> 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/feature-documentation/planning/ai-assistants/lisa.md).

# LISA

LISA is an AI Assistant in Conducttr specialised in **writing directly into the MEL**. Designers can utilise LISA in AXS as well as the Sidekick side panel in the Exercise Editor.

| Benefit                                                                | Feature                                                          |
| ---------------------------------------------------------------------- | ---------------------------------------------------------------- |
| LISA dramatically reduces the time it takes to create an exercise      | Create injects on the fly with instant MEL updates               |
| LISA helps to overcome the creative berrier                            | With Sidekick, work without switching between AXS and the Editor |
| Quickly transforms a storyline into a MEL using an ISO 22398 structure | LISA understands and generates content in multiple languages     |
| Continuity of work in Sidekick                                         | Creates a 3-act MEL                                              |

{% hint style="info" %}
The more specific you can be with LISA the better results you will get. Hence, copying a news article is handy as it has a lot of detail about time, location, incidents, etc. and prevents you typing.
{% endhint %}

## AXS

### Talking to LISA

LISA will ask for additional information and confirmation if you don't provide enough detail. She does this to ensure the best results.

{% hint style="info" %}
You can communicate with LISA in any language, and she will generate the exercise in your preferred language.
{% endhint %}

{% stepper %}
{% step %}

#### Have a conversation

In the example below, LISA is asking about the player role. This is because although the user has given details of a flood in Slovenia, the exercise would be quite different if played by e.g. a bank in Slovenia vs a local authority.

{% hint style="info" %}
If you ask LISA to use certain personas in your exercise, or if the context provided includes key personas (such as those mentioned in an article), she will use them to create the exercise personas. 
{% endhint %}

<figure><img src="/files/vmVakGJumr899avplwdU" alt=""><figcaption></figcaption></figure>

The user has added details and LISA lists what she has, asking for confirmation.

<figure><img src="/files/ZdmzrcRRIy2oUz5G9Zvw" alt=""><figcaption></figcaption></figure>
{% endstep %}

{% step %}

#### Confirm and export

Once details such as the key stakeholders are confirmed, LISA will generate injects with real content that you can import directly into the Editor.

<figure><img src="/files/qpyNZbSVRzLShv0Gawzb" alt=""><figcaption></figcaption></figure>
{% endstep %}

{% step %}

#### Review the .csv file

{% hint style="warning" %}
Just like an intern, LISA doesn't always get it right first time. If she makes a mistake, go back to the chat and correct her, then ask her to export again.
{% endhint %}

Open the exported file in Excel and check all looks good. LISA will remember the chat thread, so if you would like to make some changes, she will still maintain the same personas as the previous ones.

Once you are happy with it, import the file into the Editor.

<figure><img src="/files/3Xvhx1aU8833dzHClvG6" alt=""><figcaption></figcaption></figure>
{% endstep %}

{% step %}

#### Import MEL into the Editor

<div align="left"><figure><img src="/files/N0tNjJUqYOMJhZeNNrJh" alt=""><figcaption></figcaption></figure></div>
{% endstep %}
{% endstepper %}

## Sidekick

You can use LISA in Sidekick too, an AI-powered sidebar featured in the Editor. Based on your conversations, LISA will write directly into the MEL.&#x20;

<div align="left"><figure><img src="/files/aPcpAt11yk6gCuRd2Mxk" alt="" width="263"><figcaption></figcaption></figure></div>


---

# 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/feature-documentation/planning/ai-assistants/lisa.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.