# Turn a Prompt into a Template Here is a sample prompt that we will turn into a [template](/key-concepts/templates.md) for [evaluation](/key-concepts/evaluation.md): {% code overflow="wrap" %} ``` You are a professional email marketer. Review the following email description and write a creative email subject line idea for it that is likely to grab attention. Do not return anything except the subject line. ``` {% endcode %} ### Create a New Project Go to the home screen and press + to create a new Project. For the Project description, you can put the following: > Write email subject lines from email descriptions.

Press "Create" and you will land in a new Project called "Subject Line Writer" or similar. ### Create a Chat Template Navigate to templates in the sidebar, then press + to create a new template. Leave the type as `Chat` by default. In the `system` prompt box, enter our instructions. {% code overflow="wrap" %} ``` You are a professional email marketer. Review the following article and write a creative email subject line idea for it that is likely to grab attention. Do not return anything except the subject line. ``` {% endcode %} With the `user` prompt text box selected, press the "New field" button.

Create a new field while editing the template

For the name, enter "Content Description". The reference will be populated automatically and the helper text can be left blank.

Press "Save & close". Now press the button to insert the new Content Description field into your `user` prompt.

The entire prompt section should look like this:

Repeat the same process to create and insert a field into the `assistant` output box called "Subject Line." This should be what you have at the end:

Press "Save." We now have a Template based on our prompt that can handle different pairs of data for the `article` and the `subject_line` that we need the model to generate. --- # Agent Instructions: 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: ``` GET https://docs.entrypointai.com/guides/evaluate-a-prompt/turn-a-prompt-into-a-template.md?ask= ``` The question should be specific, self-contained, and written in natural language. 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.