> 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/aqua-intelligence-chat.md).
# aqua Intelligence Chat
aqua Intelligence chat gives you instant, contextual answers without leaving your workspace. Ask questions, get guidance, and use the responses directly in your work — all without switching between tools or digging through documentation.
#### **Where to access it**
The chat is available from any page in aqua — the navigation page, and any requirement, defect, test case, or test scenario page. Look for the **Ask** button to open it.
#### **What you can ask**
Use the chat to:
* Get answers about testing approaches, requirements writing, or QA best practices
* Ask follow-up questions to dig deeper into a topic
* Generate content you can copy directly into requirements, test cases, or defects
* Find out about aqua features and functionality
> You no longer need to spend time searching through lengthy documentation or browsing multiple resources to find the information you need. Simply ask a question, and aqua Intelligence will provide you with a relevant and accurate answer within a few seconds.
#### **Use the knowledge base in chat**
By default, aqua Intelligence answers using general AI knowledge. If you have files uploaded to the knowledge base, you can switch the knowledge source to get answers grounded in your own documentation:
* **AI knowledge** — general AI knowledge, no setup needed
* **Global knowledge base** — draws from files uploaded across your organisation
* **Project knowledge base** — draws from files uploaded for the current project
To learn how to set up and upload files, see [Knowledge Base with aqua Intelligence](/documentation/aqua-intelligence/knowledge-base-with-aqua-intelligence.md)
#### **Your chat history**
All your chat sessions are saved and accessible only to you. Other team members and administrators cannot see your conversations. You can return to any previous session at any time to review or reuse responses.
#### **Copying responses**
To use a response elsewhere in aqua, click the **Copy** icon next to the answer. The text is copied to your clipboard, ready to paste into any item.
{% hint style="success" %}
aqua Intelligence will store all you sessions only for you. aqua Administrator or other team members of your projects won't see your chats or can have access to it.
{% endhint %}
### 🔥 aqua Team tips for the best results
To make the most out of the aqua Intelligence feature, consider the following tips:
* **Be specific** — the more context you provide, the more accurate the answer. Instead of *"how do I write test cases"*, try *"how do I write test cases for a login flow with biometric authentication"*
* **Ask follow-up questions** — if the first answer isn't quite right, refine it by asking for more detail, examples, or a different angle
* **Use your knowledge base** — if your question is domain-specific, switch to the relevant knowledge base for answers grounded in your own documentation
{% hint style="info" %}
**Important Reminder:**
Please be aware that aqua Intelligence can occasionally make mistakes or provide inaccurate answers. 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/aqua-intelligence-chat.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.