# Chat Live Chat with raia is one of the core communication skills available to any AI Agent built on the raia platform. {% hint style="success" %} **Chat is an app that is part of the raia cX Suite.** {% endhint %} *** #### 🔧 **Setup and Customization** Live Chat is enabled by default as a basic skill on every new agent and can be configured during the agent creation process within the Launch Pad wizard. Users can: * Set a **Welcome Message** and introduction text * Define **predefined replies** and a **disclaimer** * Customize the **chat widget’s appearance** (color, icon, branding) * Add **custom links** to support content or CTAs * Restrict access by IP or geography A live preview shows how the chat will look and behave in real-time, so users can test interactions before deploying. *** #### 💬 **Live Chat Experience for End Users** Once deployed: * The Live Chat widget appears on websites or portals. * Users can interact with the AI Agent in a real-time chat interface. * Conversations happen asynchronously or in real-time and are recorded in threads for auditing and improvement. Live Chat supports **public and anonymous access**, meaning end users can start chatting without logging in. *** #### 👥 **Roles and Oversight** * Admins can view and manage all live chat threads in **Copilot**, raia’s interface for monitoring, training, and interacting with AI Agents. * Admins and authorized users can **take over live conversations** in real-time using "human-in-the-loop" mode. * Conversations are scored (1-10) to track interaction quality and effectiveness. *** #### 🧠 **Training and Feedback** * Every live chat conversation can be rated by users or admins. * Feedback (thumbs up/down, suggested responses) can be submitted via CoPilot, enabling rapid iteration and continuous training. *** #### 🔐 **Security and Control** * Live Chat is hosted on SOC2-compliant infrastructure. * Organizations can control access to agents and chats using permissions (Admin, Authenticated User, Public User). * Detailed logs and conversation history are stored and searchable. #### --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.raiaai.com/applications/chat.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.