> 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/getting-started/aura-ai-assistant/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.

This article explains how to start using Aura, manage your conversations, and get the most out of your interactions.

### Start a Conversation

Use Aura Assistant to ask questions, analyze data, and perform actions using natural language.

To start a conversation:

1. Open **Aura** from the side panel.

   <figure><img src="/files/eRiiJUfeDl50NIXgEthY" alt=""><figcaption></figcaption></figure>
2. Click **New Assistant**.
3. Enter your question or request in the message field.

   <figure><img src="/files/XBn3UAJkulXVu2gt0EHz" alt=""><figcaption></figcaption></figure>

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”
* “What accruals do I need this period?”

Aura will process your request and return results based on your financial data.

### How Aura Responds

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

<figure><img src="/files/Scmyb3XiTEErkp9pPorL" alt=""><figcaption></figcaption></figure>

It will:

* Retrieve relevant data from your Rillet account.
* Run the necessary analysis.
* Display the result directly in the Assistant.

Depending on your request, results may appear as:

* Tables
* Lists
* Summaries
* Structured financial outputs

If the data required to answer your question is not available, Aura will indicate that it cannot complete the request.

### Manage Your Conversations

All conversations with Aura are saved automatically, allowing you to revisit them at any time.

From the conversation panel, you can perform the following actions:

* Pin conversations to keep important requests easily accessible.

  <figure><img src="/files/ajGHegdSg2pj8aDYvJA8" alt=""><figcaption></figcaption></figure>
* Rename conversations to organize your work.
* Delete conversations you no longer need.

  <figure><img src="/files/YUHM8ncCW23iPYFBHYOY" alt=""><figcaption></figcaption></figure>
* Search your history to quickly find past conversations.

  <figure><img src="/files/50vDSErteCLOKwlEIfeb" alt=""><figcaption></figcaption></figure>

This is especially useful for recurring analyses or frequently used reports.

### Best Practices

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="success" %}

### Tip

If you regularly ask the same type of question, consider turning it into an agent so it can be reused or scheduled.
{% endhint %}

### **See Also**

For related topics, see:

* [**Aura AI Assistant**](/EjmEP4KZ9BVp9j2ho4Mh/getting-started/aura-ai-assistant.md)
* [**Aura AI Prompt Examples**](/EjmEP4KZ9BVp9j2ho4Mh/getting-started/aura-ai-assistant/aura-ai-prompt-examples.md)
* [**Reasoning Trail**](/EjmEP4KZ9BVp9j2ho4Mh/getting-started/aura-ai-assistant/audit-trail.md)
* [**Agents**](/EjmEP4KZ9BVp9j2ho4Mh/getting-started/aura-ai-assistant/agents.md)
* [**Assistant vs Agent**](/EjmEP4KZ9BVp9j2ho4Mh/getting-started/aura-ai-assistant/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 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.rillet.com/EjmEP4KZ9BVp9j2ho4Mh/getting-started/aura-ai-assistant/getting-started-with-aura-assistant.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.