惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Blog — PlanetScale
Blog — PlanetScale
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
Vercel News
Vercel News
B
Blog
腾讯CDC
P
Proofpoint News Feed
Google DeepMind News
Google DeepMind News
N
Netflix TechBlog - Medium
L
LangChain Blog
F
Fortinet All Blogs
T
The Blog of Author Tim Ferriss
人人都是产品经理
人人都是产品经理
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
I
InfoQ
IT之家
IT之家
酷 壳 – CoolShell
酷 壳 – CoolShell
aimingoo的专栏
aimingoo的专栏
D
DataBreaches.Net
Stack Overflow Blog
Stack Overflow Blog
The Cloudflare Blog
Last Week in AI
Last Week in AI
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
博客园 - 三生石上(FineUI控件)
T
Tailwind CSS Blog

DEV Community

Authentication Security Deep Dive: From Brute Force to Salted Hashing (With Java Examples) Why AI Systems Don’t Fail — They Drift Spilling beans for how i learn for exam😁"Reinforcement Learning Cheat Sheet" I Replaced Chrome with Safari for AI Browser Automation. Here's What Broke (and What Finally Worked) How Python Borrows Other People's Work The $40 Architecture: Processing 1 Billion API Requests with 99.99% Uptime Vibe Coding: A Workflow Guide (From Zero to SaaS) Most webhook security guides protect the wrong side. The scary part is delivery. Headless CMS for TanStack Start: Build a Blog with Cosmic EU Age Verification App "Hacked in 2 Minutes" — What Actually Happened Comfy Cloud’s delete function does not actually remove files Running AI Models on GPU Cloud Servers: A Beginner Guide Event-driven media intelligence with AWS Step Functions and Bedrock I scored 500 AI prompts across 8 quality dimensions — here's what broke How to Call Google Gemini API from Next.js (Free Tier, No Backend Needed) The Portal Protocol: Reclaiming Human Connection in the Age of AI How to Fix Your Team's Scattered Knowledge Problem With a Self-Hosted Forum Intro to tc Cloud Functors: A Graph-First Mental Model for the Modern Cloud Designing Multi-Tenant Backends With Both Ownership and Team Access I Built a Neumorphic CSS Library with 77+ Components — Here's What I Learned PostgreSQL Performance Optimization: Why Connection Pooling Is Critical at Scale Cómo construí un SaaS multi-rubro para gestionar expensas en Argentina con FastAPI + Vue 3 🚀 I Built an Ethical Hacking Scanner Tool – Open Source Project I Replaced /usage and /context in Claude Code With a Single Statusline A Pythonic Way to Handle Emails (IMAP/SMTP) with Auto-Discovery and AI-Ready Design I Collected 8.9 Million Polymarket Price Points — Here's What I Found About How Markets Really Move EcoTrack AI — Carbon Footprint Tracker & Dashboard Everyone's Using AI. No One Agrees How. 5 self-hosted ebook managers worth trying in 2026 Building Your First AI Agent with LangChain: From Chatbot to Autonomous Assistant
Building Yarrow: an AI I Ching divination SaaS in a few w...
Master Saw · 2026-05-08 · via DEV Community
Cover image for Building Yarrow: an AI I Ching divination SaaS in a few weeks (Next.js + Supabase + Stripe + DeepSeek)

Master Saw

Hey 👋

Just shipped Yarrow — an I Ching ("Book of Changes") divination web app that uses an LLM to write the interpretation.

Live: https://iching.lifefinetuning.com

The flow

  • User types a question
  • 3 coins are tossed 6 times (the casting itself is pure logic, no AI)
  • The resulting King Wen hexagram (1 of 64) is identified, plus any changing-line transformation
  • An LLM steeped in the Wilhelm/Baynes tradition writes the reading
  • Responds in whatever language you asked in (English, Chinese, etc. — handled by the model)

Tech stack

  • Next.js 16 + Tailwind 4 + TypeScript on Vercel
  • Supabase (auth + Postgres + magic-link email via Resend)
  • Stripe (monthly $9.99 / annual $79)
  • DeepSeek for the AI (cheap, works well for both English and Chinese)
  • Resend for transactional email
  • PostHog for product analytics + Session Replay

Things I think are interesting

  • The hexagram engine is pure logic, not AI. I encode all 64 hexagrams as binary strings and look up the King Wen number. The AI only writes the interpretation — it can never hallucinate a hexagram.
  • Each reading gets a public shareable URL (/r/[id]) with its own dynamically generated OG image (your question + the hexagram visual).
  • Anti-abuse: anonymous quota uses an IP+UA hash (not a cookie), so clearing cookies doesn't reset it. Reading slots are reserved BEFORE the AI call so people can't disconnect mid-stream to skip the count.

Free tier

  • 1 reading per day anonymous
  • 3 per day signed-in
  • Unlimited on subscription

What I'm looking for

  • General UX feedback — is the page clear? Does it feel respectful or like fortune-cookie BS?
  • I Ching practitioners — does the system prompt feel grounded or shallow?
  • Other devs — anything you'd structure differently in the auth/payment/share flow?

Solo builder in Malaysia. Happy to answer technical questions or hear honest criticism. 🙏