> For the complete documentation index, see [llms.txt](https://docs.duplocloud.com/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.duplocloud.com/docs/aws-extension/aws-extension/quick-start/connect-existing/example-cost-optimization.md).

# Example: Cost Optimization

This example shows how to connect DuploCloud to an existing AWS account and immediately put the AI to work on a real operational task: identifying cost savings opportunities.

## Prerequisites

* DuploCloud is installed and running.
* You have an AWS account with existing resources.

{% stepper %}
{% step %}

### Add your AWS account as a Provider

Navigate to **AI Admin → Providers** and add your AWS account. Supply an IAM role or access credentials with read access to your AWS resources, and set the scope to the regions you want the AI to analyze.

{% hint style="info" %}
For a full guide on connecting AWS as a Provider, see [Integrating Providers](/docs/getting-started/integrating-providers.md).
{% endhint %}
{% endstep %}

{% step %}

### Create a Workspace

Navigate to **AI Admin → Workspaces** and create a new Workspace. Attach the AWS Provider scope you just created. Assign a Persona that includes the relevant AWS skills.
{% endstep %}

{% step %}

### Open the HelpDesk and create a Ticket

Navigate to **HelpDesk** and click **New Ticket**. Select the Workspace you created. In the ticket, describe what you want:

> "Analyze our AWS account and identify the top cost savings opportunities. Include unused resources, over-provisioned instances, and any reserved instance recommendations."
> {% endstep %}

{% step %}

### Review the results

The AI agent runs the analysis and returns a structured report inside the ticket — listing findings by category, estimated monthly savings, and recommended actions. You can ask follow-up questions or instruct the agent to take action directly from the ticket.
{% endstep %}
{% endstepper %}


---

# 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.duplocloud.com/docs/aws-extension/aws-extension/quick-start/connect-existing/example-cost-optimization.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.