# Overview

Voho provides functionality to build your conversational assistant:

1. Single Prompt: Design your assistant with one comprehensive prompt
2. Multi-Prompt: Structure your assistant with multiple organized prompts

### Single Prompt Assistant

The single prompt approach allows you to define your assistant's behavior with one comprehensive prompt. It’s straightforward and great for simple use cases.

While this approach is an excellent starting point, you may face some challenges as your assistant becomes more complex:

1. The assistant may deviate from given instructions
2. Function calling becomes less reliable
3. The prompt becomes difficult to maintain as it grows larger

Due to these limitations, we recommend using the multi-prompt approach for more sophisticated assistants.

### Multi-Prompt Assistant

The multi-prompt approach allows you to create a structured tree of prompts. Each node in the tree can contain:

* Its own unique prompt
* Custom function calling instructions
* Clear transition logic to other nodes

For example, our “Lead Qualification” template demonstrates this structure:

In this template, we break down the conversation into two steps:

1. **Lead Qualification**: Gather and verify all required information about the patient's needs and preferences.
2. **Appointment Scheduling**: Schedule the dental appointment only after successfully qualifying the patient.

This structured approach prevents common issues, such as booking appointments prematurely before understanding the patient's requirements. The multi-step structure ensures the conversation follows the correct sequence and maintains context throughout the interaction.


---

# 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://voho.gitbook.io/voho/build/overview.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.