> 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/aura-actions-and-approvals.md).

# Aura Actions and Approvals

Aura in **Rillet** can take action for you directly, such as creating or updating records or sending communications. All actions that modify data require your approval before they are executed. This ensures that nothing is created, updated, or sent without your review.

### Understand How Actions and Approvals Work

Aura requires approval for any action that changes data or sends communication outside of Rillet, while read-only actions, such as generating reports or analyzing data, do not require approval and are completed immediately. The diagram shows how a request becomes an approved action.

```mermaid
flowchart LR
    A("You send<br/>a request") --> B{"Does it change data<br/>or send communication?"}
    B -- "No, read-only" --> C("Result is shown<br/>right away")
    B -- "Yes" --> D{"Is any required<br/>detail missing?"}
    D -- "Yes" --> E("Aura asks you<br/>for the details")
    E --> F
    D -- "No" --> F("Aura shows<br/>an approval card")
    F --> G("Approve")
    F --> H("Edit")
    F --> I("Reject")
    G --> J("Aura runs the action<br/>and confirms it")
    H --> F
    I --> K("Nothing changes")

    classDef start fill:#EDE9FE,stroke:#8B5CF6,color:#2E1065,stroke-width:2px
    classDef step fill:#DDD6FE,stroke:#6D28D9,color:#2E1065,stroke-width:2px
    classDef gate fill:#7C3AED,stroke:#5B21B6,color:#FFFFFF,stroke-width:2px
    classDef end1 fill:#C4B5FD,stroke:#7C3AED,color:#2E1065,stroke-width:2px
    class A,C start
    class E,F,G,H,I step
    class B,D gate
    class J,K end1
    linkStyle default stroke:#7C3AED,stroke-width:2px
```

The following actions require your approval:

| Area                             | Actions That Require Approval                    |
| -------------------------------- | ------------------------------------------------ |
| **Journal entries**              | Creating or updating journal entries             |
| **Invoices and customers**       | Creating or updating invoices or customers       |
| **Bills, vendors, and expenses** | Creating or updating bills, vendors, or expenses |
| **Payments**                     | Recording payments                               |
| **Communication**                | Sending emails                                   |
| **Close**                        | Creating close periods or checklist tasks        |
| **Agents**                       | Running Agents that include data changes         |

### Review, Edit, or Reject an Action

When Aura prepares an action, it displays an approval card directly within the conversation where you made the request. If required information is missing, Aura will ask you to provide additional details before generating the approval card.

For example, if you ask Aura to "Create an invoice for Adobe", provide all required details in your response:

| Field                | Value                |
| -------------------- | -------------------- |
| **Customer**         | Adobe                |
| **Customer Segment** | Enterprise           |
| **Cash account**     | Mercury Checking     |
| **Invoice date**     | 2026-04-21           |
| **Due date**         | 2026-05-21           |
| **Product**          | Subscription         |
| **Revenue account**  | SaaS Revenue         |
| **Amount**           | 5000                 |
| **Description**      | Monthly subscription |

Once all required and valid information is provided, Aura generates an approval card in the conversation with the full invoice details. The approval card shows all parameters of the action, so you can review everything before execution and choose one of these options:

| Option      | What It Does                                                                                                                                                                                                                                                                                                                                                               |
| ----------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Approve** | Executes the action exactly as proposed. Aura then updates the card to show the **Approved** status and displays a confirmation message in the conversation with the created record details, such as the invoice number, customer name, amount, invoice and due dates, cash account, line item details, revenue account, customer segment, and a link to view the invoice. |
| **Edit**    | Lets you modify any details, such as amounts, dates, line items, or descriptions, before approving the updated action.                                                                                                                                                                                                                                                     |
| **Reject**  | Cancels the action before it is executed, so you can provide corrected information, request a new version from Aura, or continue with a different request. Aura makes no changes unless an action is approved.                                                                                                                                                             |

### Manage Approvals Across Agents and Activity

Agents follow the same approval rules as Aura Assistant, and the **Queue** tab in [**Aura Activity**](/EjmEP4KZ9BVp9j2ho4Mh/aura-ai/aura-ai/aura-activity.md) gathers the proposals waiting for review across Aura Assistant conversations and Agents. This keeps even scheduled or multi-step processes under your control, and finance teams can manage approvals at scale from a single workspace.

| Where                 | How Approvals Work                                                                                                                                                                                      |
| --------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Aura Assistant**    | An approval card appears in the conversation where you made the request.                                                                                                                                |
| **Agents**            | When an Agent includes an action that modifies data or sends communication, the Agent pauses at that step, displays an approval card, and continues only after you approve, edit, or reject the action. |
| **Queue in Activity** | You can review pending proposals, approve or reject actions, view supporting details, and open the related workflows and conversations.                                                                 |

### Track Approved Actions

All actions performed through Aura are tracked alongside other records in Rillet. For each action, you can see who created or approved it, when it was performed, and the related record in the system. Records created by Aura also link back to the original conversation or Agent, so you can open a journal entry or invoice to see how it was created and approved, or use [**Audit Trail**](/EjmEP4KZ9BVp9j2ho4Mh/aura-ai/aura-ai/audit-trail.md) to further validate the data, logic, and calculation steps behind the result.

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

Aura will never modify your financial data or send communications without your explicit approval. All actions must pass through the approval step before they are executed.
{% endhint %}

### Frequently Asked Questions (FAQ)

<details>

<summary>Can Aura create multiple close checklist tasks at once?</summary>

Each action Aura takes generates its own approval card, including creating close periods or checklist tasks. There is no dedicated bulk-create action, so creating several tasks means reviewing and approving each one individually.

</details>

### **See Also**

To learn more about actions and approvals in **Rillet**, review these articles:

* [**Getting Started with Aura Assistant**](/EjmEP4KZ9BVp9j2ho4Mh/aura-ai/aura-ai/getting-started-with-aura-assistant.md)
* [**Upload Files to Aura**](/EjmEP4KZ9BVp9j2ho4Mh/aura-ai/aura-ai/connect-external-apps-with-aura-mcp-connector/upload-files-to-aura.md)
* [**Aura Agents**](/EjmEP4KZ9BVp9j2ho4Mh/aura-ai/aura-ai/aura-agents.md)
* [**Aura Activity**](/EjmEP4KZ9BVp9j2ho4Mh/aura-ai/aura-ai/aura-activity.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)


---

# 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/aura-actions-and-approvals.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.