Parts of a Prompt: Understanding the Key Elements

Introduction

In the rapidly evolving field of Generative AI, crafting effective prompts is essential to achieving high-quality outputs. A prompt is the input provided to an AI model, and its structure determines the accuracy, relevance, and format of the response. Whether you're using AI to write content, generate data, or create images, understanding the parts of a prompt can help you guide the model toward producing better results.

In the previous docs, we discussed instruction prompting, role prompting, and shot-based prompting. In this document, we conclude this discussion by summarizing the main parts of the prompt.

We break down the essential parts of a prompt, providing examples and tips on how to use each element effectively:

1. Introduction
2. Key Parts of a Prompt
   • The Directive
   • Examples
   • Role (Persona)
   • Output Formatting
   • Additional Information
3. How to Order Parts of the Prompt
4. Conclusion
5. FAQ

Key Parts of a Prompt

Prompts are made up of several key components that work together to guide the AI. While not every prompt will contain all these elements, understanding how each part functions can help you create more targeted and effective inputs.

The key parts of a prompt are:

• The Directive
• Examples
• Role (Persona)
• Output Formatting
• Additional Information

1. The Directive

The Directive is the main instruction in the prompt. It tells the AI exactly what task it should perform. Without a clear directive, the AI may provide a generic or irrelevant response.

What is a Directive?

A directive is a concise instruction or question that gives the AI a clear task to perform. It can range from a request to generate text, solve a problem, or format information in a specific way.

For example, here a prompt with a single instruction:

Implicit Directives

In some cases, the directive may be implied rather than explicitly stated. These types of prompts still guide the AI but rely on context or formatting to convey the task.

Best Practices for Directives:

• Be clear and concise.
• Avoid ambiguous or vague instructions.
• When possible, use action verbs to indicate the specific task (e.g., “write,” “list,” “translate”).

2. Examples

When the task is more complex, providing Examples can help guide the AI in producing more accurate responses. This technique is especially useful in few-shot and one-shot prompting, where a model is given one or more examples of what you expect in the output.

Why Use Examples?

Examples demonstrate the expected format, style, or structure of the output. By including them in the prompt, you can guide the AI’s behavior and help it better understand the desired result.

In this example, the AI is shown how to structure the translation, and it will follow the same pattern for the remaining sentences.

Best Practices for Examples:

• Provide clear and relevant examples that match the task.
• Use examples to demonstrate the structure or content you expect.
• Adjust the number of examples based on task complexity (one-shot or few-shot).

3. Role (Persona)

Assigning a Role to the AI, also known as a persona, helps frame the response in a specific way. By telling the AI to act as an expert, a professional, or a specific character, you can guide the tone, style, and content of the response.

What is a Role?

The role element in a prompt assigns a specific persona or perspective to the AI, encouraging it to tailor its response according to the designated role. This can greatly enhance the accuracy and relevance of the response, especially for tasks requiring domain-specific knowledge or a particular tone.

Here, the AI is instructed to respond as if it were a medical professional:

The AI will assume the role of a customer service agent, ensuring the tone is appropriate for business communication:

Best Practices for Using Roles:

• Use roles to add expertise or a specific perspective to the response.
• Ensure the role fits the task at hand (e.g., using a marketing expert to write promotional content).
• Combine the role with additional context for better results.

4. Output Formatting

Sometimes, it’s important to specify the format in which you want the AI to present its output. Output Formatting ensures that the response follows a particular structure—whether it’s a list, a table, or a paragraph. Specifying the format can help prevent misunderstandings and reduce the need for additional post-processing.

Why Output Formatting Matters

Without clear formatting instructions, the AI may provide a response that is technically correct but not in the desired format. Specifying the structure makes the output easier to use.

It is often desirable for the GenAI to output information in certain formats, for example, CSVs or markdown formats. To facilitate this, you can simply add instructions to do so as seen below:

Style Instructions

You can also specify stylistic preferences, such as tone or length, within the output formatting. This allows you to control not just the content but how it’s presented.

For example:

5. Additional Information

Additional Information, sometimes referred to as context, though we discourage the use of this term as it is overloaded with other meanings in the prompting space[^b]. It provides the background details the AI needs to generate a relevant response. Including this information ensures that the AI has a comprehensive understanding of the task and the necessary data to complete it.

What is Additional Information?

Additional information can include relevant facts, data, or other background information that helps the AI generate a more accurate and contextually appropriate response. This element is especially important for complex tasks that require specific knowledge.

In this example, the patient’s medical history is crucial to generating a valid prediction.

Best Practices for Additional Information:

• Include only relevant information—avoid overloading the prompt with unnecessary details.
• Ensure the information is clearly linked to the task.
• Use this element to provide essential background that the AI might not otherwise have.

How to Order Parts of the Prompt

There is no single “correct” order for arranging the elements of a prompt, but there are guidelines that can help improve clarity and prevent misunderstandings. In general, starting with examples or context and ending with the directive ensures the AI focuses on the task after processing the relevant information.

Now that you understand the different parts of a prompt, you may wonder if there is a common order in which you should arrange them. You should first note that not all of these occur in every prompt, and when they do there is no standard order for them. However, we do have a suggested order. To understand our order, first consider the following two prompts, which each contain a role, an instruction (the directive), and additional information.

Although usually both prompts would give approximately the same output, we prefer the second prompt, since the instruction is the last part of the prompt. This is preferable, since with the first prompt, the large language model (LLM) might just start writing more context instead of following the instruction; if given the first prompt, the LLM might add a new line:

March 15, 2022: Follow-up appointment scheduled with neurologist to assess concussion recovery progress.

This is due to the fact that LLMs are trained to predict the next token (similar to word) in a paragraph.

Recommended Order for Prompts:

1. Examples (if needed)
2. Additional Information
3. Role
4. Directive
5. Output Formatting

In this prompt, the role and task come after the context, ensuring the AI processes the timeline before generating the output.

Why Order Matters

The order of the elements affects how the AI processes the information. For instance, placing the directive last helps avoid the AI continuing the additional information instead of focusing on the task at hand.

Conclusion

Crafting effective prompts requires an understanding of the key elements that guide AI responses. By mastering the use of Directives, Examples, Roles, Output Formatting, and Additional Information, you can improve the accuracy and relevance of the outputs generated by AI models. Experimenting with different combinations of these elements will allow you to tailor prompts for a wide range of tasks and achieve better results.

FAQ

Why is it important to formalize the language we use to discuss prompting?

Formalizing prompt language can help you, as a developer, to both create more effective prompts with the key components and better engage in prompt engineering discourse.

What are the key parts of a prompt?

Some key parts of a prompt discussed in this article are The Directive, Examples, A Role, Output Formatting, and Additional Information

How do you order the parts of a prompt?

You should put the examples first, then additional information, then the role, directive, and output formatting.

How does output formatting improve AI responses?

Output formatting ensures that the AI delivers the response in the desired structure, whether it’s a table, list, or paragraph, reducing the need for post-processing.

Can prompts work without examples?

Yes, many prompts don’t need examples, especially for simpler tasks. However, including examples can guide the AI more effectively for complex requests.

Valeriia Kuka

Valeriia Kuka, Head of Content at Learn Prompting, is passionate about making AI and ML accessible. Valeriia previously grew a 60K+ follower AI-focused social media account, earning reposts from Stanford NLP, Amazon Research, Hugging Face, and AI researchers. She has also worked with AI/ML newsletters and global communities with 100K+ members and authored clear and concise explainers and historical articles.

Footnotes

1. Schulhoff, S., Ilie, M., Balepur, N., Kahadze, K., Liu, A., Si, C., Li, Y., Gupta, A., Han, H., Schulhoff, S., & others. (2024). The Prompt Report: A Systematic Survey of Prompting Techniques. arXiv Preprint arXiv:2406.06608. ↩

2. Searle, J. R. (1969). Speech acts: An essay in the philosophy of language. Cambridge University. ↩

3. Xia, C., Xing, C., Du, J., Yang, X., Feng, Y., Xu, R., Yin, W., & Xiong, C. (2024). FOFO: A Benchmark to Evaluate LLMs’ Format-Following Capability. In L.-W. Ku, A. Martins, & V. Srikumar (Eds.), Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 680–699). Association for Computational Linguistics. https://doi.org/10.18653/v1/2024.acl-long.40 ↩