> For the complete documentation index, see [llms.txt](https://docs.rillet.com/EjmEP4KZ9BVp9j2ho4Mh/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.rillet.com/EjmEP4KZ9BVp9j2ho4Mh/aura-ai/aura-ai.md).

# Aura AI

Aura is Rillet’s built-in AI assistant, letting you ask questions, analyze performance, generate reports, and take action using natural language instead of navigating multiple reports manually. Through Agents, it can also draft and execute multi-step processes, such as preparing reports or generating accounting entries, always with your approval. Aura uses your actual, authorized financial data in Rillet, and lets you know when requested data is not available rather than generating unsupported results.

### **What You’ll Find in This Section**

This section includes a set of guides that help you understand how to use Aura in different scenarios, from quick analysis to more advanced multi-step processes.

{% columns %}
{% column %}
{% content-ref url="/pages/CmmzJ1ul9151in9Icx4O" %}
[Getting Started with Aura Assistant](/EjmEP4KZ9BVp9j2ho4Mh/aura-ai/aura-ai/getting-started-with-aura-assistant.md)
{% endcontent-ref %}
{% endcolumn %}

{% column %}
{% content-ref url="/pages/ALsMa0pJuxC9nTcVjkhP" %}
[Upload Files to Aura](/EjmEP4KZ9BVp9j2ho4Mh/aura-ai/aura-ai/connect-external-apps-with-aura-mcp-connector/upload-files-to-aura.md)
{% endcontent-ref %}
{% endcolumn %}
{% endcolumns %}

{% columns %}
{% column %}
{% content-ref url="/pages/uJYWgL6nCispXxfAP1UK" %}
[Aura Actions and Approvals](/EjmEP4KZ9BVp9j2ho4Mh/aura-ai/aura-ai/aura-actions-and-approvals.md)
{% endcontent-ref %}
{% endcolumn %}

{% column %}
{% content-ref url="/pages/PRkyjtN3AgzU4wdG9LA4" %}
[Aura Command Center](/EjmEP4KZ9BVp9j2ho4Mh/aura-ai/aura-ai/aura-command-center.md)
{% endcontent-ref %}
{% endcolumn %}
{% endcolumns %}

{% columns %}
{% column %}
{% content-ref url="/pages/pMb5uhB7Ri4L3qLU3bW8" %}
[Audit Trail](/EjmEP4KZ9BVp9j2ho4Mh/aura-ai/aura-ai/audit-trail.md)
{% endcontent-ref %}
{% endcolumn %}

{% column %}
{% content-ref url="/pages/d7bNosqscr2IrdqV6ljL" %}
[Aura Agents](/EjmEP4KZ9BVp9j2ho4Mh/aura-ai/aura-ai/aura-agents.md)
{% endcontent-ref %}
{% endcolumn %}
{% endcolumns %}

{% columns %}
{% column %}
{% content-ref url="/pages/zgjrJkGdsShIwOqgHz9Z" %}
[Assistant vs Agent](/EjmEP4KZ9BVp9j2ho4Mh/aura-ai/aura-ai/assistant-vs-agent.md)
{% endcontent-ref %}
{% endcolumn %}

{% column %}
{% content-ref url="/pages/t5kNRImXDPQ793Nm2tb1" %}
[Aura AI Prompt Examples](/EjmEP4KZ9BVp9j2ho4Mh/aura-ai/aura-ai/aura-ai-prompt-examples.md)
{% endcontent-ref %}
{% endcolumn %}
{% endcolumns %}

### **How to Use This Guide**

Start with **Getting Started with Aura Assistant** if you are new to Aura, then review **Actions and Approvals** to understand how actions work. Explore **Agents** to automate tasks, and check **Aura AI Prompt Examples** for ideas. You do not need to learn specific commands or syntax to use Aura. Just ask in plain language, and Aura determines how to retrieve the data, run the analysis, or prepare the action.


---

# 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.rillet.com/EjmEP4KZ9BVp9j2ho4Mh/aura-ai/aura-ai.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.