---
sourceDocument: Australia Conversational Interfaces
sourceDocumentLink: https://www.servicenow.com/docs/r/conversational-interfaces
Release :
- australia
ft:locale :
- en-US
ft:publication_title :
- Australia Conversational Interfaces
ft:clusterId :
- convint
bundleId :
- convint
workflow :
- Platform
---
# Agentic conversations in Virtual Agent
# Agentic conversations in Virtual Agent {#ariaid-title1}
* Release version: Australia
*
* Updated March 12, 2026
*
*  5 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 Agentic conversations in Virtual Agent
Agentic conversations in Virtual Agent enable a more intelligent and interactive experience by allowing the virtual agent to understand, reason, plan, and execute complex user requests.
It orchestrates multiple AI agents, skills, topics, knowledge base (KB) articles, and custom capabilities within ServiceNow to fulfill user intents effectively.
This feature enhances the Virtual Agent's ability to break down multi-part queries, handle sequential tasks, and provide precise, actionable responses.
Show full answer Show less
## Enabling Agentic Conversations
To use agentic conversations, administrators must manually enable AI agents and configure assistants with specific scopes mapped to portals. Key steps include:
* Creating or using existing Virtual Agent assistants.
* Assigning assistants to portals or channels.
* Enabling agentic support for those assistants.
* Mapping AI agents to assistants in AI Agent Studio to make them available for orchestration.
During conversations, only configured AI agents for the active assistant are considered, enabling dynamic planning and execution.
## Key Features and Examples
* **Multi-question handling:** Breaks complex questions into individual parts and provides distinct answers rather than a mixed response.
* **Multi-skill execution:** Separates user requests involving different skills (e.g., ordering coffee and food) and executes them sequentially.
* **Complex task orchestration:** Understands dependencies between multiple tasks, executes them in order, and uses outputs from prior steps as context for subsequent actions.
* **Combination of QnA and agent tasks:** Processes queries that involve retrieving information and performing actions (e.g., fetching policy info and sending an email) by recognizing separate intents and executing them in sequence.
## Managing Conversations
Users can halt an ongoing agentic conversation by selecting an interrupt icon, which stops the current process and allows starting a new query.
## Error Handling and Fallback Options
The system provides clear messages and options when the AI agent cannot fulfill requests due to misunderstandings, inactivity, or technical issues. These include:
* Offering to connect with a live agent or create support requests.
* Warning users about session timeouts with the option to continue the conversation.
* Providing fallback options if multi-step tasks fail at any point, enabling users to choose alternative actions.
**Important:** Customers should review AI-generated responses for accuracy before acting on them to ensure correct outcomes.
When you ask a question to the virtual agent, the agent understands the query. It can reason, plan, and execute across 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.
* If for the given assistant, specific agents are available to perform user tasks or sub tasks, they're used.
* If a specific agent isn't available, the system automatically employs the Search Agent to discover answers or appropriate skills within the system (again based on the assistant scope).
* If skill execution is required, the system automatically executes the discovered skills.
* The system can plan and orchestrate execution among multiple agents, skills, and QnA to accomplish complex tasks.
{#agentic-conversations-vad__ul_gjw_vfp_hfc}
## Enable AI agents in Virtual Agent {#agentic-conversations-vad__id_g3k_rgp_hfc}
Role required: admin or virtual_agent_admin
Note:
You must manually enable agents to make them discoverable in Virtual Agent. For more information about changing the settings, see [Conversational settings for assets in the Asset library](https://www.servicenow.com/docs/GT83sh8Ib1e4eCvtN6C1dw "Manage asset settings from the Asset library for individual active assets.").
To enable AI agents in Virtual Agent:
1. Create and configure multiple assistants with specific scope and map the assistants to one or more portals.
The configuration consists of the following:
* Creating an assistant in Virtual Agent or using the default. To create an assistant, see [Create a chat assistant](https://www.servicenow.com/docs/hL1ApC7i3vwv2qnO8gZiCg "Create a chat assistant on your instance. Add basic details and set your assistant as a primary assistant.")
* Assigning specific assistants to a specific portal or portals. For more information, see [Display your assistant on a portal, channel, or mobile app](https://www.servicenow.com/docs/d0gS20y_GOvvL45UPn~l4Q "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.").
{#agentic-conversations-vad__ul_uh5_nqp_hfc}
2. Ensure that Agentic support is enabled. For more information about using agentic support, see [Use agentic support for a chat assistant](https://www.servicenow.com/docs/UpLqbjMMEjsrmapeXFi1zw "Let the assistant use AI agents and agentic orchestration. AI agent skills are prompt-based and can perform complex tasks. Admins can choose between agentic or standard search Q&A modes.").
3. Map or publish an agent to one or more assistants on AI Agent Studio to make the agent available within a specific assistant. For more information, see [Create an AI agent](https://www.servicenow.com/docs/access?context=configure-next-best-action-agent&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US).
{#agentic-conversations-vad__ol_vbg_btp_hfc}
During execution, only the configured AI agents are considered for the current assistant and dynamically makes them available to the Orchestrator for planning.
## Examples of AI agent behavior for user utterances {#agentic-conversations-vad__section_gs2_lqp_hfc}
The examples will consider the following available example resources in the system:{#agentic-conversations-vad__table_llk_4dq_hfc__entry__3}
| Agents | Skills/Topics | KB Articles |
|-|-|-|
| Check IT Ticket status agent Email Agent Meeting scheduling Agent | Order coffee Order food Order laptop Order accessories | Spam ESPP policy |
[ ]
{#agentic-conversations-vad__table_llk_4dq_hfc}
Scenario 1: Multiple questions from KB articles
Utterance: How do I avoid spam? How do I detect it?
* Non-agentic response: Produces a single mixed answer.
* Agentic response: Breaks it into two questions and provides a better answer for each one of them.
{#agentic-conversations-vad__ul_rhj_b1q_hfc}
Scenario 2: Multiple skills with slot filling
Utterance: Hey, order a coffee for me, preferably dark roast and something to eat, maybe a pizza?
* Non-agentic response: Produces a single answer. Mostly listing all matching available skills. No auto-execution since it matched multiple skills.
* Agentic response: Breaks it into two distinct tasks, order coffee and order food/pizza. Executes one after another, completing the entire user request.
{#agentic-conversations-vad__ul_fmk_mbq_hfc}
Scenario 3: Complex utterance with a combination of skills, agents, and QnA
Utterance: I am going on PTO tomorrow. Get my expense report and my IT ticket status. Send a summary of the expense report to John Jacob and the details on ticket status to Robert Williams, informing them of my PTO and requesting them to work on them.
* Non-agentic response: Produces a single answer. It lists all matching available skills. No auto-execution will take place since it matched multiple skills.
* Agentic response: Breaks it into multiple distinct tasks, reasons and plans, understands the dependencies, and executes one after another. The response completes the entire user request using output from prior actions as context as needed.
{#agentic-conversations-vad__ul_rm1_g2q_hfc}
Scenario 4: Complex utterance with a combination of QnA (KB) and agent
Utterance: What is the maximum contribution amount for espp? Send an email to Robert with the details.
* Non-agentic response: Produces a single answer and doesn't complete or even suggest the second action since there's no corresponding skill.
* Agentic response: Understands the two separate intents and executes them in sequence while using the output from the first intent to fulfill the second intent.
{#agentic-conversations-vad__ul_iyp_2sq_hfc}
## Halting and restarting agentic conversations {#agentic-conversations-vad__section_slj_3zp_sfc}
If you want to stop an agentic conversation mid-query, hover over the send icon ![Send icon.]() while the agent is researching a query. The icon becomes an interrupt flow icon ![Interrupt flow icon.](). Select the icon and the conversation stops. A message appears: The current conversation has been stopped, but you can begin again. Enter a new query to restart the agentic conversation.
## Error handling and fallback options {#agentic-conversations-vad__section_hwh_kys_k3c}
When the AI agent cannot understand a request, encounters a system error, or a session becomes inactive, it displays a message and presents options to help you continue.
* When ServiceNow Otto cannot find an answer:
Depending on how your administrator has configured the assistant, these options may include:
* Requesting a live agent.
* Creating a support request.
* Viewing office hours
{#agentic-conversations-vad__ul_ztc_3rt_k3c}
For example, if you ask about a topic the AI agent cannot find information on, you might see a message such as: "I can't find anything on that directly but I can help you explore other options." Select one of the
displayed options to continue.
* Session timeout due to inactivity:If you stop responding during a conversation, the AI agent waits for a set period before ending the session. When a session is about to time out, you will receive a warning message. For
example: "Looks like you've left this conversation. Would you like to keep going?". If you want to continue, respond to resume the conversation.
If there is no response to the warning, the session ends with a session end
message. For example, "Our chat has timed out due to inactivity. Just start a new conversation whenever you're ready. I'll be here to help!". You can start a new chat to continue getting help.
* Technical errors and system timeout:
If the AI agent encounters a backend error or cannot complete a request due to a technical issue, it displays a message and presents fallback options. For example: "It looks like I'm having trouble completing your request
right now because of a technical failure. But I can help you explore other options." You can select one of the available fallback options to continue.
* Errors during agentic tasks:
When you ask the AI agent to complete a multi-step task on your behalf, it plans and carries out the steps automatically. If a step in the plan cannot be completed, it lets you know and offers fallback options so you can
decide how to proceed.
For example, if the AI agent is creating an expense report and encounters a problem, it displays a message such as: "Unfortunately that didn't work. But I can help you explore other options." The fallback options available
depend on your configuration.
{#agentic-conversations-vad__ul_cfg_qrt_k3c}
Note:
Review AI generated responses for accuracy before taking action.