使用 Fast-Agent 构建链式工作流（Chain Workflow）的步骤如下：
- Generate workflow templates: Run
fast-agent bootstrap workflow生成包含链式工作流示例的目录。 - Defining Intelligence：编辑生成的
chaining.py文件，定义链式工作流中的智能体。例如：@fast.agent("url_fetcher", "Given a URL, provide a summary", servers=["fetch"]) @fast.agent("social_media", "Write a 280 character post for the text.") async def main(): async with fast.run() as agent: result = await agent.social_media(await agent.url_fetcher("http://example.com")) print(result) - Configuring the MCP Server: in
fastagent.config.yaml中配置 MCP 服务器的端点，例如：servers: fetch: type: "fetch" endpoint: "https://api.example.com" - Running a workflow: Implementation
uv run chaining.py，智能体将从指定 URL 获取内容并生成社交媒体帖子。
链式工作流适合需要按顺序执行任务的场景，如数据提取→处理→输出。
This answer comes from the articleFast-Agent: Declarative Grammar and MCP Integration for Rapidly Building Multi-Intelligent Body WorkflowsThe
May not be reproduced without permission:AI productivity tools " 如何使用 Fast-Agent 构建链式工作流？
English 
简体中文 
日本語 
Deutsch 
Português do Brasil