> For the complete documentation index, see [llms.txt](https://docs.avoautomation.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.avoautomation.com/avo-assure/create-and-execute-tests-with-design-studio/optimizer-beta/prompts/working-with-custom-prompt.md).

# Working with Custom Prompt

The Custom prompts allow you to create your own queries based on specific project data or requirements. This article explains how to create and run Custom prompts. It also explains how to view the results returned by created prompts.

{% hint style="info" %}
**Note**: 

* The **Custom** section appears after you create and send a custom prompt.
* You can also select **+ Create New** to create a custom prompt.
  {% endhint %}

To create and view Custom prompts, perform the following actions:

1. On the **Home** page, under **Projects**, select the required project.
2. Select **Design Studio** > **Optimizer**.
3. In the **Optimizer** page, go to the **Analyze my** text box.
4. Enter your question or prompt. For example, Analyze my test cases that nobody has run since June.
5. Select the Send <i class="fa-paper-plane-top" style="color:$primary;">:paper-plane-top:</i> icon. The Optimizer processes your question and displays the **Action Summary** with the corresponding results in a table.


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.avoautomation.com/avo-assure/create-and-execute-tests-with-design-studio/optimizer-beta/prompts/working-with-custom-prompt.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.