> For the complete documentation index, see [llms.txt](https://docs.entrypointai.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.entrypointai.com/guides/evaluate-a-prompt/prepare-validation-examples.md).

# Prepare Validation Examples

Now we have a [template](/key-concepts/templates.md) for our prompt, but we need data to use in it.

Navigate to the Examples page and press +.

<figure><img src="/files/tqCOkUNIkIV9kU6bF9sk" alt=""><figcaption></figcaption></figure>

For the dataset, choose *Validation*.

Then, enter the Content Description and Email Subject from the first row in the table below.

| Content Description                                                                                                         | Email Subject                                                           |
| --------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------- |
| The email promotes a buy one get one free offer on socks.                                                                   | Double the Comfort: Buy One, Get One Free on All Socks 🧦🧦             |
| The email discusses the importance of nutrition and weight training to improve health and body composition.                 | Transform Your Health: Unlock the Power of Nutrition & Weight Training! |
| The email asks the user if they will complete a short survey in order to provide feedback to the business on their service. | Your Opinion Matters: Take Our Quick Survey & Help Us Improve           |

It should look like this:

<figure><img src="/files/B636l07jhqk6NZwhrlMA" alt=""><figcaption><p>Creating a validation example</p></figcaption></figure>

Press "Save & next." Repeat with the next row until all three examples from the table have been entered.

Close the example editing screen and you should see our three new examples, each with an orange line at the bottom to indicate they are validation examples:

<figure><img src="/files/fhpJ1Ee20cNijay8ApFs" alt=""><figcaption></figcaption></figure>

Three examples isn't very many, but it's enough to try evaluating our prompt. It's also enough to use the [Synthesis tool to start building our dataset.](/guides/build-a-dataset/synthesize-examples.md)

Next, we'll create a [templated model.](/key-concepts/models.md#templated-models)


---

# 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.entrypointai.com/guides/evaluate-a-prompt/prepare-validation-examples.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.