> 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/grounding-with-aqua-intelligence-version-before-ai-reviewed.md).

# Grounding with aqua Intelligence (version before AI-reviewed)

### Introducing AI grounding with your own data in aqua

You can now make AI in aqua even smarter by grounding it in your own knowledge base.

Whether you’re working with industry standards or internal documentation you can now upload files to help AI generate more accurate, useful, and relevant outputs.

### **What is grounding?**

Think of grounding like giving AI a **cheat sheet**.

aqua Intelligence is smart — but it doesn’t know your internal terminology, standards, specifics or what your team agreed last quarter. With grounding, you upload files, and AI can use them to give better, more tailored answers.

### **What can AI do with grounded knowledge?**

When you provide context, AI becomes more precise and useful. 

For example, it can:

* Write **requirements or test cases** that match your industry, product, or internal standarts.
* Use your **project-specific terms** and phrasing instead of generic wording.
* **Answer questions** using your uploaded documents as a source of truth.

Whether you work in medical, finance, insurance, or tech — AI will reflect *your world*, not someone else’s.

### **How it works?**

You can upload documents and reference material at two levels:

* **Global level**: Available across all projects
* **Project level**: Scoped to specific projects only

This allows you to give aqua Intelligence the right context depending on your use case and project.

You stay in full control — AI never scans your project data automatically. It only uses what you’ve explicitly uploaded in the **AI knowledge base** section.

<figure><img src="/files/VdwzR0QKdXX8WcGyp3ic" alt=""><figcaption></figcaption></figure>

<figure><img src="/files/NudtA7emxUNceCpNkT6N" alt=""><figcaption></figcaption></figure>

### **Is it secure?**

Yes. Files are only used for generating responses during your session. They are:

* Not used for model training
* Not accessed unless uploaded
* Respect your project permissions and visibility

You can remove or replace files anytime.

{% hint style="info" %}
**File support and future plans**

Currently, you can upload documents in:

* PDF, DOCX, XLSX, Markdown, and TXT

We're also exploring the possibility of **company-defined templates**, which would allow aqua Intelligence to generate requirements and test cases that follow your internal standards and formatting.
{% endhint %}

### Access and trial periods

We want to make sure everyone can explore RAG and see the value it brings. That’s why we’re offering a free trial for all customers:

* **Public cloud users**\
  RAG will remain free to use in beta, so you can experiment and integrate it into your daily work at no extra cost for now.
* **Private cloud users**\
  You’ll have a **one-month trial** period once enabled after the request. The reason for this shorter trial is that RAG in private clouds requires dedicated infrastructure and data isolation, which come with additional costs.&#x20;

### Pricing information

RAG is planned as a **paid add-on** in the future. For public cloud users, we will announce the pricing well in advance before 2027.

\ <mark style="color:orange;">For private cloud users, pricing depends on your individual setup and infrastructure. To get a tailored offer, please contact your</mark> <mark style="color:orange;"></mark><mark style="color:orange;">**Customer Success manager**</mark><mark style="color:orange;">.</mark>

### How to get access

If you’d like to use RAG, simply:

* Reach out to our **Customer Success team**, or
* Fill out our [**request form**](https://tally.so/r/mYvXB6)

Once approved, you’ll be able to explore RAG right away and enjoy it during the beta phase.


---

# 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/grounding-with-aqua-intelligence-version-before-ai-reviewed.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.