Futures
Access hundreds of perpetual contracts
TradFi
Gold
One platform for global traditional assets
Options
Hot
Trade European-style vanilla options
Unified Account
Maximize your capital efficiency
Demo Trading
Introduction to Futures Trading
Learn the basics of futures trading
Futures Events
Join events to earn rewards
Demo Trading
Use virtual funds to practice risk-free trading
Launch
CandyDrop
Collect candies to earn airdrops
Launchpool
Quick staking, earn potential new tokens
HODLer Airdrop
Hold GT and get massive airdrops for free
Launchpad
Be early to the next big token project
Alpha Points
Trade on-chain assets and earn airdrops
Futures Points
Earn futures points and claim airdrop rewards
I've always wanted to build an AI health management system for myself and my family, gradually filling it in with each checkup, doctor visit, and medication. These past few days while visiting my parents, I set up theirs too.
Inspired by @coolish's previous health management approach, I built this in a day using Claude Code + Obsidian:
📸 Photograph medicine boxes → AI automatically identifies drug names, dosages, frequency
📋 Photograph health reports (30+ pages) → AI reads each page, extracts abnormal markers, establishes trend comparisons
🗂 Organize by family member → Medical history, medication lists, follow-up timelines
📅 Generate follow-up calendar → Which tests are due, which ones are overdue—everything at a glance
📝 Output daily management plans → Dietary restrictions, exercise recommendations, warning signs for medical attention
💬 Simplified version → Convert key points into conversational language to send to parents
The biggest takeaway wasn't technical:
During the process, I discovered several things I had no idea about—one marker consistently elevated over multiple checks, a medication dosage that needs adjustment, a follow-up already overdue by a month.
Elderly people aren't deliberately hiding things from you; they simply can't remember and don't take it seriously themselves.
I also exported 4 years of Apple Watch health data and had AI analyze it. 3.39 million records, processed in minutes: VO2Max dropped 5 points over six months, weekday steps 2,000 fewer than weekends. The cost of sitting and coding all day—data doesn't lie.
The tools are simple: Claude Code as entry point, Obsidian for storage, Mac Calendar for reminders. No need for any medical AI products; existing tools work perfectly.
Seeing Zhang Xuefeng's message today makes me feel this can't be delayed. One annual checkup is a snapshot; daily health management is real monitoring.
Long-term goal: equip each family member with an AI health assistant they can chat with—no AI expertise needed, just ask directly about daily health issues. For now, I'm building a solid data foundation.