This feature is in beta state - if you experience any issues or would like to share feedback, please contact your CSM.
The UltimateGPT (uGPT) block, by default, utilises the last visitor message as a prompt for searching the knowledge source and delivering an answer whenever the UltimateGPT system reply is triggered within a conversation.
However, this default behaviour has limitations. Frequently, questions that can be answered with a knowledge source article are found in the middle of a conversation or within a specific Intent, and the last visitor's message may lack the necessary original context. This results in the uGPT being unable to provide an accurate response.
To enhance the capabilities of the uGPT block and enable its use within pre-defined Intents, Ultimate introduced the Custom Question field within the Details section of the uGPT block in the Dialogue Builder. This feature allows for the specification of a custom question or prompt, ensuring more accurate and contextually relevant responses, even when the original context is not readily available in the last visitor message.
The Custom Question feature empowers you to incorporate context from previous messages, including intents, specific user inputs, session parameters, and more. This enables uGPT to provide more precise and contextually relevant responses, even when the original context is not readily available in the last visitor message.
Custom Question Examples
In this example, we illustrate how to effectively utilise the Custom Question feature in the context when a specific Intent is triggered:
1. Triggering the Intent Reply: Sizing Enquiries
The Intent Reply "Sizing Enquiries" is triggered when visitors inquire about their shoe size.
2. Dialogue Design
Within the dialogue, the AI agent engages with visitors in the following manner:
- The AI agent requests the visitor's foot length in centimetres.
- It inquires about the preferred location for receiving shoe size information, which can be UK, US, or EU.
3. Session Parameter Collection
Visitor inputs, such as foot length in centimetres and chosen location, are collected and stored as session parameters: {{foot_lenght_cm}} and {{location}}.
4. Configuring the Custom Question in uGPT Block
To harness the potential of the Custom Question feature, the bot builder sets up the Custom Question within the uGPT block. In this instance, the question posed is: "Which shoe size would you recommend based on my {{foot_lenght_cm}} and my {{location}}?"
5. Testing the Custom Question
During testing, the uGPT's response utilises the Custom Question as the prompt instead of relying solely on the last visitor message - "US" as shown above. The uGPT uses the Custom Question to search the knowledge source and deliver an accurate answer to the visitor's sizing inquiry based on the session parameters shared.
This example demonstrates how the Custom Question feature empowers the AI agent to provide context-aware responses, enhancing the user experience in pre-defined Intents.
