> For the complete documentation index, see [llms.txt](https://docs.foretellreality.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.foretellreality.com/foretell-ai/authoring-tool/ai-personas.md).

# AI Personas

The AI Personas tab is where you create the characters the trainee will talk to.

You can create multiple personas that represent different kinds of people one might encounter in this scenario, though most simulations usually stick to just one persona.

To create a new persona, near the top of the AI Personas tab click on the plus button next to the existing personas. This will automatically generate a random avatar, name, role, and age for you to edit. You can duplicate existing avatars using the duplicate button that loocks like a square on top of another square in the bottom right corner of the avatar icon, and delete personas using the button that looks like a trash can in the bottom right corner of the avatar icon.

<figure><img src="/files/vPyXtOGrBqc8mcW7JtYR" alt=""><figcaption></figcaption></figure>

Our online tool for creating a new AI persona is split into two sections:

## Basic information and prompt text input

* Define the Name, Role, and Age of the AI agent
* Select the appearance of the AI agent
* Choose a voice for the AI agent
* Provide starting instructions for the conversation
* (Optional) Provide a block of text to prompt the AI agent in the “Instructions” box instead of using our advanced settings

<figure><img src="/files/G1QPKlurvHZa2ECWLWeZ" alt=""><figcaption></figcaption></figure>

* In addition, you can provide the publicly available knowledge regarding this Persona

<figure><img src="/files/9e4sOf74gUhkHqTR1gx8" alt=""><figcaption></figcaption></figure>

## Advanced Settings

The advanced settings allow you to provide context boxes and conditions for the conversation.

To enable Advanced Settings, click on the toggle labeled **"View Advanced Settings"** below the list of AI Personas

<figure><img src="/files/uksWEi1NWvYMs4HmREzU" alt=""><figcaption></figcaption></figure>

### Additional Details

Additional Details are input fields that let you categorize background information into sections such as “Persona Objectives”, “Background and Context”, or “Common Responses”.

To edit the name or contents of an Additional Detail slot, simply click on the name or contents box and you'll be able to edit the text. Once you are done editing, click on the green **"Save"** button that might otherwise just display a checkmark.

To add a new slot click onk the **"+ Add Additional Detail"** button near the top of the list and a new slot will appear at the bottom of the list of details.

<figure><img src="/files/a9srnv2Wf88ZtClKlB7R" alt=""><figcaption></figcaption></figure>

### Conditions

Conditions are a way to program responses for when specific topics occur. These can be used to unlock new sections of the conversation, to trigger emotional responses, or to give the AI agent responses for common questions.

To create a new condition, scroll down to the Conditions section. Each condition is split into two text boxes, an **"If"** and **"Then"** box. Type in the condition in the **"If"** box and the response in the **"Then"** box, then make sure to click on the plus sign to the right of the condition to ensure it is added. You can delete conditions by clicking on the minus button to the right of the condition.

<figure><img src="/files/MDCUl6AH26NCAqy8g7MX" alt=""><figcaption></figcaption></figure>

### Supporting Documents

Supporting Documents are a way to provide reference files for the AI agent to use during conversation. In addition to the AI persona details we type in, we can provide documents such as a pdf of the company's employee handbook, a resume, or a witness statement.

There are two places to submit Supporting Documents. Supporting Documents uploaded to the Scenario tab will be used for all AI Personas, while Supporting Documents uploaded to the AI Persona tab will only be used when that AI Persona is used.

To upload a document, click on the button labeled **"Upload Supporting Document(s)"**. This will open a File Explorer window where you can search for and select the file you wish to upload. These files must be text based. After uploading, the contents of the document will be added to a new slot in the **"Created and/or Uploaded Supporting Documents"** section. You can edit the name and contents of the upload after the fact by clicking on the text boxes, making your changes, then clicking the **"Save"** button at the bottom of the page.

<figure><img src="/files/TxxNKXZr4aqmQ6u29lic" alt=""><figcaption></figcaption></figure>

You can also simply type in a supporting document by clicking on the **"+ Add Supporting Document"** button.

## Persona Creation Best Practices

We have identified three stages in AI Persona creation:

1. [Character Identity](/foretell-ai/authoring-tool/ai-personas/character-identity.md) - Defining who the AI agent is and what their background is
2. [Speaking Style](/foretell-ai/authoring-tool/ai-personas/speaking-style.md) - The things the AI agent says and the emotions they display
3. [Testing](/foretell-ai/authoring-tool/ai-personas/testing.md) - Ensuring the AI agent responds appropriately during the simulation


---

# 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:

```
GET https://docs.foretellreality.com/foretell-ai/authoring-tool/ai-personas.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.
