Find answers in our Knowledge Base
AI Agent
15
Comm100 AI Agent is an intelligent virtual agent that uses Large Language Models (LLMs) to understand customer requests, provide relevant answers, and perform configured actions. It can use your Knowledge and configured workflows to respond to customer ...
Comm100 AI Agent can be applied to Live Chat, social (WhatsApp, WeChat, Twitter, Facebook, Instagram, LINE, and Telegram), Messenger, Signal, and SMS channels to help improve your customer service. Using an AI Agent to reach out to your customers brings...
Introduction to AI Agent TopicsA Topic represents the subject or purpose of a customer conversation. Topics help you group customer requests with similar intents and define how the AI Agent should respond when a Topic is matched. You can use Topics to p...
Comm100 AI Automation offers a wide range of automation features by leveraging AI and generative AI. In Comm100, we use AI Credits to track the usage of AI Automation features. The AI Credit volume is shared across all AI features on the same site.The...
IntroductionAI Agents can generate responses through analysis of the extensive Knowledge sources you provide using Large Language Models (LLMs). These responses are not predefined or stored in a database; they are automatically generated to provide cohe...
A Function is a predefined or dynamic task that the AI Agent can invoke during a conversation. Functions and MCP Servers allow the AI Agent to go beyond its knowledge base by retrieving real-time data, processing complex tasks, interacting with external...
Comm100 AI Agent allows you to send data to and receive data from an external server or third-party services using Webhook. You can use a Webhook action in the AI Agent's workflow to push data to or get data from your own system automatically whenever a...
Comm100 provides a variety of actions for building AI Agent response flows. When configuring AI Agent Topics and Events, you can use these actions to define how the AI Agent responds and performs actions during a conversation. The following table lists ...
When configuring a Topic or Event, you can use the Condition action in a By Workflow response to direct the AI Agent to different actions based on predefined rules. Conditions can evaluate conversation data, Variables, visitor or ticket information, Cus...
When creating a Topic for an AI Agent, you can define the Topic answer by workflow or by natural language. Using natural language allows you to give instructions to tell the AI Agent what to do if the topic matches, making it well-suited for scenarios t...
Events are triggers that prompt the AI Agent to take predefined actions when specific situations occur during a conversation. For example, when a conversation starts, or when the AI Agent cannot answer a customer’s question, the AI Agent can automatical...
AI Agent's capability evolves in its practical usage. When the AI Agent cannot provide an answer by matching a Topic or retrieving Knowledge content, or when visitors give a thumbs-down to an answer, these questions are collected in the Learning section...
Topic Matching Sensitivity controls how confident the AI must be when matching a visitor’s question to a specific Topic. You can set a threshold from 0 to 100, which tells the AI the minimum similarity score a Topic must reach to be considered a match. ...
LLM Functions enable your AI Agent to perform tasks such as extracting structured data, summarizing conversations, classifying intent, or generating responses using a large language model. Instructions define what the model should do and how to return t...
AI Agent Test Center enables you to validate your AI Agent by creating reusable test cases, executing them in batches, and reviewing the test results. It helps you verify that your AI Agent matches the correct Topics and returns the expected responses, ...