vercel · Vercel AI SDK Docs

AI SDK Agents: Overview

An introduction to building AI agents using the AI SDK, covering core concepts and the architectural approach to agentic workflows.

Derived skill

Files assembled from official documentation

Viewing SKILL.md

An introduction to building AI agents using the AI SDK, covering core concepts and the architectural approach to agentic workflows.

Use when you need to understand the fundamental architecture and design patterns required to implement autonomous AI agents using the AI SDK.

File	Contains	Use For
`SKILL.md`	Entry point: scope, routing table, and workflow.	Start here.
`docs/ai-sdk-agents-overview-workflow-guide.md`	An overview of AI SDK agents explaining how large language models use tools in a loop to accomplish tasks using the ToolLoopAgent class.	Questions about an overview of AI SDK agents explaining how large language models use tools in a loop to accomplish tasks using the T...
`examples/ai-sdk-agents-overview-ai-sdk-toolloopagent-typescript.text`	A TypeScript code example demonstrating the implementation of a ToolLoopAgent using the AI SDK with a weather tool.	Exact payloads, commands, or snippets shown in A TypeScript code example demonstrating the implementation of a ToolLoopAgent using the AI SDK with a weather tool.

Agents are large language models (LLMs) that use tools in a loop to accomplish tasks.
Main sections: ToolLoopAgent Class, Why Use the ToolLoopAgent?, Structured Workflows, Next Steps.

Open the most relevant file under docs/ for the exact documented workflow and wording.
Open schemas/ files for exact structured contracts.
Open examples/ files for concrete requests, commands, snippets, and manifests.
Do not add behavior or configuration that is not present in the attached source files.