> For the complete documentation index, see [llms.txt](https://docs.getyolo.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.getyolo.ai/en/kezdetek/what-are-prompts.md).

# What Are Prompts?

## **What Is a Prompt, and How Do You Create Good Prompts for AI?**

A prompt is the question or instruction you give to the AI to receive a response on a specific topic. A well-crafted prompt allows the AI to provide accurate and relevant answers—especially when working from books or photographed documents.

### How to Create Good Prompts:

1. <mark style="color:purple;">**Be clear and specific:**</mark>&#x20;

Be clear about what you want to know or what task you expect the AI to perform.

* Example: "Create a short quiz with 5 questions based on Chapter 3 of the book ‘Foundations of Hungarian History’, focusing on the topic of the 1848 Revolution."

2. <mark style="color:purple;">**Refer to a specific book or document:**</mark>

If you're asking based on an uploaded or photographed textbook, clearly indicate which topic or section your question refers to.

* Example: "Based on the photographed essay, correct the spelling mistakes and suggest improved sentence structures!"
* Example: "Help me solve the math homework problem based on Chapter 4 of the uploaded textbook!"

3. <mark style="color:purple;">**Ask the AI to create exercises:**</mark>

The AI can generate tasks or tests based on any uploaded material.

* Example: "Write a short essay question about photosynthesis based on the uploaded biology textbook."
* Example: "Create a 10-question quiz based on the chapter about Europe’s climate in the attached geography document."

4. &#x20;<mark style="color:purple;">**Ask your questions simply and clearly:**</mark>

When asking for help with a math homework problem, make sure your question is easy to understand.

* Example: "Explain and solve the quadratic equation shown in the image."
* Example: "Help me calculate the area of the triangle in the homework using the data shown in the attached image."

5. <mark style="color:purple;">**Use Example Questions:**</mark>

If you're not sure exactly what or how to ask, you can also use the example questions suggested by the AI. This will help guide you and ensure you get the best possible results.

### Examples of Common Use Cases:

* Essay correction: "Based on my photographed essay, correct any spelling mistakes and make the text more fluent!"
* Quiz creation: "Create a 5-question quiz on the Industrial Revolution using the uploaded history textbook!"
* Solving Math Homework: *"*&#x45;xplain Example 5 from Chapter 2 of the uploaded textbook step by step!"

{% hint style="info" %}
The clearer and more precise your question is, the better answers you'll receive. Make sure that uploaded documents are readable and well-structured—this helps the AI process the content more effectively and provide accurate responses!
{% endhint %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.getyolo.ai/en/kezdetek/what-are-prompts.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.