Learn about Generative No Match

Overview

Generative No Match allows Voiceflow's AI Assist to take over the conversation and generate responses when the user fails to invoke one of your Assistants known Intents. 

Generative No Match is an experimental feature leveraging Large Language Models (LLMs) and should not be used in production use cases for business critical applications because of its tendency to generate false information. See more below.

Meaning, if the user gives an Utterance that does not match with an Intent in your Assistant, AI Freestyle will generate a response to the user if Freestyle is turned on.

Turn Generative No Match On/Off

Generative No Match can be turned on and off in the settings tab under the AI Assistant tab.

Generative No Match generated responses

When Prototyping in Voiceflow, or viewing Transcripts, responses generated by Generative No Match will be marked with the Ai Assist icon. 

Users will not see the Ai Assist icon when your Assistant is live.

How Generative No Match responses are generated

Generative No Match responses are generated using an LLM (Large Language Model) which is an AI model that is able to understand conversation context and generate new responses. LLMs like Generative No Match are often unable to know truth from falsehood, and have a tendency to generate false responses. This is because LLMs are AI's trained on the corpus of knowledge on the internet, but are not familiar with your specific Assistant's context.

Generative No Match is still an experimental feature for this reason and is not recommended to be used for serious production use cases.