Open-sourced my complete AI-native architecture series from a solo builder project (spare time).

4 articles (EN/ZH) covering: - Constrained DSL for reliable LLM decisions - 60/40 → 90/10 AI-driven development workflow - "Boring" hybrid agent architecture - Low-cost multi-vendor cloud scaling

Real scale: 28 repos, 538k LOC, 3k+ users, low four-digit RMB yearly infra.

Repo: https://github.com/myinvestpilot/ai-architecture

Pure sharing, no promo. Feedback, critiques, or your solo AI-native experiences welcome!

Thanks