This section of the user guide is focused on Automatic Content Generation. To help you navigate the article we have broken it down into the following sections:
- What is the Automatic Content Generation Feature?
- Who has access to Turn on Automatic Content Generation?
- How do I turn on Automatic Content Generation?
- How does Automatic Content Generation work?
- How does Automatic Content Generation create responses?
- How do I know which questions were answered with Automatic Content Generation?
- How can I test the Automatic Content Generation feature before turning it on?
What is the Automatic Content Generation Feature?
Automatic Content Generation provides new generative AI auto content generation technology if turned on for the chatbot. When turned on it is globally used by the chatbot. When a user asks a question that is not already in the chatbot's knowledge base, generative AI uses harvested spider data to automatically generate a response "on the fly" and presents the response in the chatbot. When turned on, Automatic Content Generation will be used for texting as well.
Who has access to Turn on Automatic Content Generation?
The feature is available to individuals with the following permissions:
For more information on user permissions, review the User Roles & Permissions article.
How do I turn on Automatic Content Generation?
1. Under the Chatbot selection, select Behavior Settings.
2. Select the Edit icon on the top right
3. Select Status On for Automatic Content Generation and then select Save
How does Automatic Content Generation work?
When a user asks the chatbot a question, the system will initially look for a response in the knowledge base. If no matches are found, then content will be automatically generated if possible. There can be several outcomes to the use of Automatic Content Generation:
- Automatic Content Generation finds a response from the spidered content and provides a response.
- If there are not enough matches in the spidered content to provide a response, then the chatbot will provide an IDK as the response.
- If the question asked is considered to be toxic, the chatbot will decline to answer the question and respond with "I'm here to provide helpful and respectful information. If you have any other questions, feel free to ask, and I'll do my best to help."
How does Automatic Content Generation create responses?
The following steps are used to create a response using Automatic Content Generation once the user inputs a question (query):
The raw query is analyzed using ChatGPT to internally generate multiple search queries
Relevant content is retrieved from the Knowledge Sources database
The relevant content is reranked.
The ranked relevant content is sent to ChatGPT along with the original query to generate a response
How do I know which questions were answered with Automatic Content Generation?
Automatic Content Generation responses will not be saved in the knowledge base but will be retained and logged as "Generative AI" responses and marked with a GenAI" badge. To find interactions that used Automatic Content Generation access the interactions in the client admin.
For information on how to view Interactions, review the Chatbot Transcripts & Interactions articles.
How can I test the Automatic Content Generation feature before turning it on?
The Content Generator tool uses the same underlying function as Automatic Content Generation to generate the response when you have the “Use only Spider content” option selected while managing your content. Therefore, once you have your spiders set up you can test generating responses using the Content Generator tool since that tool will produce the same response as if the user asked the question in the chatbot and ACG kicked in.
For more information about how the content generator tool uses spidered content to generate responses, review the Content Generator section of the Creating a Knowledge Base Response article.
Was this article helpful?
That’s Great!
Thank you for your feedback
Sorry! We couldn't be helpful
Thank you for your feedback
Feedback sent
We appreciate your effort and will try to fix the article