> 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/agents.md).

# Agents

An Agent is a multi-step plan that Aura builds based on a request you describe. Instead of completing tasks one by one in Aura Assistant, you can review the full plan, make adjustments, and run it as a structured process.

Agents are useful for complex tasks, recurring processes, or anything you want to standardize and automate.

### **When to Use Agents**

UUse Agents when you need more structure and control over your tasks.

Agents are especially useful when:

* A task requires multiple steps.
* You want to review the full plan before execution.
* You need to repeat the same process regularly.
* You want to schedule work to run automatically.

For simple questions or quick analysis, use Aura Assistant instead.

### Create an Agent

You can create an Agent from scratch or use a suggested one.

To create an Agent:

1. Go to **Aura** **AI** from the side panel.

   <figure><img src="/files/fKkw6COelN4qim5BhacE" alt=""><figcaption></figcaption></figure>
2. Click **Aura Agent**.

   <figure><img src="/files/ixEJZma5HDunB5CsOhqv" alt=""><figcaption></figcaption></figure>
3. Choose one of the following options:
   * Select **My Agents** and click **Create Agent** to start from scratch.

     <figure><img src="/files/dFqgLfQI3ZH0YnCk82lK" alt=""><figcaption></figcaption></figure>
   * Select **Suggested** to use a prebuilt agent.

     <figure><img src="/files/hSAXfTrnokBHtx9fVNps" alt=""><figcaption></figcaption></figure>
4. Describe what you want to accomplish.

Aura will generate an agent plan that includes:

* A list of tasks.
* The order in which they run.
* Dependencies between tasks.

You can also include files in your request. Aura will use them as input when building or executing the Agent.

### Review and Edit the Plan

Before running an Agent, you can review and adjust each step.

In the Agent plan, each task includes:

* A name
* Instructions
* Dependencies (if applicable)

From this view, you can:

* Edit the instructions for any step.

  <figure><img src="/files/YpiDZ32Rlsy2RlLc8HGX" alt=""><figcaption></figcaption></figure>
* Add new tasks using **Add Tasks.**

  <figure><img src="/files/66z59STL9cu8bDSf1weg" alt=""><figcaption></figcaption></figure>
* Remove tasks you don’t need.

This allows you to refine the Agent before execution.

### Run a Workflow

Once the plan is ready, you can run it immediately.

To run a workflow:

1. Review the workflow plan.
2. Click **Execute Workflow.**<br>

   <figure><img src="/files/KySWkfed1xL1sxWUEKqm" alt=""><figcaption></figcaption></figure>

Aura will run the workflow and display progress for each step as it executes.

### Approvals Within Agents

Agents follow the same approval rules as Aura Assistant.

Approval cards appear during Agent execution when a step requires creating, updating, or sending data.

If a step includes an action that modifies data or sends communication:

* The Agent pauses at that step.
* An approval card is displayed.
* You must choose to approve, edit, or reject the action.

After your decision, the agent continues from the same step.

Read-only steps, such as analysis or reporting, run automatically without approval.

### Save and Reuse Agents

You can save Agents to reuse them later.

<figure><img src="/files/WlwnnFYVbhiqDZN7uH6O" alt=""><figcaption></figcaption></figure>

When saving an Agent, you can:

* Enter a name.
* Add a description.
* Choose whether to share it with your organization.

Saved Agents appear under **My Agents** and can be reused at any time.

### Schedule an Agent

Agents can be scheduled to run automatically.

To schedule an Agent:

1. Go to the **Agent**.
2. Click **Schedule Agent.**
3. Select one of the following options:
   * One-time execution.
   * Recurring schedule (daily, weekly, monthly, or custom).

<figure><img src="/files/E0GEAZZ9mMQlmIcgMZYW" alt=""><figcaption></figcaption></figure>

All schedules run based on your subsidiary’s timezone. The scheduler always reflects the default subsidiary you are working in.

You can pause, edit, or cancel a schedule at any time.

<figure><img src="/files/lvzkzxrpoR1ubmB6O9ln" alt=""><figcaption></figcaption></figure>

### Scheduled Agents and Approvals

Scheduled Agents do not bypass approvals.

<figure><img src="/files/h0P1ZZQfb6jKeg1fI0rS" alt=""><figcaption></figcaption></figure>

If an Agent includes actions that modify data or send communication:

* The agent pauses at that step.
* It is marked as **Needs attention.**
* You must review and approve, edit, or reject the action.

Once you take action, the agent resumes from the same step and continues execution.

This ensures that all changes remain under your control, even for automated agents.

### Agent History

Each Agent run is recorded so you can review past activity.

From the Agent history, you can:

* View previous executions.
* Review results and outputs.
* See approved or rejected actions.

This helps you track performance and understand how agents are being used.

{% hint style="success" %}

### Tip

If you find yourself repeating the same task regularly, turn it into an agent and schedule it. This reduces manual work and helps ensure consistency.
{% endhint %}

### **See Also**

For related topics, see:

* [**Getting Started with Aura Assistant**](/EjmEP4KZ9BVp9j2ho4Mh/getting-started/aura-ai-assistant/getting-started-with-aura-assistant.md)
* [**Upload Files to Aura**](/EjmEP4KZ9BVp9j2ho4Mh/getting-started/aura-ai-assistant/upload-files-to-aura.md)
* [**Actions and Approvals**](/EjmEP4KZ9BVp9j2ho4Mh/getting-started/aura-ai-assistant/actions-and-approvals.md)
* [**Reasoning Trail**](/EjmEP4KZ9BVp9j2ho4Mh/getting-started/aura-ai-assistant/audit-trail.md)
* [**Assistant vs Agent**](/EjmEP4KZ9BVp9j2ho4Mh/getting-started/aura-ai-assistant/assistant-vs-agent.md)
* [**Aura AI Prompt Examples**](/EjmEP4KZ9BVp9j2ho4Mh/getting-started/aura-ai-assistant/aura-ai-prompt-examples-1.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/agents.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.