Skip to content

faq.mdx

Latest commit

 

History

History
79 lines (62 loc) · 3.85 KB

faq.mdx

File metadata and controls

79 lines (62 loc) · 3.85 KB
Raw
title Common Questions
description We've got answers to some common questions!
hideTOC true

Common Questions

We've got answers to some common questions!

A Copilot is a trusted partner that lives in your application to help your users get things done. There are two main types, the **Concierge** and the **Worker**. 
### Concierge

The Concierge Copilot understands your application's capabilities and full user context. It translates
high-level user intent into actions by serving as an intelligent intermediary.

For example, our [Banking Assistant](https://github.com/CopilotKit/CopilotKit/tree/main/examples/showcases/banking) implements Concierge Copilots
to help users manage their (_fake_) banking needs.


### Worker

The Worker Copilot is a domain-specific agent that can help users perform their core work tasks.
It serves as a partner to the user that is better at performing some tasks and worse at others.
Ultimately, it amplifies your users to produce better work than they thought possible. This pattern
is often used in backoffice copilots.

Think of the Worker Copilot as Cursor, Replit Agent, or Windsurf, but for any domain. For example,
see our [Open Researcher ANA](https://github.com/CopilotKit/CopilotKit/tree/main/examples/showcases/research-canvas).
### Batteries included chat components Beautiful, powerful and customizable chat components just an import away. | | | |---------|-------------| | **Chat** | Simple and powerful chat interface | | **Pop-up** | The Chat component in a pop-up format | | **Sidebar** | The Chat component in a sidebar format | | **Copilot Textarea** | Powerful AI autocompletion as a drop-in replacement for any textarea | | [**Headless**](/custom-look-and-feel/slots) | Full customization of the chat interfaces | 
### Deeply integrated Copilots
Give Copilots the ability to execute tools directly in your application.
|  |  |
|---------|-------------|
| **Copilot Readable State** | Enables Copilots to read and understand the application state |
| **Frontend Tools** | Copilots can execute tools in the application |
| [**Generative UI**](/generative-ui/your-components/display-only) | Render any component in the copilot chat interface |
| **AI Autosuggestions** | AI-powered autosuggestions in your AI chat interface |
| **Copilot Tasks** | Let your copilots execute tools proactively based on application state |

### Rich agentic experiences
Integrate your LangChain agents into your product with ease.
| |  |
|---------|-------------|
| **Deep support for LangChain** | Bring your LangChain agents directly into your product |
| **Human-in-the-loop** | Allow your users to work with your agents to solve complex problems |
| **Shared state** | Render the state of your LangChain agents with less than 10 lines of code |
Great question! CopilotKit has three main components: 1. **CopilotKit UI**: The UI components that you use to build your Copilots and Agents. 2. **CopilotKit Runtime**: The runtime that you use to build your Copilots and Agents. This serves as the backend for your Copilots and Agents. 3. **CopilotKit SDK**: In more complex applications, you'll use the SDK to deeply integrate CopilotKit into your agents. Yes! CopilotKit supports most LLMs, including OpenAI, Anthropic, Google, and more. In addition, you can use any LLM that is supported by LangChain. 
For more information, checkout our documentation on [bringing your own LLM](/built-in-agent/model-selection).