Agentic conversations in Virtual Agent
Summarize
Summary of Agentic conversations in Virtual Agent
Agentic conversations in Virtual Agent enable the assistant to understand complex user queries by reasoning, planning, and executing actions across multiple AI agents, virtual agent topics, skills, catalogs, knowledge base articles, and Now Assist supported skills. This capability allows the Virtual Agent to handle multi-step and multi-intent requests efficiently by orchestrating multiple agents and skills to fulfill user tasks and subtasks automatically.
Show less
Key Features
- Multi-agent orchestration: The Virtual Agent can dynamically use specific AI agents configured for tasks or resort to a Search Agent to find relevant skills or information when no specific agent is available.
- Assistant and portal configuration: Admins can create multiple assistants with defined scopes, assign them to portals, and add AI agent skills for targeted user interactions.
- Execution planning: The system plans and sequences the execution of multiple skills and agents to complete complex user requests, leveraging outputs from prior actions as context.
- Interrupt and restart capabilities: Users can halt an ongoing agentic conversation mid-query and restart a new one as needed, providing control over the interaction flow.
Examples of Agentic Behavior
- Handling multiple questions from KB articles: Splits compound questions into individual queries and provides separate, precise answers rather than a mixed response.
- Executing multiple skills with slot filling: Breaks down requests involving ordering different items (e.g., coffee and food) into distinct tasks and executes them sequentially, completing the full request.
- Complex multi-skill requests: For multi-intent utterances involving agents, skills, and QnA, the Virtual Agent plans and executes dependent tasks in order, using earlier outputs as needed.
- Combining QnA and agent execution: Recognizes separate intents within a single query (e.g., retrieving policy info and sending an email) and processes them sequentially, even when no direct skill exists for one part.
Practical Implications for ServiceNow Customers
By enabling agentic conversations, ServiceNow customers can deliver more intelligent, context-aware Virtual Agent experiences that handle complex, multi-step user requests seamlessly. This reduces the need for manual intervention and improves user satisfaction by providing precise, actionable responses and task execution. Administrators should configure assistants, portals, and AI agents carefully to tailor the Virtual Agent’s capabilities to organizational needs.
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 Now Assist in 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 for the task or sub task, 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.
Enable AI agents in Virtual Agent
Role required: admin or virtual_agent_admin
- 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
- Assigning specific assistants to a specific portal or portals. For more information, see Display your chat assistant on a portal, channel, or mobile app.
- Ensure that the AI agents skill is added to the assistant.
- 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.
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
| 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 |
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.
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.
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, completing the entire user request using output from prior actions as context as needed.
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.
Halting and restarting agentic conversations
If you want to stop an agentic conversation mid-query, hover over the send icon 
while the agent is researching a query. The icon becomes an 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.