What problem does it solve? Building AI agents that remember conversations, call tools, and stream responses requires stitching together state management, vector search, and real-time delivery. This Skill provides working patterns for implementing persistent, tool-using agents on the Convex backend platform. ## Core Features & Use Cases - Thread Management: Create, list, and query persistent conversation threads that survive restarts using the @convex-dev/agent component. - Tool Integration: Define Convex functions as agent tools (knowledge search, task creation, external API calls) with typed parameters. - Streaming & RAG: Stream tokens to clients in real time and perform vector search over embedded documents for retrieval-augmented generation. - Workflow Orchestration: Coordinate multi-step agent workflows such as research pipelines with status tracking. - Use Case: You are building a chat assistant in a Next.js app backed by Convex. Use this Skill to set up the agent component, persist threads, attach tools, and stream responses to a React chat interface. ## Quick Start Set up a Convex agent with thread management, tool calling, and streaming chat responses in my project.
