[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-81649":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":9,"language":10,"languages":9,"totalLinesOfCode":9,"stars":11,"forks":12,"watchers":13,"openIssues":14,"contributorsCount":14,"subscribersCount":14,"size":14,"stars1d":15,"stars7d":15,"stars30d":15,"stars90d":14,"forks30d":14,"starsTrendScore":13,"compositeScore":16,"rankGlobal":9,"rankLanguage":9,"license":9,"archived":17,"fork":17,"defaultBranch":18,"hasWiki":19,"hasPages":17,"topics":20,"createdAt":9,"pushedAt":9,"updatedAt":21,"readmeContent":22,"aiSummary":23,"trendingCount":14,"starSnapshotCount":14,"syncStatus":24,"lastSyncTime":25,"discoverSource":26},81649,"ai-qa-learning-roadmap","duveyvaishnavi-stack\u002Fai-qa-learning-roadmap","duveyvaishnavi-stack","Free kit — AI + RAG + MCP for QA engineers. Working code + 5-week learning roadmap",null,"TypeScript",22,5,3,0,1,2.33,false,"main",true,[],"2026-06-12 02:04:17","# 🤖 AI QA Orchestration — Full Learning Kit\n\n> Everything you need to go from manual QA to AI-powered test pipelines.\n> Built and maintained by [Vaishnavi Duvey](https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fvaishnve-duvey-53b9a8143\u002F) — QA Manager & AI Testing \n\n![Python](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPython-3.9+-blue)\n![Playwright](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPlaywright-TypeScript-green)\n![Claude](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPowered%20by-Claude%20AI-purple)\n\n💡 Why I built this\n\nSomeone asked me: \"Is there any way I could learn how to build these?\"\nSo I built a free learning kit.\nThis repo started from a LinkedIn post that got 10,378 impressions — proof that QA engineers want practical AI content, not theory. Everything here is what I actually built and learned, shared openly so you don't have to figure it out alone.\n\n\"This is the kind of AI-in-QA content that feels practical instead of theoretical.\"\n— Comment from the LinkedIn community\n\n\n🚀 How to use this repo\nIf you're a beginner:\n\nStart with the 5-week roadmap below — follow it week by week\nRead the architecture section — plain English explanation\nRun orchestrator.py — see AI generate real tests in 3 minutes\n\nIf you're intermediate:\n\nClone the repo and run orchestrator.py immediately\nSwap the story variable with your own user story\nUpdate standards with your team's conventions\nStar the repo — Stage 2 + 3 dropping this week\n\nIf you're advanced:\n\nFork the repo and contribute MCP connectors or RAG improvements\nOpen a PR — reviewed within 24 hours\nTag me on LinkedIn when you ship something with it!\n\n---\n\n## 📌 What is this?\n\nThis repo is a **free, complete kit** for QA engineers who want to build AI-powered testing pipelines using:\n\n- 🤖 **Claude AI** (Anthropic) — reads stories, generates test cases, writes Playwright specs\n- 🔌 **MCP** (Model Context Protocol) — connects AI to Jira, GitHub, TestRail automatically\n- 📚 **RAG** (Retrieval Augmented Generation) — gives AI your private codebase knowledge\n\nNo fluff. No theory. Just working code and a clear learning path.\n\n---\n\n## 🗂️ What's inside\n\n```\nai-qa-learning-roadmap\u002F\n│\n├── 📄 README.md                  ← You are here\n├── 🐍 orchestrator.py            ← Working AI QA pipeline (start here)\n├── 📁 examples\u002F\n│   └── STORY-1042.spec.ts        ← Example Playwright output generated by AI\n├── 📁 docs\u002F\n│   ├── architecture.png          ← Pipeline architecture diagram\n│   ├── ROADMAP.md                ← 5-week learning roadmap\n│   └── HOW_IT_WORKS.md           ← Plain English explanation of AI + RAG + MCP\n└── 📁 coming-soon\u002F\n    ├── jira-mcp-connector.py     ← Stage 2 — Jira MCP (coming this week)\n    └── rag-layer.py              ← Stage 3 — RAG with pgvector (coming soon)\n```\n## 📅 Weekly content\n\n| Week | Topic | Status | Guide |\n|------|-------|--------|-------|\n| 1 | Python + Anthropic API | ✅ Live | Run `orchestrator.py` |\n| 2 | Prompt Engineering | ✅ Live | [WEEK2-PROMPT-ENGINEERING.md](.\u002FWEEK2-PROMPT-ENGINEERING.md) |\n| 3 | RAG + Vector Databases | 🔜 Coming soon | — |\n| 4 | MCP Connectors | 🔜 Coming soon | — |\n| 5 | AI Agents + Orchestration | 🔜 Coming soon | — |\n\n⭐ Star the repo to get notified when each week drops!\n---\n\n## ⚡ Quick start — run it in 3 minutes\n\n```bash\n# 1. Clone the repo\ngit clone https:\u002F\u002Fgithub.com\u002Fduveyvaishnavi-stack\u002Fai-qa-learning-roadmap\n\n# 2. Install dependencies\npip install anthropic\n\n# 3. Set your API key (get it free at console.anthropic.com)\nexport ANTHROPIC_API_KEY=sk-ant-your-key-here   # Mac\u002FLinux\nset ANTHROPIC_API_KEY=sk-ant-your-key-here       # Windows\n\n# 4. Run the pipeline\npython orchestrator.py\n\n# Output: STORY-1042.spec.ts — ready-to-run Playwright file ✅\n```\n\n---\n\n## 🏗️ Architecture\n\n```\n┌─────────────────────────────────────────────────┐\n│              MCP Tools Layer                     │\n│   Jira · GitHub · TestRail · Slack              │\n└──────────────────┬──────────────────────────────┘\n                   ↓\n┌─────────────────────────────────────────────────┐\n│            AI Orchestrator                       │\n│  Claude reads stories · generates tests          │\n│  writes Playwright specs · opens PRs             │\n└──────────────────┬──────────────────────────────┘\n                   ↓\n┌─────────────────────────────────────────────────┐\n│           RAG Knowledge Layer                    │\n│  Your codebase · standards · past incidents      │\n│  Embedded in pgvector (free)                     │\n└─────────────────────────────────────────────────┘\n```\n\n---\n\n## 🗺️ 5-Week Learning Roadmap\n\n| Week | Topic | Resources | Cost |\n|------|-------|-----------|------|\n| 1 | Python + Anthropic API | [docs.anthropic.com](https:\u002F\u002Fdocs.anthropic.com) · [Python for Everybody](https:\u002F\u002Fcoursera.org\u002Fspecializations\u002Fpython) | Free |\n| 2 | Prompt Engineering | [Anthropic Prompt Guide](https:\u002F\u002Fdocs.anthropic.com\u002Fen\u002Fdocs\u002Fbuild-with-claude\u002Fprompt-engineering\u002Foverview) · [DeepLearning.AI](https:\u002F\u002Fdeeplearning.ai\u002Fshort-courses) | Free |\n| 3 | RAG + Vector DBs | [Building RAG — DeepLearning.AI](https:\u002F\u002Fdeeplearning.ai\u002Fshort-courses\u002Fbuilding-evaluating-advanced-rag) · [pgvector](https:\u002F\u002Fgithub.com\u002Fpgvector\u002Fpgvector) | Free |\n| 4 | MCP Connectors | [modelcontextprotocol.io](https:\u002F\u002Fmodelcontextprotocol.io) · [MCP Servers](https:\u002F\u002Fgithub.com\u002Fmodelcontextprotocol\u002Fservers) | Free |\n| 5+ | AI Agents + Orchestration | [AI Agents in LangGraph](https:\u002F\u002Fdeeplearning.ai\u002Fshort-courses\u002Fai-agents-in-langgraph) | Free |\n\n> 💡 **Best way to learn:** Follow this repo — each stage ships as working code you can run and study.\n\n---\n\n## 🚀 Pipeline stages\n\n### ✅ Stage 1 — AI Core (available now)\n- Reads user stories\n- Generates happy path + edge cases + negative tests\n- Writes ready-to-run Playwright TypeScript spec files\n\n### 🔧 Stage 2 — MCP Connectors (coming this week)\n- Jira MCP — auto-fetch stories when they move to \"Ready for QA\"\n- GitHub MCP — auto-open PRs with generated spec files\n- Zero keyboard interaction between story and PR\n\n### 🧠 Stage 3 — RAG Layer (coming soon)\n- Embed your codebase, page objects, and standards\n- AI generates tests using YOUR selectors and conventions\n- Tests look like a senior QA on your team wrote them\n\n---\n\n## 💬 From the community\n\n> *\"This is the kind of AI-in-QA content that feels practical instead of theoretical.\"*\n\n> *\"The interesting part is not the 60 lines of Python. It's the orchestration thinking behind it.\"*\n\n> *\"Where is the MCP and RAG layer?\"* — Stage 2 dropping this week! ⬆️ Star to get notified\n\n---\n\n## 🤝 Contributing\n\nFound a bug? Want to add a connector? PRs welcome!\n\n1. Fork the repo\n2. Create your branch: `git checkout -b feature\u002Fjira-mcp`\n3. Commit your changes\n4. Open a PR — I review within 24 hours\n\n---\n\n## 👩‍💻 About the author\n\n**Vaishnavi Duvey** — QA Manager & Business Analyst | AI-Assisted Testing & Automation\n\nI share practical AI + QA content every week on LinkedIn.\n\n🔗 [LinkedIn](https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fvaishnve-duvey-53b9a8143\u002F) · ⭐ [Star this repo](https:\u002F\u002Fgithub.com\u002Fduveyvaishnavi-stack\u002Fai-qa-learning-roadmap)\n\n---\n\n## ⭐ If this helped you\n\nGive it a star — it helps more QA engineers find this resource!\n\n⭐ [Star this repo](https:\u002F\u002Fgithub.com\u002Fduveyvaishnavi-stack\u002Fai-qa-learning-roadmap) — it helps more QA engineers find this!\n\n---\n\n*Built by Vaishnavi*\n","该项目提供了一套免费的工具包，旨在帮助QA工程师从手动测试过渡到基于AI的测试流水线。核心功能包括使用Claude AI自动生成测试用例和编写Playwright测试脚本，通过MCP协议自动连接Jira、GitHub等平台，并利用RAG技术增强AI对私有代码库的理解。项目采用TypeScript编写，并附带了一个为期5周的学习路线图，适合不同水平的QA工程师学习实践。无论是初学者还是有一定经验的技术人员，都能在这个项目中找到合适的起点，逐步掌握如何构建和优化自己的AI驱动测试流程。",2,"2026-06-11 04:05:50","CREATED_QUERY"]