AI Agent

ℹ️

AI Agent – a virtual assistant that understands what the customer wants and easily directs them to the right flow or action. You can define which details or parameters the agent should collect from the customer to complete the action smoothly. The AI Agent can also provide information directly from your company’s knowledge base.

What Is the AI Agent?

An AI Agent is a trained assistant designed to:

Understand customer intent using natural language.

• Ask the right questions to gather all necessary details.
• Trigger specific actions or flows.
• Serve information based on existing knowledge base content.

Example:

You can create an AI Agent for booking flight tickets. If a user writes:

"I want to fly to Athens"...

the AI Agent will ask for relevant parameters (dates, number of passengers, etc.), collect the answers, and trigger the relevant action to book the flight.
The AI Agent can also act as a hub: If a customer asks about a different issue (e.g., change a meal), the agent will redirect them to the proper flow, handled by a more specific AI Agent.

How to Access the AI Agent Feature

Path:Settings → Chatbot and AI → AI Chatbot → AI Agent

How to Create an AI Agent

Step 1:

Choose a Template or Start Blank
Click Add to start a new AI Agent. You can:

• Start with a Blank Agent
• Use a template like “Conversation Routing Agent” or “Knowledgebase Query + Human Handoff”

Step 2:

Fill in Agent Details

• Agent Name: Give your agent a clear name.
• Agent Behavior (limit: 5000 characters): Define the agent’s purpose.

Example:

“You are a travel agent. Your goal is to help users find flights, make bookings, and provide support related to air travel.”

Step 3:

Add Actions

You must define at least one action for your agent.

• Action Name: A friendly label.
• AI Action Name: For internal use.
• "When to Use" (limit: 1000 characters): Describe when this action is relevant.

• Use this agent everytime a customer want to book a flight.

• Parameters: Define what data the agent should collect (no limit on the number of parameters).

🚧

You can add multiple actions (up to 20 per agent).

Step 4:

Connect to Knowledge Base (Optional)
Enable access to your knowledge base and select specific categories for your AI Agent. This allows it to answer FAQs or provide product info using real company content.

Step 5:

Test Your Agent use the built-in test simulator to try out your agent’s responses.
Type a test message and see how your AI Agent responds.

Routing Agent vs. Domain-Specific Agent

Create dedicated agents for different tasks, with an agent router on top of them. By creating "blocks" of agents, each agent is focused on a specific task, which helps improve accuracy and intent recognition. Dividing the tasks to different agents also helps ensure that a change in one agent doesn't affect the other agents.
For example, one agent handles flight bookings, another handles inflight services, and one handles cancellations.

Routing Agent: This agent Acts as a smart router. It understands the customer’s general intent and passes them to the right flow or AI Agent. For example, if a customer asks about a booking, it will redirect them to the booking flow that uses the booking AI agent. If they ask about meal changes, it routes them to the meal service flow, which will use the specific AI agent for inflight meal updates. Usually, the AI Agent router will be the first touch point in the flow.

Domain-Specific Agent: Built to complete tasks from start to finish. For example, an agent that collects all information needed to book a flight.

Next Steps

Congratulations! Now that you have an AI Agent configured, you have to add it to a flow to use it.