You now have the option with Global No Match in your Assistant to choose generative or static responses. You can modify by going to your Settings (gear icon on the bottom of the lefthand panel, when inside your project), and selecting the 'Edit' button beside 'Global No Match' under 'Global Logic'. A generative Global No Match means that if the question hits the fallback (meaning no relevant Intents or Knowledge Base content was found), the question will be answered by a general AI. A static Global No Match means your Assistant will respond with a message you define every time (ie. I'm sorry, I don't have an answer for that. Is there something else I can answer for you?).
Static Global No Match
Static Global No Match gives you complete control for when your Assistant cannot answer the user's question via defined Intents or Knowledge Base content-match. If you want to stop your Assistant from providing responses outside of your defined Intents and Knowledge Base, use static.
Generative Global No Match
Generative Global No Match allows Voiceflow's AI Assist to take over the conversation and generate responses when the user's question fails to match to one of your Intents or the Knowledge Base.
Generative Global 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.
To modify how answers are generated from AI, you can use the following configurations:
- Model - This is the model that will be used to created your prompt completion. Each model has it's own strengths and weaknesses, so be sure to select the one that is best for your task:
- GPT-3 DaVinci - most stable performance, best suited for simpler functions
- GPT-3.5-Turbo - fast results, average performance on reasoning and conciseness
- GPT-4 - most advanced reasoning and conciseness, slower results
- Claude V1 - consistently fast results, moderate reasoning performance
- Claude Instant V1 - fastest results, best suited for simpler functions
- Temperature - This will allow you to influence how much variation your responses will have from the prompt. Higher temperature will result in more variability in your responses. Lower temperature will result in responses that directly address the prompt, providing more exact answers. If you want 'more' exact responses, turn down your temperature.
- Max Tokens - This sets the total number of tokens you want to use when completing your prompt. The max number of tokens available per response is 512, (we include your prompt and settings on top of that). Greater max tokens means more risk of longer response latency.
- System - This is the instruction you can give to the LLM model to frame how it should behave. Giving the model a 'job' will help it provide a more contextual answer. Here you can also define response length, structure, personality, tone, and/or response language. System instructions get combined with the question/prompt, so be sure they don't contradict.
Generative Global No Match generated responses
When Prototyping in Voiceflow, or viewing Transcripts, responses that fall to your Generative Global No Match will be marked with the Ai Assist icon.
Note: Users will not see the Ai Assist icon when your Assistant is live.
How Generative Global No Match responses are generated
Generative Global 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.