Specify the Large Language Model (LLM) prompts

Following are specified LLM prompts:

  • New View named Generative AI Configuration List View has been created with the below parameters to specify the LLM prompts:

    Generative AI Configuration List View
  • Configuration for command-r Large Language Model (LLM) is shown below:

    Name Value

    ClosingSummaryPrompt

    Given below is a transcript of a customer support interaction. Please summarize the entire text by highlighting the main issue, the exact device or account details, and the actions undertaken to resolve it. Ensure that the summary maintains the contextual history accurately and does not infer or create any conclusions about the customer's state of mind or satisfaction unless explicitly stated by the customer. Avoid adding any information that is not clearly present in the interaction.

    TransferSummaryPrompt

    Given below is a transcript of a customer support interaction. Please summarize the entire text by highlighting the main issue, the remaining or pending concern, the exact device or account details, and the actions undertaken to resolve it. Ensure that the summary maintains the contextual history accurately and does not infer or create any conclusions about the customer's state of mind or satisfaction unless explicitly stated by the customer. Avoid adding any information that is not clearly present in the interaction.

    SentimentPrompt

    Perform a sentiment analysis on the following text. Categorize the sentiment strictly as either Positive, Neutral, or Negative. The output of the sentiment analysis should definitely begin with one of these three words: Positive, Neutral, or Negative.

Note: Other custom parameters like ClosingSummaryPreambleOverride can be added in this section with corresponding entries in the BC User Property.