UltimateGPT (uGPT) is activated through the utilization of the UGPT block within our dialogue builder. The input for this process comprises the latest visitor message and various configuration settings. Depending on the specific scenario triggered by the UGPT block, the conversation will progress either with a generated UGPT response or by following the predefined dialogues associated with other scenarios.

In this article, we will cover:

  • Using the uGPT block
    • Response generated
    • Escalation required
    • Not understood
    • Error occurred

Every individual uGPT AI agent comes preconfigured with a uGPT block in the uGPT system reply setup. Additionally, uGPT can be added to any other intent or template reply by simply selecting the uGPT block from the block menu.:

Currently, the uGPT block serves a singular purpose: "Respond with informational content." However, our future plans include expanding its capabilities to encompass additional uGPT-related tasks.

Using the uGPT block

Bot builders have the flexibility to utilize actions and resolution states similar to other blocks. Apart from the four scenarios detailed below, the uGPT block provides various configuration options that allow specifying the context uGPT should consider when generating a response. The forthcoming sections will provide a detailed explanation of all the scenarios and configuration options available.

Response generated

This scenario is activated when uGPT successfully generates a response to the question posed in the latest visitor message, considering both the context provided by the knowledge base and the specific query. However, if the last visitor's message is more of small talk rather than a question, uGPT attempts to provide a response solely based on that particular message.

In the dialogue design, there are two distinct options available for sharing or incorporating the uGPT-generated response. These options offer flexibility in how the response can be integrated into the ongoing conversation.

Option Explanation Example
Share with visitor

By choosing this option, the AI agent will immediately send the generated response to the chat without requiring any other blocks in the reply. This is the recommended method for sharing the uGPT response directly with the visitor. 


However, it's worth noting that we also retain the response in the session parameter "ugptResponse", allowing it to be utilized in actions or at a later point in the conversation. This ensures flexibility and potential applications beyond the immediate chat interaction.
Only save response

Opting for the second option involves not sending the response directly to the chat. Instead, the response is saved solely in the session parameter "ugptResponse." The primary purpose of this option is to enable the continuation of the dialogue with other blocks and logic. Later on, the response can be sent to the chat using a bot message block along with the session parameter.


This approach also offers the flexibility to save the potential response internally for testing or evaluation purposes, while still allowing the conversation to progress without sending the response to the visitor immediately.

In addition to the "ugptResponse" session parameter, we also provide access to the articles sourced from the knowledge base used as context for the generated response through the "dataSources" session parameter. Users can retrieve information from up to five articles using this parameter. 

Escalation required

The escalation required scenario is activated when UltimateGPT identifies that the visitor's intention is to speak with a human rather than posing a question or engaging in small talk. In such instances, we promptly trigger the scenario and guide the conversation along the pre-designed dialogue path.
Just like the "response generated" scenario, the “escalation required” scenario also continues within the same reply. To handle this scenario effectively, the bot builder needs to continue the dialogue by incorporating further blocks. This may involve linking to another reply or adding an escalation block to save the response.

Not understood

The uGPT block includes two additional scenarios that are activated when uGPT fails to generate a response. By default, both scenarios are directly linked to their respective system replies. The first scenario is called the "not understood" scenario, which is directly linked to the "default reply."

The "not understood" scenario comes into play when uGPT is unable to find relevant articles or data to generate a response. However, bot builders have the flexibility to toggle off the direct linking to the "default reply" if they wish to continue the dialogue in such situations.

Error occurred

The second scenario that may be activated when uGPT fails is the "error occurred" scenario. This occurs when uGPT is either unreachable, returns an error, or encounters another issue within the system. By default, this scenario is directly linked to the "Technical error reply." However, similar to the "not understood" scenario, the dialogue can be continued by disabling the fallback option in the block drawer.

It's essential to note that only in the "response generated" scenario, the uGPT response and used articles are saved to the underlying session parameters. Whenever a new uGPT block and the "response generated" scenario are successfully triggered, the content of these session parameters gets overwritten. This ensures that the most recent response is always captured for future use

Referencing knowledge base articles

One of the parameters that is returned with the uGPT block is dataSources which can be used to show the articles used to form the response so users can dive further into details outside the chat. These can be included in carousels to make the experience more visual. To do this, follow the below instructions.

  1. Add a Conditional Block
  2. In the conditional block, set the variable ugptClassifiedTask
  3. As a condition, set the operator to IS and include the valuequestion answering to cover questions the End User might have with your knowledge base or even when the End User inputs any small talk.
  4. Create a Bot Message as a Fallback to the Conditional Block
  5. Add a Carousel Node
  6. Convert it to a dynamic carrousel by going to the block details drawer and pressing the Convert To Dynamic Carousel button
  7. Add the dynamic content as dataSources
  8. Customize the template card and button using the parameters %title and %url for the respective fields
  9. Remove the fallback toggle.
    The template card button with an external link in a Dynamic Carousel is expected to be the last interaction of the End User with the bot. Instead of clicking the links, when anything is typed below, it triggers the fallback. By turning off the Fallback button it will restart the conversation when the user asks another question. 
    Correto.gif

Using Custom Questions

When editing the UltimateGPT node, you can define a Custom Question. The Custom Question will overwrite the visitor's last message, like a button push, allowing you to provide contextually relevant answers. The field also allows you to use parameters to include information about the user to make a question more relevant, like their subscription status or tier.

uGPT for Ticket AI Agents (EAP)

uGPT is fully available for chat AI agents. Starting on October 9, 2024, uGPT is also available in an early access program (EAP) for ticket (email) AI agents. This functionality is known as generative replies for email.

Outside of the following exceptions, the uGPT functionality described in the rest of this article is identical between chat and ticket AI agents:

  • AI-generated responses require additional language for ticket AI agents. For ticket AI agents, you must write additional response text to couch the AI agent’s reply. This behavior is different from uGPT for chat AI agents, where a default AI response is sent on its own. The screenshot below shows an example response for a ticket AI agent.
  • No escalation options for ticket AI agents. A uGPT block in a dialogue for a ticket AI agent doesn’t have an escalation option like it does for a chat AI agent. The screenshot below shows dialogue build for a ticket AI agent with a Fallback node instead of an Escalation required node. The Fallback node is how you address scenarios where uGPT isn’t able to answer the customer’s question.

Powered by Zendesk