> 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/getting-started-with-aura-assistant.md).

# Getting Started with Aura Assistant

Aura allows you to interact with your financial data using natural language. You can ask questions, explore reports, and perform actions without navigating multiple areas of the platform. Aura also remembers your preferences across sessions, so you do not need to repeat the same instructions every time. See [**Aura Memory**](/EjmEP4KZ9BVp9j2ho4Mh/aura-ai/aura-ai/aura-memory.md) to learn how to save and manage what Aura remembers.

### Before You Begin

To get better results when using Aura, keep the following in mind:

* Include specific details such as timeframes, entities, or accounts.
* Ask follow-up questions to refine results.
* Reuse previous conversations for recurring analysis.

{% hint style="info" %} <mark style="color:$info;">**Note:**</mark>

If you regularly ask the same type of question, consider using [**Aura Agents**](/EjmEP4KZ9BVp9j2ho4Mh/aura-ai/aura-ai/aura-agents.md) to turn it into a workflow you can reuse or schedule.
{% endhint %}

### Start a Conversation

Follow these steps to start a conversation and use Aura Assistant to ask questions, analyze data, and perform actions using natural language:

1. Open **Aura** from the side panel.
2. Click **New Session**.
3. Enter your question or request in the message field.

   <figure><img src="https://612265232-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FNpXFVFZpTQck3vIrjmHB%2Fuploads%2Fm8ez4W7p1XGkqStEpoHR%2Fimage.png?alt=media&amp;token=74272f6e-b33d-42cb-b029-1752f73985d3" alt=""><figcaption></figcaption></figure>

{% hint style="info" %} <mark style="color:$info;">**Note:**</mark>

You can ask questions in plain language, such as “What were my top 10 vendors last month?”, “Show me the P\&L for Q1 2026”, or “What accruals do I need this period?” Aura processes your request and returns results based on your financial data. See [**Aura AI Prompt Examples**](/EjmEP4KZ9BVp9j2ho4Mh/aura-ai/aura-ai/aura-ai-prompt-examples.md) for more.
{% endhint %}

### Understand How Aura Responds

When you ask a question, Aura performs several steps to generate a response.

<figure><img src="https://612265232-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FNpXFVFZpTQck3vIrjmHB%2Fuploads%2FDPohQNm9UkwK1X6hRiA9%2Fimage.png?alt=media&amp;token=f7208ada-1f94-4cf1-b38c-66bd3ced0e38" alt=""><figcaption></figcaption></figure>

Aura retrieves the relevant data, runs the analysis, and displays the result as a table, list, summary, or structured output, or indicates that it cannot complete the request if the data is unavailable.

### Manage Your Conversations

Complete any of the following steps from the conversation panel to manage a saved conversation:

1. Click the **three dots (•••)** next to the conversation, then choose one of the following:
   * Pin it to keep important requests easily accessible.
   * Rename it to organize your work.
   * Delete it when you no longer need it.
2. Search your history to quickly find past conversations.

   <figure><img src="https://612265232-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FNpXFVFZpTQck3vIrjmHB%2Fuploads%2FDX30mQa2IwxnGp78IdnQ%2Fimage.png?alt=media&amp;token=dc6c6257-bf68-4efe-8e03-904bb4446e5b" alt=""><figcaption></figcaption></figure>

Rillet saves every conversation with Aura automatically, so you can revisit or reuse it later, which is especially useful for recurring analyses or frequently used reports.

### **See Also**

To learn more about Aura in **Rillet**, review these articles:

* [**Aura AI Assistant**](/EjmEP4KZ9BVp9j2ho4Mh/aura-ai/aura-ai.md)
* [**Aura Memory**](/EjmEP4KZ9BVp9j2ho4Mh/aura-ai/aura-ai/aura-memory.md)
* [**Aura AI Prompt Examples**](/EjmEP4KZ9BVp9j2ho4Mh/aura-ai/aura-ai/aura-ai-prompt-examples.md)
* [**Audit Trail**](/EjmEP4KZ9BVp9j2ho4Mh/aura-ai/aura-ai/audit-trail.md)
* [**Aura Agents**](/EjmEP4KZ9BVp9j2ho4Mh/aura-ai/aura-ai/aura-agents.md)
* [**Assistant vs Agent**](/EjmEP4KZ9BVp9j2ho4Mh/aura-ai/aura-ai/assistant-vs-agent.md)


---

# 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/getting-started-with-aura-assistant.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.