Proteus

s. - *Real editor, not a toy*: Phase 1 is complete with a working demo. You can create shapes, text, images, transform them, copy/paste, undo/redo—all the core editor capabilities. - *Learning resource*: If you want to understand how editors work (scene graphs, rendering, interaction systems) or how to structure code for AI collaboration, this is a live case study. *Current status:* Phase 1: Core editing (scene graph, rendering, interaction, tools) Phase 2: Multimodal elements (video, audio, web embeds) Phase 3: AI Agent integration (natural language → editor actions) Phase 4: Real-time collaboration *Try it:* [Live Demo](https://proteus.gezilinll.com/) *Code:* [GitHub](https://github.com/gezilinll/Proteus) *Articles:* [Tech Blog](https://github.com/gezilinll/Proteus/tree/main/articles) (4 articles so far, covering architecture, rendering, interaction design) *The experiment:* What happens when you stop reviewing AI's code and instead focus entirely on architecture, problem diagnosis, and guiding AI through testing and context-building? That's what I'm exploring here. Would love feedback from the HN community—especially from those building complex frontend apps or thinking about AI-native development workflows. --- ## Alternative Shorter Version (if character limit is an issue) *Title:* Proteus: An AI-native multimodal editor where AI writes 80% of the code *Description:* Building an open-source editor (Figma + Notion, AI-native) where AI writes most code while I focus on architecture and decisions. *Why:* In 2025, AI can code—so what becomes valuable? System design, technical decisions, and ownership. *What's different:* - AI-native from day one (not bolted on) - Fully transparent (all code + articles public) - Real editor (Phase 1 complete, working demo) - Learning resource (how editors work, AI-native architecture) *Status:* Phase 1 | Phase 2-4 *Demo:* https://proteus.gezilinll.com/ *Code:* https://github.com/gezilinll/Proteus *Articles:* https://github.com/gezilinll/Proteus/tree/main/articles Experimenting with: What happens when you stop reviewing AI code and focus on architecture + problem diagnosis?

s. - *Real editor, not a toy*: Phase 1 is complete with a working demo. You can create shapes, text, images, transform them, copy/paste, undo/redo—all the core editor capabilities. - *Learning resource*: If you want to understand how editors work (scene graphs, rendering, interaction systems) or how to structure code for AI collaboration, this is a live case study. *Current status:* Phase 1: Core editing (scene graph, rendering, interaction, tools) Phase 2: Multimodal elements (video, audio, web embeds) Phase 3: AI Agent integration (natural language → editor actions) Phase 4: Real-time collaboration *Try it:* [Live Demo](https://proteus.gezilinll.com/) *Code:* [GitHub](https://github.com/gezilinll/Proteus) *Articles:* [Tech Blog](https://github.com/gezilinll/Proteus/tree/main/articles) (4 articles so far, covering architecture, rendering, interaction design) *The experiment:* What happens when you stop reviewing AI's code and instead focus entirely on architecture, problem diagnosis, and guiding AI through testing and context-building? That's what I'm exploring here. Would love feedback from the HN community—especially from those building complex frontend apps or thinking about AI-native development workflows.