# prai ## Documentation - [Introduction](/getting-started/introduction): Get started with prai - [Your First Workflow](/getting-started/first-workflow): Build a complete prai workflow from scratch - [Special Step Types](/getting-started/special-step-types): prai provides specialized step functions beyond the basic `step()` function for common data processing patterns like filtering data, combine results, and perform other operations in AI workflows. - [Advanced Usage](/getting-started/advanced-usage): This guide covers advanced **prai** features and patterns for building advanced AI workflows. - [Best Practices](/getting-started/best-practices): guidelines and optimization tips for building reliable, maintainable, and performant prai workflows - [Steps](/concepts/step): What is a prai step? - [Models](/concepts/model): What is a prai model? - [History](/concepts/history): What is prai's history? ## MCP Server This documentation is available via Model Context Protocol (MCP) server at https://docs.pmnd.rs/api/mcp Configure in your MCP client: ```json { "mcpServers": { "pmndrs": { "type": "http", "url": "https://docs.pmnd.rs/api/mcp" } } } ``` --- For full documentation content, see llms-full.txt