Human Support Escalation
As powerful as AI chatbots can be, sometimes human accountability and expertise is still needed. GPT-trainer’s built-in human support escalation feature allows you or your collaborators to step in during any ongoing chat session and take over the conversation.
Set Up Human Escalation Agent
Under our multi-Agent framework, the human support Agent operates under the same principle as any other Agent, except that it does not generate responses through an LLM but instead routes the user’s query to a human. To activate the human support escalation feature, go to “AI Agents” tab, then click “Create new agent” button. Find the “Human Escalation” Agent and click “Choose template”. You may need to scroll down to find it.
Then, click on the Human Escalation Agent. You have the ability to configure the conditions under which human support agent should be connected. By default, the chatbot user must explicitly request for human agent assistance. You can also modify the pre-canned messages to display accompanying different scenarios.
Once you are comfortable with the settings, connect the Agent.
To test your human support escalation setup, you’ll need to generate a public link to the chatbot and access it using another browser tab. The built-in “Preview” tab does NOT support human escalation testing.
Go to “Deploy / Integrations” tab, click “Share”. You may need to change your chatbot visibility settings temporarily in order to generate the link.
Once you have the link, open a new browser tab and navigate to it. Do not close the original gpt-trainer tab. You should be taken to the chatbot as a typical user. You can then test it by submitting queries requesting human support.
To take over as a human agent, head over to “Inbox” in your gpt-trainer browser tab. You should see an orange dot next to the session requesting human support. Click it and you will be able to engage directly with the user. Simply start typing a response in the chat input text box at the bottom of the chat log.
As soon as you send the first message, AI Supervisor and all AI Agents will be disabled. You can have a direct conversation with your user for as long as you’d like. Once you are done, you can end the live chat session and put your user back on to the AI chatbot by clicking “End Live Chat”.
You may stay and continue to monitor the user’s interaction with the chatbot as the AI regains control over response generation.
Depending on your use case, you may wish to fine tune the circumstances when the user should be redirected to a human agent. To do so, please review our documentation on Fine Tuning Agent Intents.
Enabled Human Support Notifications
Our Human Escalation Agent provides essential notifications, ensuring prompt assistance when your users request support. These notifications enable you to address queries swiftly, enhancing user satisfaction and operational efficiency. However, to make these notifications work seamlessly, certain steps need to be followed.
Access Human Escalation Agent Settings
- Navigate to Settings: Enter your Human Escalation Agent settings.
- Enable Human Escalation Notifications: This ensures that notifications related to user support requests are activated.
- Notification Sound: Activate this option if you wish to receive an audible alert along with the notifications.
- Save Changes: This ensures that your preferences are applied and notifications are set up according to your selections.
Browser Permissions
Each web browser manages permissions for notifications and sounds on a per-website basis. To ensure that you receive notifications properly, you’ll need to enable both permissions within your browser settings. To proceed forward:
- Launch your browser where you will use GPT-trainer platform.
- Enable your browser permissions by choosing option bellow:
Operating System Permissions
Operating systems also have their own permissions that allow setting restrictions to notifications for different apps, including browsers. To enable notifications, choose your operating system below:
