.
Yuk, kunjungi www.platihan.id sekarang juga dan dapatkan E-Book pilihanmu sebelum kehabisan!

Belajar jadi mudah dan praktis!
Temukan eBook berkualitas di www.platihan.id dan upgrade kemampuanmu!

DAPATKAN SEKARANG JUGA!