Skip to main content

AI Concierge: Additional Prompts

Learn how to use additional prompts for the AI Concierge to control and tailor its behavior for different use cases.

Written by Alexander Knechtl

Additional Prompts in the AI Concierge

Under Additional Prompts in the AI Concierge, you can control the AI's behavior and tailor it for different use cases.

Three predefined categories are available to help you get started:

  • Communication Style

  • Limitations

  • Escalations

You can also create custom categories at any time if you need additional structure.


How It Works

To create a new additional prompt, first open the desired category. Then click “Add Additional Prompt”, enter a name for the prompt, and define the prompt content.

An additional prompt is a short instruction for the AI Concierge. You can use it to define how the AI should respond or behave in specific situations.

Within an additional prompt, you can also:

  • use Member Properties such as #Vorname

  • include Agent Actions such as @Support-Anfrage


Conditions for Additional Prompts

You can also define conditions for each additional prompt.

This lets you specify when a prompt should be active. For example, you can use this to control the AI Concierge:

  • only for specific courses

  • only for specific user groups

  • depending on progress or access

This allows you to flexibly determine which instructions should be considered in each situation.


Categories in Detail

1. Communication Style

In the Communication Style category, you define how the AI Concierge communicates with your members.

This category helps keep the AI's general writing style and behavior consistent.

For example, you can specify whether the AI should respond in a casual, friendly, direct, or particularly professional manner.

2. Limitations

In the Limitations category, you define what the AI Concierge should not do.

This allows you to define clear boundaries and guidelines for the AI.

Typical examples include:

  • not addressing certain topics

  • not providing recommendations outside the platform context

  • not responding to sensitive content

This ensures that the AI Concierge only operates within the parameters you define.

3. Escalations

In the Escalations category, you define when a request should be escalated.

This is particularly helpful when the AI Concierge reaches a point where an automated response is no longer sufficient.

Typical use cases include:

  • a member is dissatisfied

  • a support request arises

  • a question cannot be answered

In this category, you can use Agent Actions to:

  • notify team members

  • trigger external processes through Zapier or Make

This ensures that important situations are not overlooked and can be addressed in time.


If you have any further questions, please contact our support team through the Help Center in the bottom left. We usually respond within 5 minutes on business days between 09:00 and 17:00.

Did this answer your question?