GenAI Prompts

NiCE CXone GenAI Prompts lets you customize and manage generative AIClosed Artificial intelligence (AI) technology that generates new content based on user prompts. Follows patterns and structures learned from training data. prompts for NiCE CXone products that utilize them. Once you have customized a prompt, you can add transcripts, summaries, or articles to test the prompt against. GenAI Prompts gives you better control over the content and format of the AI-generated responses and improves the large language model (LLMClosed Large Language Model. A type of AI that processes, understands, and generates human language based on context.) response.

GenAI Prompts currently lets you customize the following prompts: 

Key Facts About GenAI Prompts

  • GenAI Prompts is available for all systems but you can only create prompt profiles for the products and features you have enabled.

  • A new, unpublished profile is only accessible to the user who created it. Once it's been published, it shows a version number and is available both for other users to see and for selection in the related NiCE CXone product.

  • When you make changes to a new or existing prompt profile without publishing the changes, those changes are saved for up to 30 days from the last time you edited it. Only you can see those changes. After 30 days:

    • Changes to a new profile revert to the default settings.

    • Changes to an existing profile revert to the most recently published settings.

  • You can use AI Assist within a prompt profile to refine the profile's instructions so the generated output matches an example you provide. For more information, see

  • The icon next to a prompt profile indicates its current status.

    • Icon: Orange notepad with writing: The profile is a new draft that hasn't been published yet.

    • Icon: Green check mark wtih a circle around it: The profile is published with no pending changes from you.

    • Icon: Purple notepad with writing on it and a circle with an arrow in the corner: The profile is reverted to an earlier version that isn't the currently published one.

    • Icon: A blue check mark with a circle around it ending in an arrow: The profile has been published but has pending, unpublished changes.

  • The Prompt Template pane at the top of the prompt profile shows where the profile settings, like tone and length, fit into the prompt. You can click the links in the prompt template to be taken directly to the setting that populates it.

  • All users can now open the LLM Model dropdown. Users with an Prompt Editor Advanced license can select any model in the list; other users are limited to standard models. The list itself is grouped by standard and premium models, with models verified by NiCE CXone shown first and the rest listed alphabetically.

    If the LLM model currently selected for a profile is scheduled for retirement, NiCE CXone displays a warning next to the LLM Model dropdown stating that the model will retire in a set number of days and prompting you to update to a supported model.

    When a model you use is closer to its retirement date, NiCE CXone also displays an LLM Update dialog when you open the affected profile. The dialog states the date the model switches to retention mode, after which the model is no longer accessible, and reminds you to update the LLM and test and publish all affected profiles before that date. Select Don't show this message again to suppress the dialog for that profile, or click OK to close it.

    This table shows the LLMs you can choose from, along with a rating from 1-10 for the speed, accuracy, complexity handling, and hallucination resistance. 1 is always the lowest and 10 is always the highest score. A high score is desirable for speed, accuracy, and complexity handling, but not for cost and hallucination resistance.

    This table lists only the LLM models that NiCE CXone has verified for this use case. The LLM Model dropdown in the application may show additional models that have not yet been verified by NiCE CXone; in the dropdown, an icon next to a model indicates it has been verified by NiCE CXone. You can select any listed model, but if you choose one that isn't in this table, testing that model for your specific use case is your responsibility.

    LLM Model Speed Accuracy Complexity Handling Hallucination resistance notes
    Nova Micro 10 6 5 6 Lightweight, low latency; limited reasoning.

    Nova Lite

    9

    		 7 6 7 Higher intelligence than Micro; still lightweight and fast.
    Nova Pro 8 8 8 8 Good balance of intelligence, reasoning, and speed.
    Claude 4.5 Haiku 8 8 7 8 Strong accuracy and reasoning; suitable for efficiency-focused use cases.
    Claude 4.5 Sonnet 7 9 9 9 Flagship-level intelligence and reasoning.
    Claude 3 Haiku (Deprecated) 8 7 6 7 Reliable and efficient for its time. Included for consistency, but other models are likely a better choice for modern applications.
    Claude 3.5 Haiku (Deprecated) 8 8 7 8 Strong accuracy and reasoning; suitable for efficiency-focused use cases.
    Claude 3.5 V2 Sonnet (Deprecated) 7 9 9 9 Flagship-level intelligence and reasoning.