When you start a brand new project, the machine learning model behind the AI text generation is pretty basic, and mostly based on the general knowledge domain. To make it more specific and tailored to your business, you'll need to add some context first, and then fine-tune the model on actual conversations that your human agents will be doing.
How to set the initial context
To set the initial context, open the "Settings - Integrations" menu and click the "OpenAI" settings tab. The settings are pretty self-explanatory and you can set the context in plain natural language (see the example below).
Setting the context for AI-based live chat automation
You should provide a general description of the context of the conversations, and then provide 1 to 3 example questions (with suggested responses) that your customers may ask.
The "temperature" setting affects the flexibility of the model (the higher the temperature, the more improvisational the model becomes), and you can also adjust the maximum suggestion length.
How to fine-tune the model
Once the initial context is set, the learning process starts. Your virtual assistant will be using the conversations done by your human agents to fine-tune itself, and you will notice the change quite soon. On average, it takes 100 to 1000 live chat sessions to get enough data for the model so that it will be able to provide meaningful responses.
We can also help you with the fine-tuning process by custom-analyzing your data and suggesting the fine-tuning mechanics. Just ping us at [email protected] with your account details, and we'll build a custom fine-tuned AI model for your customer service and live chat automation needs.