Describe use cases for Generative AI bots
As mentioned previously, generative answers are a popular topic right now. Generative AI enables organizations to be able to provide more natural conversations to their customers. Generative answers in Copilot Studio allow your copilot to find and present information from multiple sources, internal or external, without created topics. Generative answers can be used as primary information sources or as an alternative source when authored topics can't answer a user's query. As a result, you can quickly create and deploy a functional copilot. You don't need to manually author multiple topics that might not address all customer questions.
When a copilot can't find a matching intent (topic) for the user's query, it can use generative answers and tries to answer a question. This behavior is called "Generative Answers for fallback." If the user's intent isn't matched to topics or generative answers, the fallback system topic is used. System topics can escalate a query for the copilot.
Another advantage to using generative AI is that the context of what the user is asking is remembered. For example, we're using MSLearn as a knowledge source. When a user asks Copilot “What does the IF function in Excel do?”, it looks through MS Learn and provides an answer. If you then ask it “Can you provide me with an example?”, it understands that you're still referring to the IF function and provides you with a contextual answer.
