ambitious-aqua
ambitious-aqua2y ago

I don't understand Intents.

Hi, my intents are not getting triggered even though I have used specific utterances to trigger them. They were working last night when I finished configuring the chatbot but this morning it stopped working, is there any reasoning for this?
1 Reply
Tico | Voiceflow Assistant
Intents in Voiceflow represent specific actions or requests that a user wants to perform or receive. They are defined as triggers that initiate a particular conversational flow or action. These intents are linked to specific phrases or commands, known as utterances, that a user might say. For example, if an intent was to "Create New Ticket", you might add multiple utterances, like "I want to create a new ticket" or "I need to open a request", that point to the same intent. The more utterances you have, the better the Natural Language Understanding (NLU) will be at recognizing user responses as intents. If your intents are not getting triggered, it could be due to a few reasons. One possibility is that changes were made to the intents, such as the confidence score, last editor, or updates. Another possibility is that the specific utterances used to trigger the intents are no longer valid or recognized by the AI. It's also important to routinely test and analyze confidence levels to ensure that the intents accurately capture user queries. In Voiceflow, you can also add required entities to an intent if it requires specific information. For example, if the intent is for users looking to book an appointment, you can add entities like "date," "time," or "service type." Under 'Utterances,' you can type in examples of what users might say to trigger this intent, e.g., "I want to schedule a meeting," "Can I book a time for a call?" Remember, managing intents and utterances effectively is crucial for the performance of your chatbot. It allows users to converse with the assistant as if they are talking to a real person, and Voiceflow's NLU-powered assistant will utilize both Large Language Technology and NLU capabilities to contextualize freeform text responses and map them to assistant-recognized user intents.

Did you find this page helpful?