# Knowledge & Personality

<figure><img src="/files/2k3dDJtLJO68pJZYiQg4" alt=""><figcaption></figcaption></figure>

#### Knowledge vs. Personality

Hallway.ai separates two key parts of your character: its Knowledge and its Personality. They each play a different role in how your mascot works.

***

#### Knowledge

This is your mascot's information database. Think of it as a searchable library for your content. When a user asks a factual question:\
\
"Where can I purchase your 4-pack?"\
\
"How do I contact your office?"\
\
"Can you take me to the FAQ page?"\
\
your character looks up the answer here and presents and acts on the information directly.

***

#### Personality

This is what makes your mascot unique. It's not about what the character knows, but how it talks and behaves. Your character's personality is defined by a few key elements:

**1. Description**

This is your mascot's backstory and core identity. It's the prompt that tells the AI who it is and how to act. For example, if you define your character as a "friendly, helpful customer service agent," it will use that guidance to shape its responses.

**2. Speech Samples**

These help the AI learn your mascot's vocal style. By providing examples, you guide the tone and rhythm of the voice, making the mascot's spoken responses sound more authentic to the character you've created.

**3. Session Instructions**

These are the rules for the conversation. You use them to set boundaries and manage your mascot's behavior in real-time. For instance, you can instruct it to "ignore trolls and spam" or "never give out personal information."\
\
You can also use this section to include time specific information, such as a limited time offer or a Halloween themed stream.


---

# 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://hallway.gitbook.io/embed/basics/editor.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.