{"repo":"Ge-limin/ai-native-engineering-manifesto","free":true,"listed":false,"github":"https://github.com/Ge-limin/ai-native-engineering-manifesto","clone":"git clone https://github.com/Ge-limin/ai-native-engineering-manifesto.git","description":"A manifesto and playbook for AI-native software engineering in the LLM era / AI-Native的软件工程宣言","language":null,"stars":317,"topics":["agentic-coding","ai-agents","ai-coding","ai-native","best-practices","claude-code","context-engineering","cursor","developer-productivity","engineering-culture"],"license":"CC-BY-4.0","category":"ai-agents","readme_excerpt":"AI-Native Engineering Manifesto (English) 中文版请见：AI-Native 工程宣言（中文） Extended deep-dive chapters live under chapters/ , expanding several of the 11 hard truths into full articles. 📖 E-book : a curated, book-style web edition lives at liminge.space/manifesto. --- Table of Contents - AI-Native Software Engineering - AI-Native Engineering: 11 Hard Truths for 2025 - Extended Chapters: AI-Native Engineering Practices - March 2025 - May 2025 Revision - December 2025 Revision - May 2026 Revision AI-Native Software Engineering Author Limin Ge --- --- First Draft March 2025 Revisions May 2025, December 2025, May 2026 --- AI-Native Engineering: 11 Hard Truths for 2025 1. If a knowledge, methodology, or tech stack is older than 3 years, it’s obsolete until proven otherwise. 2. Your codebase, your docs, your meeting notes — none of these are your backbone. Your only reliable, compounding asset is your test case library. 3. To truly understand AI, you must understand its nature: AI is completely, fundamentally stateless. 4. We can accept AI making mistakes — as long as those mistakes don’t kill the team before the next model upgrade. 5. Software complexity must flatten. We’re moving from deep, vertical stacks to wide, horizontal systems. 6. The context window is the most critical computational resource every engineer must master. 7. Plan–Act, Test–Code, and Doc–Code–Doc are the new operating system of engineering. 8. The future of code isn’t abstraction — it’s tiny, isolated, AI-readable u","default_branch":null,"files":null,"tree":[],"storefront":"/r/Ge-limin","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/Ge-limin/ai-native-engineering-manifesto/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}