Do I have to add questions to my bot's Understandings?
Adding Organization Questions is by no means required! Org Questions are an entirely optional tool that provide an added layer of customization to your bot's Knowledge Base, enabling it to better understand questions specific to your institution. You can add as many or as few questions as you'd like. Our AI is built to work off of the Questions alone, and any additional edits will only function to make your bot more precise in its ability to answer incoming messages.
Does a question have to be present in an Understanding verbatim for my bot to be able to identify it?
No! Good thing, because that would be a lot of questions.
leverages AI to match incoming messages to the best response from the Knowledge Base. Simply put, your bot's AI uses a complex set of processes to compare each incoming message to every Understanding in its Knowledge Base, and identify the ones that are closest in meaning to the incoming message. If it's confident enough in its comparison, your bot will deliver an answer if one has been approved for the Understanding.
Where do Questions come from?
There are thousands and thousands of Questions throughout the Knowledge Base which have been generated over time by the knowledge building team. When an incoming message does not match properly to an Understanding, it is often reviewed and added to the question collection that is the best match for the understanding in order to better match to similar messages in the future.
To learn more about how the AI works in this blog post. 's chatbots, check out
Why is there a question that does not match with the Summary Question in an Understanding?
In some cases, a question is added that does not align with the intent of the summary question, or a question is not generalized to be universally-applicable before it is added.
If you come across an understanding that does not belong within an understanding, or one that contains names or references irrelevant to your institution, deactivate it by clicking the toggle next to the question. Your bot will immediately stop using that understanding in its Knowledge Base. It will also be a signal to theteam that one of the questions in our Question Collection does not belong there.
The AI that powers your bot is built to handle some out-of-place data. It considers each Understanding holistically, and the thousands of question synonyms throughout the Knowledge Base provide a cushion for individual questions that might end up in the wrong Understanding.
Why do some of theQuestions contain words beginning with an "@" symbol?
Questions occasionally include words beginning with an “@” symbol, like @college or @orientation, which are generic representations of an institution’s information and naming conventions. These allow the Questions to be applied across different bots’ Knowledge Bases.
Article is closed for comments.