最近团队在推进“测试智能体”落地，我基于 Playwright 封装了三个核心 AI Agent，分别负责 用例生成、自动执行与自愈、结果断言分析。三者在工作流中协作，让 Web 自动化测试的编写与维护成本降低了约 60%。下面是完整实操记录，所有命令均可直接复现。 一、整体架构 Agent 1 – 用例生成器：根据自然语言需求或 Swagger 文档，调用 RAG + Playwright 代码 ...

Model Context Protocol (MCP) 这个协议简单说就是给大语言模型接入外部数据和工具提供了一套标准化方案。MCP 统一了模型和各种数据源、工具服务之间的交互方式。 FastMCP 是目前用 Python 构建 MCP 服务器最顺手的框架，把底层那些复杂的协议实现全都封装好了，开发者 ...

OpenAI is rolling out support for MCP, an open-source technology that large language models can use to perform tasks in external systems and access the data they contain. OpenAI Chief Executive ...

Microsoft has announced Playwright, a tool that lets developers write tests in Python for web applications across Chrome, Chromium-based Edge, Apple Safari and Mozilla Firefox. Playwright, a Python ...

What if your coding assistant could do more than just write lines of code? Imagine it stepping into the role of a full-fledged UI designer, creating polished, responsive, and accessible interfaces ...

Microsoft's AI Toolkit extension for VS Code now includes a Tool Catalog that can scaffold a Python or TypeScript MCP server with the core transport and registration plumbing already set up. In ...

Microsoft today announced the release of the Python version of Playwright, a framework for end-to-end testing of web applications in Python. Playwright is the latest in a slew of Microsoft-created ...