# Create a multi-prompt assistant

## 1. Break the conversation into steps

In each step, you can define a prompt.

## 2. Define logic for each step

Just like in the “Lead qualification” template, you can have this prompt to define when to move to the next step like if users say “yes” to the question, transition to your\_next\_state state.

```

##Task
1. Inform the user about the purpose of the call and provide a brief introduction.  

   wait for user response

2. Ask if the user is experiencing any dental issues or requires a routine checkup.  

   wait for user response
   - If the user mentions a dental issue, transition to discuss_concern to gather more details.  
   - If the user needs a routine checkup, transition to schedule_appointment.  

3. Ask if the user is interested in receiving a follow-up reminder or dental care tips via email.  
   - If yes, collect their email and transition to update_contact_preferences.  
   - If no, politely thank them and end the call using end_call.
   
...


```

If you find that the AI assistant still doesn't stop at the right time, or you need to perform some actions instead of stopping at each action, you can write it more precisely by adding a "wait for user response" as shown below.

```

## Task 
1. Inform user why you are calling.  
2. Ask for user's name.  

wait for user response  

3. Ask if user wants to schedule an appointment, report an emergency, or inquire about services.  

wait for user response  
   - If scheduling, transition to the appointment scheduling state.  
   - If it's an emergency, transition to the emergency state.  
   - If inquiring, provide relevant information.  

...


```

## 3. Define when to call the function

Just like in the “Lead qualification” template, you can have the prompt to define when to call the function like call the `your_function_name` function to book the appointment.

```

## Task 

3. Confirm the date, time, and type of dental appointment selected by the user: "Just to confirm, you want to schedule a [routine checkup/dental consultation] on [date] at [time]." Ensure the chosen slot is available.  
4. Once confirmed, call function **book_appointment** to finalize the appointment.

...

```


---

# 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/create-a-multi-prompt-assistant.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.