The AI Agent enables the chatbot to automatically respond to users using artificial intelligence, interpreting questions and generating answers based on a configured context. This makes support more natural, flexible and capable of handling open-ended questions.
Unlike rigid flows with buttons or fixed paths, the AI Agent understands the user's message intent and responds dynamically.
When the AI Agent is active in the chatbot:
The user sends a message.
The AI analyzes the content of the question.
The system queries the configured context (information, rules or knowledge base).
The AI generates an appropriate response and sends it to the user.
This allows answering questions such as:
Service hours
Information about products or services
Frequently asked questions
General guidance
All without the need to create a specific flow for each question.
To create your AI Agent, see the article below:
AI Agents - Initial SettingsConfiguring the MCP AI Agent - Creating an Agent to Rewarm LeadsThe AI Agent can be used at different points in the chatbot, for example:
Initial support to answer general questions
Automatic support before routing to an agent
Flow supplement, when the user asks questions outside the bot's script
Knowledge base, answering questions about products, services or processes
To obtain better answers, it is important to properly configure the AI context.
It is recommended:
Insert clear information about the company
Define service rules
Include frequent questions and answers
Provide products, services and hours
The more complete the context, the more accurate the AI's responses will be.
Even when using AI, the chatbot can transfer the user to an agent when necessary.
Some examples:
When the AI does not know how to answer
When the user requests to speak with an agent
When human support is required
Thus, the AI Agent helps to automate a large part of conversations, but retains the possibility of human support when needed.
✅ Tip: The AI Agent can be combined with traditional chatbot flows, using menus, buttons and automations to create a more complete support experience.
Last updated
Was this helpful?
Was this helpful?
