> For the complete documentation index, see [llms.txt](https://docs.aqua-cloud.io/documentation/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.aqua-cloud.io/documentation/aqua-intelligence/create-test-cases-in-seconds-with-aqua-intelligence/create-test-cases-from-a-requirement.md).
# Create test cases from a requirement
Navigate to aqua and open an existing requirement or create a new one. Once you finish editing it, save your item and click on the aqua Intelligence 'Test' button.
Once the modal appears, the requirement will be automatically linked.
You can also provide some context to aqua Intelligence, so it can better understand your project or specifics of the requirement and generate test cases taking into account added information. This includes, for instance, a glossary of words that are unique for your project or some important information about the product or device that is under the test.
{% hint style="info" %}
If you want to generate a test case for a selected requirement based solely on a description or file, you can switch on the fly by simply selecting the desired option.
{% endhint %}
You can select whether aqua Intelligence should generate one or multiple test cases.
For a single test case, you can define paths: *positive* and *negative*. When you select multiple, AI will generate your test cases with positive and negative paths included.
When generating multiple test cases, you can preview created test cases and decide which should be kept and which should be discarded.
To preview a test case, click on the 'Eye' icon.
You can regenerate test cases too. Simplu click on the corresponding button and provide some additional instructions.
Here’s another neat trick. Once the aqua Intelligence generates a test based on requirement, it is immediately added as a dependency to the requirement. It will also be marked as covered.
{% hint style="info" %}
**Important Reminder:**
Please be aware that aqua Intelligence can occasionally make mistakes or provide inaccurate results. We strongly recommend verifying any crucial information for accuracy.
{% 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.aqua-cloud.io/documentation/aqua-intelligence/create-test-cases-in-seconds-with-aqua-intelligence/create-test-cases-from-a-requirement.md?ask=&goal=
```
`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.