Agentic conversations in Virtual Agent
Summarize
Summary of Agentic conversations in Virtual Agent
Agentic conversations in Virtual Agent enhance the way the Virtual Agent understands and processes user queries by leveraging AI agents, virtual agent topics, conversational actions, skills, and knowledge base (KB) articles. This capability allows the system to reason, plan, and execute complex tasks by orchestrating multiple agents and skills automatically. When specific agents are unavailable for a task, the system uses a Search Agent to find relevant answers or skills within the assistant’s scope.
Show less
Enabling AI Agents in Virtual Agent
To enable AI agents, administrators or virtualagentadmins must create and configure multiple assistants with defined scopes and assign them to portals. Key steps include:
- Creating or using default assistants.
- Assigning assistants to portals, channels, or mobile apps.
- Adding AI agent skills to assistants.
- Mapping or publishing AI agents to assistants in AI Agent Studio so they become available during conversations.
Only configured AI agents for a given assistant are considered during execution, allowing dynamic orchestration for planning and task completion.
Practical Examples of Agentic Behavior
Agentic conversations break down complex user requests into manageable tasks, enabling step-by-step execution and improved user experience compared to non-agentic responses, which often provide single, mixed answers or fail to execute multiple tasks.
- Scenario 1 (Multiple KB questions): Breaks multiple questions into separate queries and delivers precise answers for each.
- Scenario 2 (Multiple skills with slot filling): Separates requests such as ordering coffee and food into distinct tasks and executes them sequentially.
- Scenario 3 (Complex tasks with agents and QnA): Understands dependencies among multiple tasks like expense reports and IT ticket statuses, executing them in order and using outputs contextually.
- Scenario 4 (QnA and agent combination): Recognizes separate intents such as retrieving ESPP policy info and sending email, performing both actions sequentially.
Controlling Agentic Conversations
Users can interrupt an ongoing agentic conversation by hovering over the send icon during query processing, which changes to an interrupt flow icon. Selecting this stops the conversation, allowing users to start a new query and restart the agentic process.
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.