Using Now Assist in Virtual Agent

Now Assist in Virtual Agent enhances the user experience by combining AI Search with generative AI chat skills. These skills can speed up issue resolution and reduce deflection to a live agent.

Now Assist in Virtual Agent provides your users with an interactive generative AI experience. A friendly, natural language conversation is easier to understand and helps make requesters more comfortable with talking to a bot.

The following examples highlight how a conversation powered by generative AI might look in Virtual Agent .

Starting the conversation The following figure shows an example of the beginning of a new conversation.

Figure 1. Now Assist greeting

Table 1. Now Assist greeting elements Element Description 1: Bot greeting Note: The Answers generated by AI. Review for accuracy. message prior to the greeting can't be edited or turned off.

After greeting the user, the bot provides an explanation of what the user can expect. Because the large language model (LLM) is still learning, the bot indicates that it may make mistakes, and that the user should check answers for accuracy.

2: User request The user can enter any utterance. 3: Response indicator While the LLM processes the utterance, animated dots in the chat window let the user know that the bot is working.

Conversing with the Virtual Agent After the user enters an utterance and a search result is found, a synthesized response may appear. A synthesized response includes a brief summary of the requested information and search results along with Genius Results. For more information on how these search results are found, see Now Assist Actions Genius Results and Now Assist Q&A Genius Results .

If multiple results are found, they are presented to users, and users can view the Sources section at the bottom of the synthesized response. The Sources section also includes any relevant Knowledge Base article's attachments. Users can view Knowledge Base articles, Virtual Agent topics, subflows or actions, and complete catalog request items. Virtual Agent can only return available catalog items that match a user's request when the Now Assist Multi-Turn Catalog Ordering skill is enabled. Users can follow up on a synthesized response and receive an answer that considers the previous context. For example, if you previously were chatting about the company's travel policy and then enter International, the system recognizes that you are wanting additional information on the company's international travel policy.

Note: For full catalog functionality in the chat window, enable the generative AI experience for catalog item request submissions. For more information, see Configure Now Assist in Conversational Catalog Request .

Whenever a single Virtual Agent topic is found within a synthesized response, users are brought directly into that action's flow. You may consider bypassing the synthesized response and options by automatically launching catalog items, too. For more information on automatically launching single search result actions, search for the sn_nowassist_va.synthesized_autostart_items system property in Available system properties .

The following options may appear depending on what search results are returned:

Conversational catalog: The Start request option appears and if selected, the requester can launch the catalog request flow within the Virtual Agent . Non-conversational catalog: The Go to request option appears with an external link that if selected, either redirects the requester to a new browser or pop-up window for them to order the catalog item. Topic, subflows, or action: The [Asset's name] option appears and if selected, the requester is launched into that flow within the Virtual Agent . Q&A Knowledge Base : The answer is generated by Now Assist with the option to view your sources through the numbered citations icon ( ). After selecting the numbered citations icon to display the sources, you can select each Now Assist link to review the source in depth. Need something else: The View other options option appears and if selected, a list of standard search results in list formatting appears along with one fallback topic. If there are no standard search results, only the fallback topic appears.

Figure 2. A synthesized response example with conversational and non-conversational catalog options

Figure 3. A conversational catalog response flow example

Each Virtual Agent response includes feedback icons. The user can indicate if the response was helpful by selecting the like thumbs up icon ( ). If the response wasn't helpful, the user can select the dislike thumbs down icon ( ). This feedback is used to train the LLM model and improve responses over time.

When the catalog order is complete, Virtual Agent displays a card for the order.

Figure 4. A summary confirmation example for a completed catalog request

If the user needs more help, Now Assist in Virtual Agent directs the user to either a live agent, resets the conversation, or creates an incident. The option is determined by the admin in the Now Assist in Virtual Agent guided setup. For more information, see Configuring Now Assist in Virtual Agent .

Live agent support routes the user to an available agent when configured. Reset the conversation restarts the conversation to the beginning to ask another question. Record producer directs the user to a catalog record producer to create an incident or case.

If a user doesn't have any skills configured for them by the administrator, no available skills are shown. However, the chat bar remains available for the user to enter an utterance. This triggers AI Search for a Knowledge Base article or catalog item.

Figure 5. Example of an open chat widget with no skills activated

For information about configuring a Now Assist skill, see Activate a Now Assist skill .

Engaging with small talk Small talk topics and small talk utterances from the Semantic Filter Framework are recognized. Small talk is supported by your primary and fallback languages. The semantic filtering recognizes these types of small talk:

Greetings: For example, Hi, how are you today? Gratitude: For example, Thanks, this was helpful! Complaint: For example, This answer doesn't help me. Chat conversations with complaints may prompt you to request a live agent or another fallback topic, for example, a create a support request topic.

Closure: For example, That's all I needed. Bye. The conversation ends when closure small talk is recognized.

More information Want to learn more? Visit these resources. For more information on topic switching during a conversation, see Mid-topic switching during Now Assist in Virtual Agent conversations . For more information on Now Assist , see Now Assist . For more information on Now Assist in AI Search , see Now Assist in AI Search . For more information on Now Assist in Virtual Agent analytics, see Analyzing Now Assist in Virtual Agent .