背景
问题
改造庭院让人无从下手：一张灵感照片说不清材料、数量、工具和步骤，也说不清哪里会出错——而多数工具只会像聊天机器人一样给出自信的猜测。
方法
方案
这是一个结构化的规划应用，而不是聊天机器人：确定性引擎才是真正的依据，完全离线、无需 AI 密钥和照片也能工作——AI 只负责润色已生成的方案。每份方案都基于区域化目录（以安大略为先）、价格区间而非虚假精确价、在未测量时自动放宽的用料计算，以及分阶段的操作指南。
功能
- Deterministic planning engine as the source of truth
- Local-first storage with optional Supabase cross-device sync
- Free/Open Data Mode — works with no paid API
- Region-aware retailer links and honest price bands
- Optional AI presentation (Claude) with silent fallback
- On-device photo segmentation (TensorFlow.js)
架构笔记
- The deterministic engine owns the truth; AI and live data only enrich, never override.
- Local-first by design — the plan never waits on the network; cloud sync sits behind the local layer.
- Every live fact carries a source, a confidence tag, and a 'last checked' time.
挑战
结果
A working local-first planning app live at bloomprint.online that chooses honest grounding — sourced facts, confidence tags, price ranges — over confident AI guesswork.
学到的东西
复盘
- 01Deterministic-first earns trust a chatbot-first tool can't.
- 02Honest hedging — ranges, 'verify before buying' — reads as more credible than false precision.
- 03Local-first changes every assumption about state, sync, and failure.
下一步
下一步
- 01Expand the catalog beyond Ontario
- 02Wire real live-data providers
- 03Add collaborative plans