AI Detection

This action will forward any user text to an existing AI trained assistant. The conversation will not hold and will continue with all other actions.

Settings

The action uses the following settings:

Setting	Description	Parsed
Prompt	The prompt forwarded to the AI provider	✅
Auto-Generate Content	If enabled, Xenioo will automatically generate any required bubble to display the AI reply	⛔
Split Paragraphs	If enabled, Xenioo will follow the AI reply line break to generate multiple bubbles	⛔
Can Bypass Input State	Enabling this option will allow the automatic activation to override any currently blocking input and activate the associated flow.	⛔
React to User Comments	Enable or Disable real-time Facebook post integration.	⛔
Specific Post Id	If enabled, Xenioo will follow the AI reply line break to generate multiple bubbles	✅

Remarks

The user_prompt variable will be set to the value of the current user text. You can use the prompt field to add additional information to each user text so that AI reply is more detailed and related to the context of the current conversation.

If Auto-Generate content flag is enabled, the AI reply is returned to the chat directly. If you want to take control of the answer disable the Auto-Generate flag and use the ai_reply_content variable to access the text.

If Split Paragraphs is selected, the returned text will be automatically split into multiple bubbles. If Auto-Generate content is enabled, the Split Paragraph flag will have no effect.

AI exchanges will be kept in a thread so that users can ask follow up questions and refine the results with additional information. Clear the ai_conversation_thread content to reset the current thread information and start a new thread.

Depending on the type of model and the specific AI provider selected it might take several seconds for the service to produce a complete answer.

Trigger

On Reply Received. This action will trigger any child operation as soon as the result is available. This trigger will not be executed if the "Auto-Generate Content" flag is enabled.

Variables

This action produces the following variables after being triggered:

Variable	Description
ai_conversation_thread	The thread id of the current conversation
ai_reply_content	The raw JSON reply of the last request

Availability

Channel specific availability follows the table below:

Channel	Availability
Facebook	Fully Available.
WhatsApp	Fully Available.
Telegram	Fully Available.
Web	Fully Available.
Alexa	Not Available. Out of AI Detection is not supported inside skills.
Google Assistant	Fully Available.
Slack	Fully Available.
API	Fully Available.

This action can be used only at Bot Global level or Behavior level.