---
sourceDocument: Zurich Conversational Interfaces
sourceDocumentLink: https://www.servicenow.com/docs/r/zurich/conversational-interfaces
Release :
- zurich
ft:locale :
- en-US
ft:publication_title :
- Zurich Conversational Interfaces
ft:clusterId :
- convint
bundleId :
- convint
workflow :
- Platform
---
# Enhanced chat
# Enhanced chat {#ariaid-title1}
* Release version: Zurich
*
* Updated March 19, 2025
*
*  22 minutes to read
Summarize
 Summarized using AI
This content was generated using new OpenAI-powered functionality. Results are provided on an as is basis and are not guaranteed to be accurate or complete.
## Summary of Enhanced Chat in ServiceNow Otto for Virtual Agent (Zurich Release)
Enhanced chat in ServiceNow Otto for Virtual Agent offers a dynamic conversational support experience that integrates AI-powered chat and search capabilities.
It supports multiple simultaneous conversations, provides superior search suggestions, and can redirect users to a full-page chat experience after a portal search.
This integration of generative AI and AI Search helps speed up issue resolution and reduces the need for live agent intervention, improving user satisfaction and efficiency on ServiceNow portals.
Show full answer Show less
The chat window and full-page chat maintain synchronized conversational history, ensuring a seamless user experience regardless of the interface used.
## Key Features
* **Integrated Chat and Search:** Users receive suggested conversational prompts and type-ahead search queries directly in the portal search bar, with options to enter chat or view search results enhanced by synthesized AI-generated responses with inline citations.
* **Dynamic Chat Window Controls:** The floating chat window can be moved, resized, pinned to the browser side, expanded to 90% screen size, or minimized, offering flexible interaction tailored to user preferences. Pinning is enabled by default on Service Portal and configurable for other portals.
* **Multi-Conversation Management:** Users can manage multiple chats via a dedicated sub-header with sections for active, closed, and updates notifications. Chats auto-close after configurable inactivity periods and can be permanently deleted by users.
* **Generative AI and Synthesized Responses:** Virtual Agent delivers concise synthesized answers with inline citations referencing catalog items, Knowledge Base articles, external content connectors, and people records. Users can interact with citations to request catalog items via chat or forms, view sources, or explore organizational charts.
* **Language Detection and Machine Translation:** The chat interface automatically detects and switches to the user's preferred language if different from the initial input, enhancing accessibility and user comfort.
* **Agentic Conversations:** When enabled, AI agents can understand and process multi-part user requests, reasoning across multiple Virtual Agent skills and external data sources. Users receive real-time processing updates and can view detailed AI agent flow steps.
* **Live Agent Chat Integration:** Users can escalate to a live agent from the chat interface when needed, with only one live chat allowed at a time. The interface displays agent details and enables ending the live chat, after which the conversation is archived.
* **Feedback and Quality Assurance:** Every Virtual Agent response includes feedback icons allowing users to rate helpfulness and provide detailed comments. Feedback data supports ongoing analytics and service improvement.
* **Fallback Options:** When Virtual Agent cannot provide relevant results, fallback options appear such as requesting live chat, performing a web search, creating a generic ticket, or triggering custom fallback topics.
## Practical Benefits for ServiceNow Customers
* **Improved User Experience:** Natural language conversations with AI-driven prompts and responses make self-service intuitive and efficient, reducing frustration and improving engagement.
* **Increased Efficiency:** AI Search combined with generative AI accelerates issue resolution by delivering relevant answers, suggested actions, and catalog request processing without needing live agent intervention.
* **Flexible Deployment:** Enhanced chat adapts to different portal configurations, supports multiple chats, and can be expanded or pinned to suit user workflows.
* **Comprehensive Knowledge Access:** Synthesized responses aggregate data from internal knowledge bases, catalog items, external content connectors, and organizational data (via Knowledge Graph), providing users with rich, actionable information.
* **Seamless Escalation:** Built-in live agent chat support ensures users can easily escalate complex issues, with chat history preserved and post-chat surveys enabled for quality assurance.
* **Multilingual Support:** Automatic language detection and translation enable global organizations to support diverse user populations effectively.
* **Administrative Control:** System properties and configurations allow administrators to customize inactivity timeouts, chat pinning behavior, suggested search queries, fallback options, and AI agent workflows to align with organizational needs.
## What to Expect When Using Enhanced Chat
* Users start conversations by typing queries in the portal search bar or chat widget, receiving AI-suggested prompts and synthesized answers with actionable citations.
* Catalog requests can be submitted and completed within chat or via forms, with order summaries displayed upon completion.
* AI agents handle complex multi-question requests, providing step-by-step processing visibility and the option to end flows if needed.
* Users can view detailed information about people and organizational structure directly in chat, enhanced by Knowledge Graph integration and external content sources.
* Feedback mechanisms promote continuous improvement of Virtual Agent responses based on user input.
* Fallback options ensure users are never left without assistance, offering alternative support paths when AI responses are insufficient.
ServiceNow Otto for Virtual Agent enhanced chat is a conversational support experience within a dynamic window that also includes the ability to have multiple active conversations and superior search capabilities. Turning on enhanced
chat's full-page experience further combines chat and search capabilities by redirecting you into a full-page chat after entering a query into a portal's search bar.
ServiceNow Otto for 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.
Note:
For more information about selecting a chat experience in the admin guided setup, see [Display your assistant on a portal, channel, or mobile app](https://www.servicenow.com/docs/n~jwLt5wx0rupNSv1G~b_A "Select a display experience for your chat assistant. Display experiences are the different places where a user can find and interact with an assistant. Select from a list of portals, messaging channels, and mobile app. To activate an assistant, at least one display experience must be configured.").
ServiceNow Otto for Virtual Agent provides your users with an interactive generative AI experience. A friendly, natural language conversation is easier to understand and helps users to be more comfortable with chatting to a bot.
The following sections highlight how a conversation powered by generative AI might look in Virtual Agent.
Note:
This content's primary focus is on enhanced chat's default chat window rather than on the optional full-page experience. The conversational fluidity and citation behavior between the enhanced chat and enhanced chat's full-page experience remains the same regardless of which chat experience you use. The conversations that you have either through the enhanced chat's window or full-page experience remain in synchronization, and the conversational history is retained in both mediums. For more information about the full-page experience, see that relevant section in [Using ServiceNow Otto for Virtual Agent](https://www.servicenow.com/docs/4X39_SlPrUYS08ifKiHsfQ "ServiceNow Otto for 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.").
## Starting the conversation {#nava-enhanced-chat__section_tts_jkp_s2c}
With enhanced chat, chat and search capabilities are combined. Suggested conversational prompts and searches may appear in a drop-down list on the portal's search bar. The Ask ServiceNow Otto section header may appear at the top of the
portal search bar's drop-down list. When you select one of these suggested queries, you're redirected into a conversation within a chat window or full-page experience. You receive relevant answers based on the prompt that you have
selected. If you select a suggested type-ahead search outside of the Ask ServiceNow Otto header, that search query begins in either the portal's search results page or within the full-page experience's Search
tab.
Figure 1. Example of type-ahead portal search
Note:
For more information about how ServiceNow Otto for Virtual Agent and ServiceNow Otto for AI Search combine to include these suggestion type-ahead searches, see [Auto-complete suggestion types included with ServiceNow Otto for AI Search](https://www.servicenow.com/docs/access?context=auto-complete-suggestion-types-na-ais&version=zurich&pubname=zurich-platform-administration&ft:locale=en-US). To learn how to activate suggestion term bold highlighting, see [Configure AI Search as the source for Ask ServiceNow Otto suggestions](https://www.servicenow.com/docs/access?context=configure-ai-search-source-ask-now-assist-suggestions&version=zurich&pubname=zurich-platform-administration&ft:locale=en-US).
When you're using enhanced chat and you enter a search query through your portal's search bar, you're redirected to the portal's search results page. At the top of the search results page, you see Genius Results in a synthesized
response generated by ServiceNow Otto. This synthesized response answer provides inline citations that appear at the end of each sentence. You can select citations and if applicable, such as for conversational catalog items, select whether to ![Request with form icon.]()Request with form or ![Request in chat icon.]()Request in chat. Similar options also appear in the regular search results area, as indicated by the request in chat icon ( ![Request in chat icon.]()) and request with form icon (![Request in form icon.]()). Depending on your selection, the catalog request flow launches within either the Virtual Agent chat or a form.
Figure 2. Example of enhanced chat synthesized response on the portal's search results page
You can start the chat experience either through the chat icon on the portal's search results page or through the portal's chat widget button.
Figure 3. Example of chat entry points on the portal's search results page Figure 4. Example of a chat widget button
After selecting the chat widget button on the portal, the floating chat window opens and replaces the chat button. A greeting message appears, and a chat is created only after you have entered an initial utterance. If you have an
active chat ongoing, the current active chat appears instead of a greeting message. You can select a predefined action, topic, suggested search query, start a new conversation, or view all options, if applicable. The View all options link only shows if more than one suggested search query or promoted topic is available.
Note:
Any search query entered into the portal's search bar or Virtual Agent is incorporated into the greeting topic for future conversations as a suggested search query. Suggested search queries can be viewed in the Search Suggestions \[sys_search_suggestion.list\] table. For more information on how to enable suggested search queries, see [ServiceNow Otto for Virtual Agent system properties](https://www.servicenow.com/docs/wHRZwSt80kdPuSySOQ979g "Use system properties to customize your assistant. Some properties are available on a system properties form, but some lesser-used properties are available only from the System Property [sys_properties] table. Legacy refers to the standard or enhanced chat experience. Premium refers to the premium chat experience.").
Figure 5. Example of the start of an enhanced chat conversation
If language detection is activated and initial utterances in the portal's search bar or chat differs from the user's language preference, the chat switches to the detected language. For more information and examples of language
detection in enhanced chat conversations, see [Using language detection and dynamic machine translation in Virtual Agent enhanced chat conversations](https://www.servicenow.com/docs/ORNUP13X6M0yRCWjf1wI_A "Enable a combination of language detection and machine translation for Virtual Agent to improve the chat experience for diverse users. You can designate fallback languages for locales or dynamically translate languages that aren't professionally localized or aren't supported in topic discovery.").
## Navigating the chat window resizing options and controls toolbar {#nava-enhanced-chat__section_m1x_rkp_s2c}
After selecting the chat widget button, the floating chat window opens and replaces the chat button. You can move the chat window by selecting the header and dragging the chat window to the desired location. You can resize the chat
window by using the window's edges to resize to your desired size or use the toolbar icons. The following list details the chat window adjustment icons:
* ![Expand icon.](): Selecting the expand icon ![Expand icon.]() expands the chat into a 90% screen-size window. The 90% screen-size window can't be resized or moved. Selecting outside of the 90% screen-size chat window resizes the chat back into the floating window.
* ![Pinned right-hand side icon.](): Selecting the pin icon ![Pinned right-hand side icon.]() pins the chat to the side of the browser but you can still resize this window to fill half the browser, if desired. When you duplicate a browser tab, open a new tab, or use the browser back button, the chat window state persists as long as you have not minimized the chat.
Important:
By default, pinning a chat window is enabled for Service Portal. For all other portals, an admin needs to create a system property to enable pinning a chat window. For more information, see [ServiceNow Otto for Virtual Agent system properties](https://www.servicenow.com/docs/wHRZwSt80kdPuSySOQ979g "Use system properties to customize your assistant. Some properties are available on a system properties form, but some lesser-used properties are available only from the System Property [sys_properties] table. Legacy refers to the standard or enhanced chat experience. Premium refers to the premium chat experience.").
* ![Down-arrow minimize icon.](): Selecting the down arrow ![Down-arrow minimize icon.]() minimizes the chat and the chat widget button reappears.
{#nava-enhanced-chat__ul_mfc_nwl_y2c} Figure 6. Example of a 90% screen-size window Figure 7. Example of a pinned chat
The ServiceNow Otto sub-header consists of four elements. The following figure and table shows an example and description of those elements.
Figure 8. Example of chat controls {#nava-enhanced-chat__table_qzq_r2c_qfc__entry__2}
| Element | Description |
|-|-|
| 1. Chats (![Chats icon.]()) | All chats appear. Chats are organized with the most recent conversations at the top. Selecting a chat opens the chat in the conversation area. If there are unread chats or notifications, a badge number appears on the Chats icon (![Chats icon.]()). Any unread chat or notification appears with a red dot next to it and the chat title appears in bold. Additionally, if you switch to a new chat while another active chat is ongoing, a pop-up message on the Chats icon (![Chats icon.]()) appears: Your previous chat was saved. You can revisit all of your past chats and continue ones that are still active. The following list includes the chat sections that you may see in the chats area. * Active: Chats where you can continue the conversation. If applicable, active chats move to the Closed chats section after two hours of inactivity. This 2 hour time limit can be configured within the Messaging Channels {sys_cs_channel.list} table. To change the inactivity time limit, from the Messaging Channels {sys_cs_channel.list} table, select the NASS record and populate the Conversation Idle Timeout field with your preferred active chat time limit. If you have no active chats, No chatter at the moment is displayed. If more than 12 active chats are running, a Show more link appears to view more chats. Selecting Show more displays an additional 10 chats. * Updates: Updates for important notifications and reminders can be configured to display. When sn_nowassist_va.nass_notification_enabled is set to true (the default), simple (nonactionable) Virtual Agent notifications appear on your portal home page. After selecting a notification, you're redirected to this Updates section. If you have no updates, You're all caught up is displayed. If more than four updates are available, a Show more link appears to view more updates. Selecting Show more displays an additional 10 updates. Note: If sn_nowassist_va.nass_notification_enabled is set to false, the Updates section doesn't appear. * Closed: Closed chats can be configured to display. You know that a message has closed when the designated time has passed (2 hours of inactivity) or you receive the following response in the chat: It looks like you're finished with this chat, so I'll go ahead and close it. Turn on closed chats by selecting the Show closed chats check box within Conversational InterfacesAssistants\[Selected Assistant Name\]Chat experienceClosed chats. After being turned on, closed chats are displayed for as long as they're available within the Conversations (sys_cs_conversation) table. Closed chats appear in a read-only mode and can't become active again. If more than four closed chats are available, a Show more link appears to view more closed chats. Selecting Show more displays an additional 10 closed chats. After a conversation has closed, you can't reopen it. Hovering over a closed chat displays the delete icon (![Delete icon]()). Confirm the chat deletion on the Delete this chat? modal to permanently delete the chat from the interface. {#nava-enhanced-chat__ul_b31_ckc_qfc} |
| 2. \[Chat name\] | The name of the conversation. If you select a promoted asset or query, that asset's title appears as the chat name. If instead you enter an utterance into the Reply to field, your initial utterance becomes the chat name. The chat name appears in both the ServiceNow Otto subheader and Chats listActive section. |
| 3. New chat (![New chat icon.]()) | A new conversation begins. You may be prompted with a greeting message along with any promoted conversational assets such as topics, subflows, and/or actions, or suggested queries. |
| 4. Support and settings () | Support contact information such as phone numbers and email addresses are listed. If live agents are available, an active Contact Live Agent button is displayed. Although multiple active conversations are possible, you can only have one live agent conversation at a time. Selecting Contact Live Agent begins a chat with a live agent. After a live agent enters the chat, the Contact Live Agent button becomes inactive. If live agents are unavailable, an inactive No live agents currently available button is displayed. Settings toggles for Audio notifications and Notifications appear. By default, audio notifications are turned on and notifications are turned off. If admins have enabled notifications within the guided setup, users can turn on the notifications. |
| 5. Interactive view (![]() or ![]()) | Note: This icon only appears in the sub-header whenever the interactive view is available. Open or close the interactive view. The interactive view appears to the right of the conversational chat area. Interactive view is only available in the following scenarios: * An organizational chart is available to view. * A document was uploaded and you choose to preview the document. * A source is available and you choose to select and view the source content. {#nava-enhanced-chat__ul_bfd_rjh_zjc} |
[Table 1. ServiceNow Otto sub-header elements]
{#nava-enhanced-chat__table_qzq_r2c_qfc}
## Chatting with Virtual Agent {#nava-enhanced-chat__section_its_kkp_s2c}
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 [Actions Genius Results](https://www.servicenow.com/docs/access?context=now-assist-catalog-ordering-gr&version=zurich&pubname=zurich-platform-administration&ft:locale=en-US) and [Knowledge base articles Genius Results](https://www.servicenow.com/docs/access?context=now-assist-qna-genius-results&version=zurich&pubname=zurich-platform-administration&ft:locale=en-US).
If multiple results are found, you can follow inline citations to either begin an action or learn more. The option to Show sources appears at the end of the synthesized response for internal and external Knowledge Base articles. Virtual Agent can only return available catalog items that match a user's request when the ServiceNow Otto Multi-Turn Catalog Ordering skill is enabled.
Note:
For full catalog functionality, enable the generative AI experience for catalog item request submissions. For more information, see [Configure ServiceNow Otto in Conversational Catalog Request](https://www.servicenow.com/docs/wsfPf2eWV3wHKNV0HnhiHg "Speed up and provide a conversational and streamlined experience based on generative AI while submitting a catalog item request in Virtual Agent. Your organization can increase self-service and reduce operating costs.").
Whenever only a single search result for topics is found, the synthesized response and options are bypassed by default and 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](https://www.servicenow.com/docs/access?context=r_AvailableSystemProperties&version=zurich&pubname=zurich-platform-administration&ft:locale=en-US).
You can create a new query from within a ServiceNow Otto conversation using mid-topic discovery. For more information, see [Mid-topic switching during ServiceNow Otto for Virtual Agent conversations](https://www.servicenow.com/docs/dGMHIZwZi7GdJOarH5DI7g "Mid-topic switching easily lets you switch between requests, using plain language whenever new queries are made in the same ServiceNow Otto for Virtual Agent conversation.").
If AI Guardian is enabled and your request contains profane content, the Virtual Agent responds with a message prompting you to re-enter an appropriate request without profanity or offensive content. If your request is too ambiguous on the portal search, a synthesized response
appears along with an Ask a follow up option. Selecting the Ask a follow up option redirects you to a Virtual Agent chat. In the Virtual Agent chat, you can submit your follow-up question or request, but the synthesized response links are only available to select on the portal page and are unavailable to select in the chat window. If your
follow-up question or request is too ambiguous in the Virtual Agent chat, Virtual Agent asks a clarifying question and displays the go to search results icon (![Go to search results icon.]()) in the feedback panel.
If your question is unclear or could apply to multiple topics, ServiceNow Otto evaluates your request and may ask for clarification before responding. This helps you receive a focused, relevant answer rather than an overwhelming list of results. If the assistant is confident it
understands your intent, it responds immediately without asking for clarification. If no relevant answer is found, the assistant displays a message and suggests an alternative, such as contacting support.
Processing messages are short status updates that appear on-screen while ServiceNow Otto works on your request. They reflect what ServiceNow Otto is actively doing at each step, such as searching for information or analyzing a document, and update as each step completes. Processing messages don't appear for simple interactions such as greetings,
which are handled instantly.
Figure 9. Example of Ask a follow up in Virtual Agent
Each Virtual Agent response includes a feedback icons panel. The feedback icons panel appears on the latest Virtual Agent response and whenever you hover over any Virtual Agent response. You can indicate if the response was helpful by selecting the like thumbs up icon (![Thumbs up icon.]()). If the response wasn't helpful, select the dislike thumbs down icon (![Thumbs down icon.]()). When you select the thumbs up or thumbs down icon, you are prompted to provide detailed feedback by selecting one or more reason check boxes. You can also select Other to add comments or suggestions (up to 300 characters). After making your selection, select Submit to submit your feedback or select X to close the dialog without submitting feedback. All submitted feedback is captured, stored, and made available through analytic dashboards.Figure 10. Example of additional feedback panel from thumbs down icon Depending on the context of the response, an additional go to search results icon (![Go to search results icon.]()) may appear in the feedback icons panel. This icon appears alongside synthesized responses in Virtual Agent, clarifying questions in Virtual Agent, and regular search results or Virtual Agent fallback topics whenever a synthesized response is unavailable. Selecting the go to search results icon (![Go to search results icon.]()) redirects you to the search results page and begins a search query using the last five chat utterances you entered. Additionally, a copy message icon (![]()) appears on received Virtual Agent responses.
Figure 11. Example of feedback panel in enhanced chat
Responses generated in ServiceNow Otto for Virtual Agent can come from a combination of catalog items, Virtual Agent topics, subflows and actions, knowledge articles, attachments, external content sources, and people citations. Inline citations appear at the end of the relevant synthesized response sentence.
Selecting an inline citation results in a popover containing either a link to an article or source, or a description and action to start the action. The following options may appear as synthesized response in-line citations
depending on what search results are returned:
* Catalog
* Topic, subflows, or actions
* Q\&A Knowledge Base articles
* External content connections
* People
* Extended entities and additional records
{#nava-enhanced-chat__ul_y4t_qf1_w2c}
Note:
Q\&A Knowledge Base and external content connection citations also appear within the expandable Show sources option.
## Agentic conversations {#nava-enhanced-chat__section_xcs_5vn_sfc}
Note:
Admins must first enable AI agents before end users can experience agentic conversations. For more information on how to set up AI agents for agentic conversations, see [Agentic conversations in Virtual Agent](https://www.servicenow.com/docs/Rq8o4DHxQPhZ7tvZzUAdeQ "When you query a Virtual Agent, it reasons, plans, and executes across a wide variety of options. The Virtual Agent can use AI agents, virtual agent topics, conversational actions and subflows, catalogs, KB articles, custom skills, and any ServiceNow Otto for Virtual Agent supported skills to help you."). ServiceNow Otto for Virtual Agent discovers and executes AI agents. For more information about AI agents, see [AI Agent Studio](https://www.servicenow.com/docs/access?context=na-ai-agents&version=zurich&pubname=zurich-intelligent-experiences&ft:locale=en-US).
When you submit a single question to the Virtual Agent, the agent understands the query and begins a flow. When you submit a message with multiple questions or requests, Virtual Agent answers the multiple questions consecutively in a response. It can reason, plan, and execute across AI agents, Virtual Agent topics, conversational actions and subflows, catalogs, Knowledge Base articles, custom skills, and any ServiceNow Otto for Virtual Agent supported skills to help you. Before receiving a response, you receive acknowledgment messages from the Virtual Agent and on-screen messages to let you know where the agent is at in the agentic processing flow. After the processing has completed its flow, a View AI Steps section header appears, where the processing flow steps can be expanded and viewed. You can stop the agentic processing flow at anytime by selecting the End flow icon (![End flow icon.]()). After an action starts, it cannot be stopped. Selecting the End flow icon (![End flow icon.]()) only stops the proceeding processing steps.
Figure 12. Example of an agentic conversation starting
## Catalog citation {#nava-enhanced-chat__section_vjg_bg1_w2c}
If you're accessing the catalog citation through the synthesized response popover, the popover options vary depending on where you're located. The only popover option when in chat is the Start request option
which begins the catalog action within the chat. There are two popover options when you select the synthesized response through the portal's search bar: ![Request with form icon.]()Request with form and ![Request in chat icon.]()Request in chat. Similar options also appear in the regular search results area, as indicated by the request in chat icon ( ![Request in chat icon.]()) and request with form icon (![Request in form icon.]()). Depending on your selection, the catalog request flow launches within either the Virtual Agent chat or a form.
Figure 13. Example of synthesized response popover on the portal's search results page Figure 14. Example of a synthesized response with catalog and knowledge base citations
If you chose to complete the catalog request through chat, after the catalog order is complete, Virtual Agent displays a summary card for the order.Figure 15. Example of summary card for catalog order in chat
## Topic, subflows, or actions citations {#nava-enhanced-chat__section_n4y_bg1_w2c}
These assets are associated with the chat icon (![Request in chat icon.]()) and if selected, that flow begins within Virtual Agent. The popover is not applicable to these types of assets.
## Q\&A Knowledge Base citations {#nava-enhanced-chat__section_ov1_dg1_w2c}
The answer is shown with the option to view your sources through the numbered inline citations icon (![Numbered citations icon.]()) and in the Show sources section. These Knowledge Base inline citations show which ServiceNow knowledge articles were used to generate the response.
Note:
If you have activated Knowledge Graph, you may get more personalized Q\&A Knowledge Base responses depending on whether the user schema attributes were triggered. For more information about receiving these personalized responses, see [Access Knowledge Graph Schema](https://www.servicenow.com/docs/access?context=access-knowledge-graph-designer&version=zurich&pubname=zurich-intelligent-experiences&ft:locale=en-US).
Figure 16. Example of Knowledge Base inline citation, popover, and Show sources expanded
## External content connections citations {#nava-enhanced-chat__section_uvy_dg1_w2c}
The answer is shown with the option to view your sources through the numbered inline citations icon (![Numbered citations icon.]()) and in the Show sources section. If external search sources are added to your information sources when [Configuring assistants overview](https://www.servicenow.com/docs/0bKmXfQyHQhSU1~pEwib6w "Use Assistant Designer to build and optimize large language model (LLM) assistants for your conversational needs. Assistant Designer is a centralized assistant administrator experience that allows you to create and manage both chat and voice assistants."), you can search through external content connections. This can include information from attachments and knowledge blocks, or from the following list of content connections:
* Adobe Acrobat Sign external content connector
* Adobe Experience Manager as a Cloud Service external content connector
* Aha! Roadmaps external content connector
* Amazon S3 external content connector
* Asana external content connector
* Atlassian Confluence Cloud external content connector
* Atlassian Jira Cloud external content connector
* Box external content connector
* Cornerstone external content connector
* Docusign external content connector
* Fluid Topics external content connector
* Dropbox external content connector
* GitHub Enterprise Cloud external content connector
* GitLab external content connector
* Google Drive external content connector
* HubSpot external content connector
* Lucidchart external content connector
* ManageEngine external content connector
* Microsoft OneDrive external content connector
* Microsoft SharePoint Online external content connector
* Microsoft Teams external content connector
* Microsoft Viva Engage external content connector
* Miro external content connector
* monday.com external content connector
* Notion external content connector
* SAP DMS external content connector
* ServiceNow documentation external content connector
* ServiceNow instance external content connector
* Slack external content connector
* Smartsheet external content connector
* Trello external content connector
* Webcrawler external content connector
* WordPress external content connector
* Workday external content connector
* Workvivo external content connector
* Zendesk Guide external content connector
* Zoom external content connector
{#nava-enhanced-chat__ul_m44_czt_3fc}
For more information about external content connections, see [External Content Connectors](https://www.servicenow.com/docs/access?context=ext-cont-connectors-landing-page&version=zurich&pubname=zurich-platform-administration&ft:locale=en-US).
## People citations {#nava-enhanced-chat__section_zxh_fg1_w2c}
Information about people in your organization can be found if you have activated Knowledge Graph.
Information about the person you're searching for appears in the synthesized response, along with an inline people citation. If a direct match doesn't occur and multiple people are found, try providing more information to narrow
down the people search results. Up to three people can appear in a synthesized response. You may be asked a clarifying question, such as Are you asking about \[user_1\], the programmer, or \[user_2\], the faculty member? to yield better results. Selecting the person's name redirects you to the portal's user profile landing page.
Figure 17. Example of synthesized response for people on the portal's search results page Figure 18. Example of synthesized response with people inline citations in chat
Selecting the person's name presents a popover. The information in the popover can include the following information:
Note:
The following popover details can be customized through EVAM. For more information about customizing the data details, see [Define an EVAM view template](https://www.servicenow.com/docs/access?context=define-evam-template&version=zurich&pubname=zurich-servicenow-platform&ft:locale=en-US).
* Manager
* Location
* Email
* Teams
* Phone
* Shared files
Important:
Shared Microsoft SharePoint files only appear if a Knowledge Graph admin has activated the sn_kg_conn_user_shared_files record in the Knowledge Graph Related Data Map \[sn_kg_related_data_map_list\] table. Shared Microsoft SharePoint files between you and the person found appear only on the people popover. These shared files only appear after you have completed the prompt to Log in, signed in successfully, and have entered a new search query for that person. A new search query is necessary after you have signed in so that up to three shared Microsoft SharePoint files can appear. You're automatically logged out of your Microsoft account every three months and must repeat the Log in prompt again to see shared files.
If you do not have a valid token, you are prompted to sign in and are redirected to the Microsoft login page. If you have not configured the Microsoft OneDrive application, see [Configure Microsoft OneDrive application for Knowledge Graph](https://www.servicenow.com/docs/access?context=create-microsoft-onedrive-app&version=zurich&pubname=zurich-intelligent-experiences&ft:locale=en-US).
* View org chart
Note:
Selecting View org chart opens the interactive view to the right of the chat conversation. The person's information is shown along with their reporting structure in their company's organization chart. You can view and select contact options in the reporting structure of the organization chart. Secondary links like View profile open in a new tab and do not disrupt the conversation.
{#nava-enhanced-chat__ul_uxk_qpp_52c} Figure 19. Example of people citation's popover
Although rare, when you receive a synthesized response that includes a person, you may also receive other citations associated with that person. For example, a Knowledge Base article that was authored by the person you searched for may also appear.
Note:
If you have activated Knowledge Graph, you may get more personalized Q\&A Knowledge Base responses depending on whether the user schema attributes were triggered. For more information about receiving these personalized responses, see [Leverage Knowledge Graph prebuilt integration with Now Assist
Virtual Agent and Now Assist Panel](https://www.servicenow.com/docs/access?context=example-use-case-for-knowledge-graph&version=zurich&pubname=zurich-intelligent-experiences&ft:locale=en-US).
## Extended entities and view records {#nava-enhanced-chat__section_ikl_1tm_rfc}
Extended entity information can be found if you have activated Knowledge Graph.
er. Only one live agent chat at a time is permitted. To exit the live chat, select End live chat. The chat history then moves to the Closed chat
These extended entities
that come from the additional custom tables associated with the Knowledge Graph natural language query (NLQ) schema can include:
* Assets
* Incidents
* Recently viewed knowledge base articles
* Requests
* Tasks
{#nava-enhanced-chat__ul_v4k_55m_rfc}
Select an entity in-line citation to view that entity record in a new tab, or select View records to view a list of additional entities. Selecting a link from the View records
pop-up opens a new tab with that entity table's data.
Figure 20. Example of extended entities and view records
The following example is of a conversation showing 3 out of 11 incidents and the option to view records to view additional users and incident records.
## Chatting with a live agent in Virtual Agent {#nava-enhanced-chat__section_ijs_vqw_s2c}
You can chat with a live agent if you need more support. Select the Contact Live Agent button found in the Support and settings () option, enter a request such as Chat with live agent into the chat, or select the Request a live agent fallback option. After an agent has accepted your chat, the agent's name
and avatar appears at the top of the chat in a banner. Only one live agent chat at a time is permitted. To exit the live chat, select End live chat. The chat history then moves to the Closed chat section.
Note:
When enhanced chat is turned on, post-chat surveys only appear after a live agent conversation has ended.
Figure 21. Example of the live chat banner
## Fallback options {#nava-enhanced-chat__section_rs2_1qq_4fc}
Note:
For more information about where and how to enable fallback options, see [Manage an assistant chat experience](https://www.servicenow.com/docs/1sTGlMoIkX17SgFzPtG8LA "Manage the chat experience of your assistant.").
A fallback state can occur whenever search results are unavailable. Scenarios where search results are unavailable include the Virtual Agent didn't understand the query, complaint small talk was found, or an error occurred. When search results are unavailable, a single or multiple fallback options may appear. These fallback options include:
* Request a live chat: Triggers live agent mode and routes you to a human support representative.
* Search the web: Triggers web search mode and uses the internet to search for the results.
Note:
Only the last query entered into the conversation is considered when entering web search mode via this Search the web fallback option.
* Create a generic ticket: Creates a record.
* Custom fallback option: Presents a fallback Virtual Agent topic.
{#nava-enhanced-chat__ul_fdz_sbq_4fc}
Select a fallback option to launch that mode or action.Figure 22. Example of multiple fallback options
*[\>]: and then