> For the complete documentation index, see [llms.txt](https://helpdocs.conducttr.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://helpdocs.conducttr.com/colibri/getting-started/creating-your-colibri-exercise.md).

# Creating Your Colibri Exercise

If you have access to a Colibri license you'll see the `New Colibri exercise` option when logging in to the Conducttr Editor.

<figure><img src="/files/RUAOIdDVjYbI7ttX48Dj" alt=""><figcaption></figcaption></figure>

{% hint style="info" %}
You can use Colibri for a wide range of self-paced exercises but the default is assumed to be a quiz. If you don't want a quiz, just **enter anything in the quiz field and then delete the table once the exercise has been auto-generated**. You can then start from scratch with an empty table.
{% endhint %}

## Generating an exercise with LISA

From here, you can generate a quiz with LISA. Below is some guidance on prompt input:

* **Policy or procedure** (default)
* **News article link**: LISA will take the information from the URL and generate a quiz based on this. This is especially good if you want to create a quiz/scenario based on real life events&#x20;
* **A scenario**: You can prompt LISA to generate a more story-driven quiz. Describe a situation and ask LISA to frame each question as a decision moment within an unfolding scene

{% hint style="info" %}
To learn more about designing judgement-led exercises in Colibri, visit the pages below:
{% endhint %}

{% content-ref url="/pages/xi8Mv59RxXnwTJz5adWX" %}
[Branching and Choices](/colibri/building-exercises/branching-and-choices.md)
{% endcontent-ref %}

{% content-ref url="/pages/OzqsBwQSsvSCVV33gBiI" %}
[Judgement-led exercises](/colibri/getting-started/creating-your-colibri-exercise/recommended-workflow/judgement-led-exercises.md)
{% endcontent-ref %}

Insert your prompt in the text-box and click `Generate exercise`:

<figure><img src="/files/WcGCEqiZYKfRbxxGYvR8" alt="" width="400"><figcaption></figcaption></figure>

Once generated, you'll have access to the Colibri Editor and LISA would have generated a quiz based on the information you provided. The exercise can now be reviewed and edited:

<figure><img src="/files/2HuosAO2YZZmZr7jzL8f" alt=""><figcaption></figcaption></figure>


---

# 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://helpdocs.conducttr.com/colibri/getting-started/creating-your-colibri-exercise.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.