# Copilot

### Copilot helps you do the following:

* Evaluate templates against well-architected frameworks, security assessments, and known configuration vulnerabilities.
* Import your configuration data from JSON, YAML, HCL, TF\_Vars, INI, and any structured data format. 
* Automatically create templates from project parameters.
* Fix template syntax and consistency issues.
* Use prompts to create config variables and templates for any project.
* Learn how to use CloudTruth. 

Copilot does not share your configuration data with outside parties. 

### Using the Copilot

Invoke the Copilot at any time using the Copilot header menu option.

First-time users will see a blank screen and ready to accept your first prompt. 

Returning users will see previous threads.

<figure><img src="/files/pIyCQ1RAHQVYmas7TtSv" alt=""><figcaption><p>Start a new prompt</p></figcaption></figure>

1. Click + to start a new thread or open a previous conversation. The state is preserved.&#x20;
2. Previous conversations are accessible in the left-hand menu.
3. Select a canned prompt. Canned prompts may require more context, which you can add in the message box.&#x20;
4. Send Copilot a prompt, upload a file to take action, or ask Copilot a question.&#x20;

### Sample Copilot conversation

<figure><img src="/files/T0NW5WRg6Az329TRK0Xp" alt=""><figcaption><p>Copilot Main Interface</p></figcaption></figure>

Here's a sample Copilot conversation requesting the AI to generate a Terraform AWS EKS best practices configuration file. The Copilot creates all the standard parameters with descriptions, default values, and templates in various formats: variables.tf, TF\_Vars, or main.tf.


---

# Agent Instructions: 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:

```
GET https://docs.cloudtruth.com/copilot.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.