Configure AI Prompt for Copilot for Agents KB Answers

You can use NiCE CXone GenAI Prompts to control the prompt that Copilot for Agents uses to create a KB answer. This lets you control the language, tone, and length of the KB answer. Once you have completed your prompt configuration, you can manually enter articles to test the settings against. If you are not satisfied with the response generated in the test, you can continue to refine your settings until you are satisfied. After that, you can publish the prompt to make it available for selection within the Copilot for Agents profile on the Copilot for Agents Config page.

• All users can now open the LLM list. Which models you can select depends on your organization's licensing. The list itself is grouped by standard and premium models, with models verified by NiCE CXone shown first and the rest listed alphabetically.

• If you do not have the Prompt Editor Advanced license, premium models appear in the list but you cannot select them.

• To see which models are premium, open the LLM Manager.

• Premium models are billed based on usage. Your organization is charged for the number of tokens the model reads and writes when a prompt runs. To use premium models, your organization needs the LLM consumption item on its contract. Contact your NiCE CXone Account Representative for pricing.

• NiCE Default is available as an LLM option. It is the model that NiCE CXone sets for that specific prompt type. If a prompt template only supports one model, NiCE Default is the only option shown and the LLM list is disabled. If a template supports multiple models, NiCE Default appears alongside them as a selectable choice.

• If the LLM currently selected for a profile is scheduled for retirement, NiCE CXone displays a warning next to the LLM list 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.

• If a model reaches its retirement date and you have not selected a different model, NiCE CXone automatically switches the profile to NiCE Default. Test and publish the profile after this switch to confirm the output still meets your requirements.

Launch GenAI Prompts

1. Click the app selector .

2. Under General, select AI Studio.

3. In the AI Studio left navigation, select GenAI Prompts.

Create Prompt Profile

Required permissions: GenAI Prompts, Prompt Access Edit

You will also need a license for NiCE CXone Copilot for Agents and the KB answers feature enabled.

Each flow comes with one default profile. You can create a custom prompt profile either by using a blank form or by copying an existing prompt and making edits. As you're working in the profile, it automatically saves for you only. Others cannot see the new profile, or edits you're making to an existing profile, until you click Publish Prompt. Profiles are also unavailable to select as the live prompt until they have been published.

1. In the Profiles tree expand Copilot for Agents > KB Answer.

2. Create a new profile. You can do this in one of two ways: 

   1. Create a new, blank profile. To do so, click the plus icon next to the AutoSummary group. The new profile appears at the bottom of the list.

   2. Duplicate an existing profile.  

      1. Click the stacked dots icon next to the existing profile you want to copy and select Duplicate.

      2. Rename the copy by locating it at the bottom of the AutoSummary profiles, clicking the stacked dots icon , and selecting Rename. Enter the new name for the profile and click the check mark to save it.

3. On the Prompt Configuration tab, adjust the values for these fields as needed:

   • Who is the persona?

   • What is the language of the summary?

   • What is the tone of the summary?

   • What are the instructions for the summary?

   • What is the max length of the summary? 

   Learn more about fields in this step

   Field	Details
   Who is the persona?	A description of the persona you want AI to take on as it generates the summary.
   What is the language of the summary?	The language the summary appears in. You can choose between these options:  English Portuguese This field only impacts the language of the generated content.
   What is the tone of the summary?	The tone of the summary between these options: Formal Informal Casual
   What are the instructions for the summary	The information you want the summary to include and the format you want it in. Important: The What is the language of the summary? field only affects the language of the generated summary. You must enter these instructions in English.
   What is the max length for the summary?	The maximum length of the summary between these options:  Short (1 - 50) words Medium (51 - 100) words Long (101 - 200) words Extra Long (201 - 250) words Extended (251 - 500) words Large language models attempt to follow the selected maximum length, but the generated summary may be slightly longer or shorter than the requested range. This can be more noticeable for shorter lengths. For more information, see About GenAI Prompts response length behavior.

4. Click Publish Prompt.

GenAI Prompts Field Length Limits

GenAI Prompts fields support two types of text inputs. Each type has a defined maximum length.

field type	Maximum length
Free text fields (for example, labels, persona descriptions)	200 characters
Text area fields (for example, instructions, long prompts)	10,000 characters

The type of field used depends on the prompt configuration.

• Free text fields are used for short inputs such as:

  • Agent label

  • Customer label

  • Persona description

• Text area fields are used for longer inputs such as:

  • Instructions

  • Custom prompts

GenAI Prompts dynamically displays the appropriate field type based on the prompt configuration.

Add Queries for Testing

Required permissions: GenAI Prompts, Prompt Access Edit

All articles you add to the table are included in the test response.

1. Click the Queries tab.

2. Enter the KB ID of the knowledge base you want to use for generating query responses.

3. Click the add + button next to the Query text box to add queries.

Use Variables in Copilot Prompts

Required permissions: GenAI Prompts, Prompt Access Edit

Use variables to define dynamic values that your prompt can reference at runtime.

1. Click the Variables tab next to Prompt Configuration and Queries.

2. On the Variables tab, click Add.

3. In the Variables column, enter a clear, descriptive variable name that matches how the data is referenced in your prompt. For example, ANI or Call Direction.

   Variable highlighting in the prompt editor is case sensitive. For example, if the variable name is ANI, only ANI is highlighted. Ani or ani are treated as different values and are not highlighted.

4. In the Values column, enter the value to assign to the variable. For example, 87654321012 for ANI or inbound for Call Direction.

   Only rows that contain both a variable name and a value are saved. Rows with a missing name or value are not saved and do not appear again.

5. Repeat these steps for any additional variables you want to add.

   The table does not support arrays.

Edit a variable

• Update the text in the Variables or Values column as needed.

• Changes are saved automatically.

Remove a variable

• Click the X icon at the end of the variable row to delete it.

Inject Variables into Copilot at Run-time Using Studio

You can pass dynamic variables from your Studio script to Copilot during run-time. These variables provide real‑time context, such as ANI, timestamps, or customer‑specific data, and allow Copilot to generate more accurate and personalized responses for each interaction.

Studio sends a JSON payload containing your run-time variables to Copilot. Copilot merges these values with the configured Copilot profile and makes them available in your prompt templates.

To inject variables do the following,

1. Generate an access token. To generate an access token, refer to the Getting Started guide on the NiCE CXone Developer portal. This token is required to securely call the Prompt Manager API or any custom API that triggers the prompt.

2. Create a connection in the Integration Hub so CXone can send the API request to the Interaction Context service. This connection allows Studio to communicate with the API securely and ensures that your runtime variables reach Copilot without additional configuration.

3. Use the script provided in Using Variables in Studio to generate and send the required variable payload during execution. This script includes:

   • Header preparation

   • Timestamp generation

   • Context data structure

   • JSON serialization

   • API submission logic

4. Inside the script, add your custom variables in the designated contextData section. Any variables added here become available to Copilot at run-time.

5. Use a Snippet or the appropriate action to POST the payload to the Interaction Context API. Copilot automatically consumes the values and makes them available in prompt templates.

6. In your Copilot profile, reference variables using double‑curly braces. For example, {{CustomerName} }, {{ProductCategory} }, or {{ReasonForCall} }. When the script sends these values at runtime, Copilot injects them into the prompt and generates a context‑aware KB answer.

Test and Publish the Prompt

Required permissions: GenAI Prompts, Prompt Access Edit

Once you have configured the prompt settings and added queries, you can test your prompt. This will help you see what the AI-generated text looks like and gives you a chance to refine your settings. Publishing the prompt makes it available both for others to see and for selection in the Copilot for Agents profile on the Copilot for Agents Config page.

1. When you are happy with your queries and prompt customization, click Test Prompt.

2. Review the Copilot for Agents KB answers generated for the queries and knowledge hub you provided. If you are not satisfied with the result, adjust the prompt configuration settings and try again. Continue testing the queries and adjusting your settings until you are satisfied with the query response your prompt is generating.

3. Click Publish Prompt.

Select the Prompt in Copilot for Agents

After you have published the prompt profile, you can select it in the Copilot for AgentsAgent Assist Hub application.

1. Still in the General application, go to AI Studio > Profiles.
2. Select the Copilot profile you want to modify or click Add Copilot Profile to create a new one. Follow these instructions if you need to configure the whole profile.
3. Click the Knowledge tab. Select Knowledge Hub as your Knowledge Source and then turn on Enable KB Answers. From the KB Answer Prompt drop-down under the Primary KB Answer Configuration section, select the prompt profile you want to use.
4. Click Save.