---
sourceDocument: Australia Conversational Interfaces
sourceDocumentLink: https://servicenow-prod.fluidtopics.net/r/de-DE/conversational-interfaces

 Release :

    - australia

ft:locale :

    - de-DE

ft:publication_title :

    - Australia Conversational Interfaces

ft:clusterId :

    - convint

bundleId :

    - convint

workflow :

    - Platform


---

# LLM Text bot response control

# LLM Text bot response control {#ariaid-title1}

* Freigeben Version: Australia
* 
* Aktualisiert 12. März 2026
* 
* ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 1 Minute Lesedauer

Use this control to write a prompt description that will dynamically create an output message to the user in conversations that use large language model (LLM) topic discovery.

## LLM Text bot response control properties {#va-ai-response__section_wtz_xg3_41c}

The Text bot response is available on the palette when you work with topics that use LLM topic discovery.  
{#va-ai-response__table_m2v_xmj_h1c__entry__2}

| Property | Description |
|-|-|
| Node name | Name that identifies this LLM Text bot response control node in the topic flow. |
| Tell the LLM how to respond | What sort of message you want the LLM to send to the user. For example, <kbd class="ph userinput">Greet the user in a friendly, professional manner</kbd>. You can create messages using plain text, scripts, or conditions defined with the data pill picker. |
| Advanced ||
| Hide this node ||
| Conditionally show this node if | No-code condition statement or low-code script that specifies a condition for presenting this node in the conversation. The condition must evaluate to true. |
[ ]

{#va-ai-response__table_m2v_xmj_h1c}

## Example Text bot response control {#va-ai-response__section_s5f_csj_dxb}