DesigningRealWorldAiAgentsWorkshop：系统从研究作为代码幻灯片视频

Hands-on workshop: Buildmulti-agent AI 系统从 scratch — Deep 研究 Agent + Writing Workflow served 作为 MCP servers. Includes 代码, 幻灯片,、视频GitHub 450 ⭐ / 126 Fork，主要使用 Python 开发。标签：ai-agent,ai-skills,ai-workflow,deep-research,mcp。访问项目：https://github.com/iusztinpaul/designing-real-world-ai-agents-workshop

项目介绍

Hands-on workshop: Buildmulti-agent AI 系统从 scratch — Deep 研究 Agent + Writing Workflow served 作为 MCP servers. Includes 代码, 幻灯片,、视频

核心功能

- Tool-use agents — letting the LLM decide which tools to call and when - Evaluator-optimizer loop — generate, review, edit in cycles - Grounded search — Gemini with Google Search grounding for factual research - Structured LLM output — Pydantic schemas for type-safe model responses - MCP server design — registering tools, resources, and prompts with FastMCP - LLM-as-judge evaluation — automated quality scoring with Opik

使用指南

> No cheating, by design. `implement_yourself/` is a self-contained project. Open your harness (Claude Code, Cursor, …) directly in that folder (not at the repo root) so its working directory is scoped to the skeleton. The agents can't see the reference implementation in `../src/`, can't grep it, can't read its files. You get a real build, not a copy-paste.

项目信息

项目地址

GitHub 仓库：<https://github.com/iusztinpaul/designing-real-world-ai-agents-workshop>

> 完整 URL：[https://github.com/iusztinpaul/designing-real-world-ai-agents-workshop](https://github.com/iusztinpaul/designing-real-world-ai-agents-workshop)

如需查看完整源码、安装命令、使用示例、API 文档，请直接访问上方项目地址。所有信息均以 GitHub 仓库为准。